Merge remote-tracking branch 'origin/main' into docs/stale-migration

# Conflicts:
#	docs/migration/api-changes.mdx

.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "mem0",
       "source": "./integrations/mem0-plugin",
       "description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search to Claude workflows.",
-      "version": "0.2.10"
+      "version": "0.2.11"
     }
   ]
 }

.cursor-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "mem0",
       "source": "./integrations/mem0-plugin",
       "description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search.",
-      "version": "0.2.10"
+      "version": "0.2.11"
     }
   ]
 }

.gitignore

@@ -189,3 +189,5 @@ eval/
 qdrant_storage/
 .crossnote
 testing.ipynb
+.weave/
+

CONTRIBUTING.md

@@ -1,72 +1,157 @@
-# Contributing to mem0
+# Contributing to Mem0
 
-Let us make contribution easy, collaborative and fun.
+First off, thank you for taking the time to contribute! 🎉 Mem0 is a
+community-driven project and we welcome contributions of all kinds — bug fixes,
+new features, documentation, examples, and integrations.
 
-## Submit your Contribution through PR
+Mem0 is a polyglot monorepo, and this guide covers contributing to both the
+**Python SDK** and the **TypeScript SDK** (and the rest of the repository).
 
-To make a contribution, follow these steps:
+## Before You Start
 
-1. Fork and clone this repository
-2. Do the changes on your fork with dedicated feature branch `feature/f1`
-3. If you modified the code (new feature or bug-fix), please add tests for it
-4. Include proper documentation / docstring and examples to run the feature
-5. Ensure that all tests pass
-6. Submit a pull request
+### 1. Open an Issue First
 
-For more details about pull requests, please read [GitHub's guides](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request).
+**Always open an issue before opening a pull request.** This lets us discuss the
+change, avoid duplicate effort, and agree on the approach before you invest time
+in code.
 
+- Search [existing issues](https://github.com/mem0ai/mem0/issues) first to see if
+  your bug or idea already exists.
+- If it doesn't, open a
+  [bug report](https://github.com/mem0ai/mem0/issues/new?template=bug_report.yml) or
+  [feature request](https://github.com/mem0ai/mem0/issues/new?template=feature_request.yml).
+- For anything beyond a trivial fix, wait for a maintainer to confirm the approach
+  before starting significant work.
 
-### 📦 Development Environment
+Every pull request must link to an issue using `Closes #<issue-number>`.
 
-We use `hatch` for managing development environments. To set up:
+### 2. Sign the Contributor License Agreement (CLA)
+
+**We cannot accept or merge any pull request until you have signed our Contributor
+License Agreement (CLA).**
+
+When you open your first PR, the CLA bot will automatically comment with a link to
+sign. Signing takes less than a minute and only needs to be done once. Pull
+requests from contributors who have not signed the CLA will be blocked from
+merging.
+
+## Repository Layout
+
+The two most common contribution targets are the SDKs:
+
+| Package               | Path       | Language     | Package manager |
+| --------------------- | ---------- | ------------ | --------------- |
+| Python SDK (`mem0ai`) | `mem0/`    | Python 3.9+  | `hatch`         |
+| TypeScript SDK (`mem0ai`) | `mem0-ts/` | TypeScript | `pnpm`        |
+
+Other packages include the CLIs (`cli/python/`, `cli/node/`), integrations
+(`integrations/`), the self-hosted `server/`, `openmemory/`, and the docs site
+(`docs/`). See [AGENTS.md](./AGENTS.md) for a full map of the repository.
+
+## Development Workflow
+
+1. **Fork** the repository and **clone** your fork.
+2. Create a **feature branch** from `main` (e.g. `feature/my-new-feature` or
+   `fix/issue-1234`).
+3. Make your changes — add **tests**, **documentation**, and **examples** as
+   appropriate.
+4. Run **linting and tests** for every package you touched (see below).
+5. Commit using [Conventional Commits](https://www.conventionalcommits.org/)
+   (e.g. `feat:`, `fix:`, `docs:`, `refactor:`, `test:`).
+6. Push and open a **pull request** against `main`, linking the issue with
+   `Closes #<number>` and filling out the
+   [PR template](./.github/PULL_REQUEST_TEMPLATE.md).
+
+### Contributing to the Python SDK (`mem0/`)
+
+We use [`hatch`](https://hatch.pypa.io/latest/install/) to manage environments.
+**Do not use `pip` or `conda` for dependency management.**
 
 ```bash
-# Activate environment for specific Python version:
-hatch shell dev_py_3_9   # Python 3.9
-hatch shell dev_py_3_10  # Python 3.10  
-hatch shell dev_py_3_11  # Python 3.11
-hatch shell dev_py_3_12  # Python 3.12
+# Activate a dev environment (3.9 / 3.10 / 3.11 / 3.12)
+hatch shell dev_py_3_11
 
-# The environment will automatically install all dev dependencies
-# Run tests within the activated shell:
-make test
-```
-
-### 📌 Pre-commit
-
-To ensure our standards, make sure to install pre-commit before starting to contribute.
-
-```bash
+# Install pre-commit hooks (runs ruff + isort on commit)
 pre-commit install
+
+# Lint, format, and sort imports
+make lint
+make format
+make sort
+
+# Run the test suite (run `make install_all` first if deps are missing)
+make test
 ```
 
-### 🧪 Testing
+- **Linter / formatter:** Ruff (line length **120**)
+- **Import sorting:** isort (`profile = "black"`)
+- **Tests:** pytest (in `tests/`)
 
-We use `pytest` to test our code across multiple Python versions. You can run tests using:
+See the full [Development guide](https://docs.mem0.ai/contributing/development) for
+environment details.
+
+### Contributing to the TypeScript SDK (`mem0-ts/`)
+
+We use [`pnpm`](https://pnpm.io/) (v10+) for all TypeScript packages. **Do not use
+`npm` or `yarn`.**
 
 ```bash
-# Run tests with default Python version
-make test
+cd mem0-ts
+pnpm install
 
-# Test specific Python versions:
-make test-py-3.9   # Python 3.9 environment
-make test-py-3.10  # Python 3.10 environment
-make test-py-3.11  # Python 3.11 environment
-make test-py-3.12  # Python 3.12 environment
-
-# When using hatch shells, run tests with:
-make test  # After activating a shell with hatch shell test_XX
+pnpm run build        # tsup (CJS + ESM)
+pnpm run test         # jest (all tests)
+pnpm run test:unit    # unit tests with coverage
 ```
 
-Make sure that all tests pass across all supported Python versions before submitting a pull request.
+- **Build:** tsup
+- **Formatter:** Prettier
+- **Tests:** jest
+- Always run type checking after changes: `pnpm run typecheck` (or `tsc --noEmit`).
+- Use ES module `import` syntax — never `require()`.
 
-We look forward to your pull requests and can't wait to see your contributions!
+## Good Contribution Practices
 
-### 🚀 Releasing
+- **Keep PRs small and focused.** One logical change per PR is easier to review and
+  merge.
+- **Follow existing patterns.** Match the style, structure, and conventions of the
+  code around you. Don't introduce new frameworks or abstractions without
+  discussion.
+- **Write tests** that would fail without your change — regression tests for bugs,
+  coverage for new features.
+- **Update documentation** in `docs/` for any user-facing change. New `.mdx` pages
+  must be added to `docs/llms.txt` (run
+  `python scripts/check-llms-txt-coverage.py --write` to scaffold entries).
+- **Add examples** when introducing new user-facing behavior.
+- **Run linters and tests locally** before pushing — CI re-runs them on every PR
+  via the CI Gate.
+- **Never commit secrets** — no `.env` files, API keys, or credentials.
+- **Don't add core dependencies lightly.** New Python dependencies belong in an
+  optional group in `pyproject.toml`, not the core `dependencies` list.
+- **Be responsive** to review feedback and keep your branch up to date with `main`.
 
-All packages are published automatically via GitHub Actions when a GitHub Release is created with the correct tag prefix.
+## Pull Request Checklist
 
-#### Tag Prefixes
+Before requesting review, make sure:
+
+- [ ] An issue exists and is linked with `Closes #<number>`
+- [ ] You have signed the CLA
+- [ ] Your code follows the project's style guidelines (lint passes)
+- [ ] You performed a self-review of your changes
+- [ ] Tests are added/updated and pass locally
+- [ ] Documentation is updated if needed
+
+## Reporting Security Issues
+
+**Do not report security vulnerabilities through public issues or pull requests.**
+Please follow our [Security Policy](./SECURITY.md) to report them privately.
+
+## Releasing
+
+All packages are published automatically via GitHub Actions when a GitHub Release
+is created with the correct tag prefix.
+
+### Tag Prefixes
 
 | Package | Registry | Tag Prefix | Example |
 |---------|----------|------------|---------|
@@ -77,15 +162,17 @@ All packages are published automatically via GitHub Actions when a GitHub Releas
 | `@mem0/vercel-ai-provider` | npm | `vercel-ai-v*` | `vercel-ai-v2.0.6` |
 | `@mem0/openclaw-mem0` | npm | `openclaw-v*` | `openclaw-v1.0.1` |
 
-#### How to Release
+### How to Release
 
 1. Bump the version in `pyproject.toml` (Python) or `package.json` (Node)
 2. Create a [GitHub Release](https://github.com/mem0ai/mem0/releases/new) with the matching tag prefix
 3. The correct workflow will trigger automatically — verify in the [Actions tab](https://github.com/mem0ai/mem0/actions)
 
-#### Publishing Details
+### Publishing Details
 
 - **PyPI packages** use OIDC trusted publishing via `pypa/gh-action-pypi-publish`
 - **npm packages** use OIDC trusted publishing via npm CLI (>= 11.5.1) — no tokens or secrets required
 - All workflows require `permissions: id-token: write` for OIDC authentication
 - First publish of a new npm package must be done manually; OIDC works for subsequent versions
+
+We look forward to your pull requests and can't wait to see your contributions!

SECURITY.md

@@ -0,0 +1,48 @@
+# Security Policy
+
+We take the security of Mem0 and our community seriously. Thank you for helping
+keep Mem0 and its users safe by disclosing vulnerabilities responsibly.
+
+## Reporting a Vulnerability
+
+Please **do not** report security vulnerabilities through public GitHub issues,
+pull requests, or discussions.
+
+If you believe you have found a security vulnerability in Mem0, please report it
+privately through one of the following channels:
+
+1. **GitHub Private Vulnerability Reporting** — open a
+   [private security advisory](https://github.com/mem0ai/mem0/security/advisories/new)
+   directly on this repository.
+2. **Email** the maintainers at **support@mem0.ai** with the subject line:
+
+   `SECURITY: Mem0 vulnerability report`
+
+To help us triage and resolve the issue quickly, please include as much of the
+following as you can:
+
+- Affected component or package (e.g. Python SDK, TypeScript SDK, server, OpenMemory)
+- Affected version, tag, or commit
+- Clear, step-by-step reproduction instructions
+- The security impact and a proof of concept, if available
+- Any suggested fix or mitigation
+
+## Response Process
+
+- We will acknowledge receipt of your report within **72 hours**.
+- We will work with you privately to confirm the issue and assess its impact.
+- Once a fix or mitigation is ready, we will coordinate a disclosure timeline
+  with you and credit you for the discovery, unless you prefer to remain anonymous.
+
+## Public Disclosure
+
+Please avoid sharing technical details of the vulnerability publicly until the
+maintainers have reviewed the issue and a fix or mitigation has been released. We
+are committed to resolving valid reports promptly and keeping you informed
+throughout the process.
+
+## Supported Versions
+
+We release security fixes against the latest published version of each package.
+Whenever possible, please reproduce the issue on the most recent release before
+reporting.

cli/node/CHANGELOG.md

@@ -5,6 +5,15 @@ All notable changes to `@mem0/cli` are documented here.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.9] — 2026-06-19
+
+### Security
+
+- Telemetry no longer passes the Mem0 API key to its child process via
+  command-line arguments. The context is now sent over stdin, so the key is no
+  longer visible in the process list (`ps`, `/proc/<pid>/cmdline`, Activity
+  Monitor). Fixes #4862.
+
 ## [0.2.8] — 2026-06-01
 
 ### Security

cli/node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mem0/cli",
-  "version": "0.2.8",
+  "version": "0.2.9",
   "description": "The official CLI for mem0 — the memory layer for AI agents",
   "type": "module",
   "bin": {

cli/node/src/telemetry.ts

@@ -145,11 +145,11 @@ export function captureEvent(
 			anonDistinctIdToAlias: anonIdToAlias,
 		};
 
-		const child = spawn(
-			process.execPath,
-			[SENDER_SCRIPT, JSON.stringify(context)],
-			{ detached: true, stdio: "ignore" },
-		);
+		const child = spawn(process.execPath, [SENDER_SCRIPT], {
+			detached: true,
+			stdio: ["pipe", "ignore", "ignore"],
+		});
+		child.stdin?.end(JSON.stringify(context));
 		child.unref();
 	} catch {
 		/* silently swallow */

cli/node/telemetry-sender.cjs

@@ -1,7 +1,8 @@
 /**
  * Standalone telemetry sender — runs as a detached child process.
  *
- * Usage: node telemetry-sender.cjs '<json context>'
+ * Usage: node telemetry-sender.cjs   (JSON context is read from stdin; a single
+ * argv argument is still accepted as a legacy fallback)
  *
  * This script is spawned by telemetry.captureEvent() and runs independently
  * of the parent CLI process. It:
@@ -19,6 +20,31 @@
 const https = require("https");
 const fs = require("fs");
 
+function loadContext() {
+	return new Promise((resolve, reject) => {
+		if (process.argv[2]) {
+			try {
+				resolve(JSON.parse(process.argv[2]));
+			} catch (err) {
+				reject(err);
+			}
+			return;
+		}
+
+		let data = "";
+		process.stdin.setEncoding("utf8");
+		process.stdin.on("data", (chunk) => (data += chunk));
+		process.stdin.on("end", () => {
+			try {
+				resolve(JSON.parse(data));
+			} catch (err) {
+				reject(err);
+			}
+		});
+		process.stdin.on("error", reject);
+	});
+}
+
 function httpsRequest(url, method, headers, body) {
 	return new Promise((resolve, reject) => {
 		const u = new URL(url);
@@ -108,7 +134,7 @@ async function sendIdentifyEvent(ctx, payload, anonId) {
 }
 
 async function main() {
-	const ctx = JSON.parse(process.argv[2]);
+	const ctx = await loadContext();
 	const payload = ctx.payload;
 
 	if (ctx.needsEmail && ctx.mem0ApiKey) {

cli/node/tests/telemetry.test.ts

@@ -0,0 +1,59 @@
+import { beforeEach, describe, expect, it, vi } from "vitest";
+
+const mockLoadConfig = vi.fn();
+const mockSaveConfig = vi.fn();
+const mockSpawn = vi.fn();
+
+vi.mock("../src/config.js", () => ({
+  CONFIG_FILE: "/tmp/mem0-config.json",
+  loadConfig: mockLoadConfig,
+  saveConfig: mockSaveConfig,
+}));
+
+vi.mock("node:child_process", () => ({
+  spawn: mockSpawn,
+}));
+
+describe("captureEvent", () => {
+  beforeEach(() => {
+    vi.resetModules();
+    mockLoadConfig.mockReset();
+    mockSaveConfig.mockReset();
+    mockSpawn.mockReset();
+    delete process.env.MEM0_TELEMETRY;
+  });
+
+  it("pipes the telemetry context through stdin instead of argv", async () => {
+    mockLoadConfig.mockReturnValue({
+      platform: {
+        apiKey: "m0-node-secret",
+        baseUrl: "https://api.mem0.ai",
+        userEmail: "",
+      },
+      telemetry: {
+        anonymousId: "cli-anon-node",
+      },
+    });
+
+    const stdin = { end: vi.fn() };
+    const child = { stdin, unref: vi.fn() };
+    mockSpawn.mockReturnValue(child);
+
+    const { captureEvent } = await import("../src/telemetry.js");
+    captureEvent("node_test_event", { case: "stdin-secret" });
+
+    expect(mockSpawn).toHaveBeenCalledTimes(1);
+    const [execPath, args, options] = mockSpawn.mock.calls[0];
+    expect(execPath).toBe(process.execPath);
+    expect(args).toHaveLength(1);
+    expect(String(args[0])).toContain("telemetry-sender.cjs");
+    expect(JSON.stringify(args)).not.toContain("m0-node-secret");
+    expect(options).toMatchObject({ detached: true, stdio: ["pipe", "ignore", "ignore"] });
+
+    expect(stdin.end).toHaveBeenCalledTimes(1);
+    const payload = JSON.parse(stdin.end.mock.calls[0][0]);
+    expect(payload.mem0ApiKey).toBe("m0-node-secret");
+    expect(payload.payload.event).toBe("node_test_event");
+    expect(child.unref).toHaveBeenCalledTimes(1);
+  });
+});

cli/python/CHANGELOG.md

@@ -5,6 +5,19 @@ All notable changes to `mem0-cli` (Python) are documented here.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.8] — 2026-06-19
+
+### Security
+
+- Telemetry no longer passes the Mem0 API key to its child process via
+  command-line arguments. The context is now sent over stdin, so the key is no
+  longer visible in the process list (`ps`, `/proc/<pid>/cmdline`, Activity
+  Monitor). Fixes #4862.
+
+### Fixed
+
+- `__version__` now matches the packaged version (was stale at 0.2.4).
+
 ## [0.2.7] — 2026-05-20
 
 ### Added

cli/python/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "mem0-cli"
-version = "0.2.7"
+version = "0.2.8"
 description = "The official CLI for mem0 — the memory layer for AI agents"
 readme = "README.md"
 license = "Apache-2.0"

cli/python/src/mem0_cli/__init__.py

@@ -1,3 +1,3 @@
 """mem0 CLI — the command-line interface for the mem0 memory layer."""
 
-__version__ = "0.2.4"
+__version__ = "0.2.8"

cli/python/src/mem0_cli/telemetry.py

@@ -137,12 +137,19 @@ def capture_event(
             "anon_distinct_id_to_alias": anon_id_to_alias,
         }
 
-        subprocess.Popen(
-            [sys.executable, "-m", "mem0_cli.telemetry_sender", json.dumps(context)],
+        child = subprocess.Popen(
+            [sys.executable, "-m", "mem0_cli.telemetry_sender"],
+            stdin=subprocess.PIPE,
             stdout=subprocess.DEVNULL,
             stderr=subprocess.DEVNULL,
             start_new_session=True,
             close_fds=True,
+            text=True,
         )
+        if child.stdin:
+            with contextlib.suppress(Exception):
+                child.stdin.write(json.dumps(context))
+            with contextlib.suppress(Exception):
+                child.stdin.close()
     except Exception:
         pass

cli/python/src/mem0_cli/telemetry_sender.py

@@ -1,6 +1,7 @@
 """Standalone telemetry sender — runs as a detached subprocess.
 
-Usage: python -m mem0_cli.telemetry_sender '<json context>'
+Usage: python -m mem0_cli.telemetry_sender   (JSON context is read from stdin;
+a single argv argument is still accepted as a legacy fallback)
 
 This module is spawned by telemetry.capture_event() and runs independently
 of the parent CLI process. It:
@@ -20,8 +21,18 @@ import sys
 import urllib.request
 
 
+def _load_context() -> dict:
+    """Load telemetry context from stdin, falling back to argv for compatibility."""
+    raw = ""
+    if not sys.stdin.isatty():
+        raw = sys.stdin.read().strip()
+    if not raw and len(sys.argv) > 1:
+        raw = sys.argv[1]
+    return json.loads(raw)
+
+
 def main() -> None:
-    ctx = json.loads(sys.argv[1])
+    ctx = _load_context()
     payload = ctx["payload"]
 
     if ctx.get("needs_email") and ctx.get("mem0_api_key"):

cli/python/tests/test_telemetry.py

@@ -0,0 +1,80 @@
+"""Tests for telemetry subprocess secret handling."""
+
+from __future__ import annotations
+
+import io
+import json
+import subprocess
+import sys
+
+from mem0_cli.config import Mem0Config, save_config
+from mem0_cli.telemetry import capture_event
+from mem0_cli.telemetry_sender import _load_context
+
+
+class _CaptureStdin:
+    def __init__(self):
+        self.buffer = ""
+        self.closed = False
+
+    def write(self, value: str) -> None:
+        self.buffer += value
+
+    def close(self) -> None:
+        self.closed = True
+
+
+class _DummyProcess:
+    def __init__(self):
+        self.stdin = _CaptureStdin()
+
+
+def test_capture_event_writes_context_to_stdin_not_argv(isolate_config, monkeypatch):
+    config = Mem0Config()
+    config.platform.api_key = "m0-test-secret"
+    config.telemetry.anonymous_id = "cli-anon-test"
+    save_config(config)
+
+    captured: dict[str, object] = {}
+    proc = _DummyProcess()
+
+    def fake_popen(args, **kwargs):
+        captured["args"] = args
+        captured["kwargs"] = kwargs
+        return proc
+
+    monkeypatch.setattr("mem0_cli.telemetry.subprocess.Popen", fake_popen)
+
+    capture_event("unit_test_event", {"case": "stdin-secret"})
+
+    argv = captured["args"]
+    assert argv == [sys.executable, "-m", "mem0_cli.telemetry_sender"]
+    assert all("m0-test-secret" not in arg for arg in argv)
+
+    kwargs = captured["kwargs"]
+    assert kwargs["stdin"] == subprocess.PIPE
+    assert kwargs["text"] is True
+
+    ctx = json.loads(proc.stdin.buffer)
+    assert ctx["mem0_api_key"] == "m0-test-secret"
+    assert ctx["payload"]["event"] == "unit_test_event"
+
+    assert proc.stdin.closed
+
+
+def test_load_context_reads_from_stdin(monkeypatch):
+    monkeypatch.setattr("sys.argv", ["telemetry_sender"])
+    monkeypatch.setattr("sys.stdin", io.StringIO('{"payload": {"event": "stdin"}}'))
+
+    ctx = _load_context()
+
+    assert ctx["payload"]["event"] == "stdin"
+
+
+def test_load_context_falls_back_to_argv(monkeypatch):
+    monkeypatch.setattr("sys.argv", ["telemetry_sender", '{"payload": {"event": "argv"}}'])
+    monkeypatch.setattr("sys.stdin", io.StringIO(""))
+
+    ctx = _load_context()
+
+    assert ctx["payload"]["event"] == "argv"

docs/api-reference/memory/add-memories.mdx

@@ -50,6 +50,7 @@ Provide conversation messages for Mem0 to extract memories from. At least one en
 | `app_id` | string | No* | Associates the memory with an app. |
 | `metadata` | object | Optional | Custom key/value metadata (e.g., `{"topic": "preferences"}`). |
 | `infer` | boolean (default `true`) | Optional | Set to `false` to skip inference and store the provided text as-is. |
+| `expiration_date` | string | Optional | Date in `YYYY-MM-DD` format. The memory is visible through this date and hidden by default after it passes. |
 
 > \* At least one entity ID (`user_id`, `agent_id`, `app_id`, or `run_id`) is required.
 
@@ -83,3 +84,11 @@ The request is queued for background processing. The response contains an `event
 <Info>
 Poll the event status via `GET /v1/event/{event_id}/`. Status will be `SUCCEEDED` or `FAILED` once processing completes.
 </Info>
+
+<Info>
+Memories with `expiration_date` remain stored after they expire. Search and get-all hide them by default; pass `show_expired: true` to include them.
+</Info>
+
+<Info>
+Python uses `expiration_date`; TypeScript uses `expirationDate`.
+</Info>

docs/api-reference/memory/create-memory-export.mdx

@@ -4,4 +4,4 @@ description: "Submit an export job to create a structured memory export using a
 openapi: post /v1/exports/
 ---
 
-Submit a job to create a structured export of memories using a customizable Pydantic schema. This process may take some time to complete, especially if you're exporting a large number of memories. You can tailor the export by applying various filters (e.g., `user_id`, `agent_id`, `run_id`, or `session_id`) and by modifying the Pydantic schema to ensure the final data matches your exact needs.
+Submit a job to create a structured export of memories using a customizable Pydantic schema. This process may take some time to complete, especially if you're exporting a large number of memories. You can tailor the export by applying various filters (e.g., `user_id`, `agent_id`, `app_id`, or `run_id`) and by modifying the Pydantic schema to ensure the final data matches your exact needs.

docs/api-reference/memory/get-memories.mdx

@@ -6,6 +6,10 @@ openapi: post /v3/memories/
 
 List memories scoped by filters with paginated results. Entity IDs (`user_id`, `agent_id`, `app_id`, `run_id`) **must** be passed inside the `filters` object — top-level entity IDs are rejected with 400.
 
+Expired memories are hidden by default. Pass `show_expired: true` to include memories whose `expiration_date` has passed.
+
+Python uses `show_expired`; TypeScript uses `showExpired`.
+
 The `filters` object supports complex logical operations (AND, OR, NOT) and comparison operators:
 
 - `in`: Matches any of the values specified
@@ -32,6 +36,7 @@ memories = client.get_all(
             }
         ]
     },
+    show_expired=False,
     page=1,
     page_size=50
 )
@@ -46,12 +51,14 @@ memories = client.get_all(
         {
             "id": "f4cbdb08-7062-4f3e-8eb2-9f5c80dfe64c",
             "memory": "Alex is planning a trip to San Francisco from July 1st to July 10th",
+            "expiration_date": null,
             "created_at": "2024-07-01T12:00:00Z",
             "updated_at": "2024-07-01T12:00:00Z"
         },
         {
             "id": "a2b8c3d4-5e6f-7g8h-9i0j-1k2l3m4n5o6p",
             "memory": "Alex prefers vegetarian restaurants",
+            "expiration_date": null,
             "created_at": "2024-07-05T15:30:00Z",
             "updated_at": "2024-07-05T15:30:00Z"
         }

docs/api-reference/memory/get-memory-export.mdx

@@ -4,4 +4,4 @@ description: "Retrieve the latest structured memory export after submitting an e
 openapi: post /v1/exports/get
 ---
 
-Retrieve the latest structured memory export after submitting an export job. You can filter the export by `user_id`, `run_id`, `session_id`, or `app_id` to get the most recent export matching your filters.
+Retrieve the latest structured memory export after submitting an export job. You can filter the export by `user_id`, `agent_id`, `app_id`, `run_id`, `created_at`, or `updated_at` to get the most recent export matching your filters.

docs/api-reference/memory/search-memories.mdx

@@ -8,6 +8,10 @@ Relevance-ranked hybrid search across stored memories. V3 uses multi-signal retr
 
 Entity IDs (`user_id`, `agent_id`, `app_id`, `run_id`) **must** be passed inside the `filters` object — top-level entity IDs are rejected with 400. At least one entity ID is required.
 
+Expired memories are hidden by default. Pass `show_expired: true` to include memories whose `expiration_date` has passed.
+
+Python uses `show_expired`; TypeScript uses `showExpired`.
+
 The `filters` object supports complex logical operations (AND, OR, NOT) and comparison operators:
 - `in`: Matches any of the values specified
 - `gte`: Greater than or equal to
@@ -20,16 +24,17 @@ The `filters` object supports complex logical operations (AND, OR, NOT) and comp
 
 ### Search parameter defaults
 
-| Parameter | V1/V2 | V3 |
-| --- | --- | --- |
-| `top_k` | Supported (default 10) | Supported (1-1000, default 10) |
-| `threshold` | No default | Default `0.1` (pass `0.0` to disable) |
-| `rerank` | Default `true` | Default `false` (pass `true` to enable) |
+| Parameter | Default |
+| --- | --- |
+| `top_k` | `10` (range 1–1000) |
+| `threshold` | `0.1` (pass `0.0` to disable) |
+| `rerank` | `false` (pass `true` to enable) |
 
 <CodeGroup>
 ```python Platform API Example
 related_memories = client.search(
     query="What are Alice's hobbies?",
+    show_expired=False,
     filters={
         "OR": [
             {
@@ -54,6 +59,7 @@ related_memories = client.search(
         "category": "hobbies"
       },
       "score": 0.82,
+      "expiration_date": null,
       "created_at": "2024-07-26T10:29:36.630547-07:00",
       "updated_at": null,
       "categories": ["hobbies"]

docs/api-reference/memory/update-memory.mdx

@@ -1,5 +1,14 @@
 ---
 title: 'Update Memory'
-description: "Update the content or metadata of a single memory by its unique ID using the PUT endpoint."
+description: "Update the content, metadata, timestamp, or expiration date of a single memory by its unique ID using the PUT endpoint."
 openapi: put /v1/memories/{memory_id}/
----
+---
+
+Use this endpoint to update mutable memory fields. To make a memory expire, set `expiration_date` to a `YYYY-MM-DD` date. To make it permanent again, send `expiration_date: null`.
+
+```python
+client.update("mem_123", expiration_date="2030-01-31")
+client.update("mem_123", expiration_date=None)
+```
+
+TypeScript uses `expirationDate`.

docs/api-reference/organization/remove-org-member.mdx

@@ -0,0 +1,5 @@
+---
+title: "Remove Organization Member"
+description: "Remove a member from an organization to revoke their access to its projects and resources."
+openapi: "delete /api/v1/orgs/organizations/{org_id}/members/"
+---

docs/api-reference/organization/update-org-member.mdx

@@ -0,0 +1,5 @@
+---
+title: "Update Organization Member"
+description: "Update an existing member's role within an organization to change their permissions and access level."
+openapi: "put /api/v1/orgs/organizations/{org_id}/members/"
+---

docs/api-reference/organizations-projects.mdx

@@ -14,7 +14,7 @@ Organizations and projects are **optional** features. You can use Mem0 without t
 
 ## Key Capabilities
 
-- **Multi-org/project Support**: Specify organization and project when initializing the Mem0 client to attribute API usage appropriately
+- **Multi-org/project Support**: Organization and project are resolved automatically from your API key via `/v1/ping/` — no org or project params are accepted by `MemoryClient.__init__`. Use a project-specific API key to target a particular project.
 - **Member Management**: Control access to data through organization and project membership
 - **Access Control**: Only members can access memories and data within their organization/project scope
 - **Team Isolation**: Maintain data separation between different teams and projects for secure collaboration
@@ -79,7 +79,7 @@ new_project = client.project.create(
 
 ### Update Project Settings
 
-Modify project configuration including custom instructions, categories, and language preferences:
+Modify project configuration including custom instructions, categories, language preferences, retrieval criteria, and memory decay:
 
 ```python
 # Update project with custom categories
@@ -98,6 +98,17 @@ client.project.update(
 # Use the input language for memory storage and retrieval
 client.project.update(multilingual=True)
 
+# Set retrieval criteria to control which memories are surfaced in search
+client.project.update(
+    retrieval_criteria=[
+        {"name": "relevance", "description": "How directly relevant this memory is to the current topic or user query", "weight": 3},
+        {"name": "access_frequency", "description": "How often this memory has been accessed or surfaced recently", "weight": 1}
+    ]
+)
+
+# Enable Memory Decay (boosts recently-accessed memories at search time)
+client.project.update(decay=True)
+
 # Update multiple settings at once
 client.project.update(
     custom_instructions="...",
@@ -109,6 +120,34 @@ client.project.update(
 )
 ```
 
+#### Set Retrieval Criteria
+
+`retrieval_criteria` is a per-project list of dictionaries (`List[Dict]`) that shapes how memories are ranked and filtered during search. Each dictionary has three fields: `name` (identifier), `description` (interpreted by the LLM to score each memory), and `weight` (relative influence on the final score). Use this to focus retrieval on intent-aligned or signal-specific memories:
+
+```python
+client.project.update(
+    retrieval_criteria=[
+        {
+            "name": "joy",
+            "description": "Measure the intensity of positive emotions such as happiness, excitement, or amusement expressed in the memory. A higher score reflects greater joy.",
+            "weight": 3
+        },
+        {
+            "name": "curiosity",
+            "description": "Assess the extent to which the memory reflects inquisitiveness or interest in exploring new information. A higher score reflects stronger curiosity.",
+            "weight": 2
+        },
+        {
+            "name": "access_frequency",
+            "description": "How often this memory has been accessed or surfaced recently.",
+            "weight": 1
+        }
+    ]
+)
+```
+
+Pass an empty list to clear all criteria and restore default retrieval behaviour.
+
 #### Toggle Memory Decay
 
 `decay` is a per-project boolean that turns on [Memory Decay](/platform/features/memory-decay) — a search-time ranking bias that reinforces recently-accessed memories and gently dampens stale ones. The flag is `false` by default; set it via the same project-update endpoint:

docs/api-reference/project/remove-project-member.mdx

@@ -0,0 +1,5 @@
+---
+title: "Remove Project Member"
+description: "Remove a member from a project to revoke their access to its memories, configuration, and resources."
+openapi: "delete /api/v1/orgs/organizations/{org_id}/projects/{project_id}/members/"
+---

docs/api-reference/project/update-project-member.mdx

@@ -0,0 +1,5 @@
+---
+title: "Update Project Member"
+description: "Update an existing member's role within a project to change their permissions and access level."
+openapi: "put /api/v1/orgs/organizations/{org_id}/projects/{project_id}/members/"
+---

docs/api-reference/project/update-project.mdx

@@ -0,0 +1,5 @@
+---
+title: "Update Project"
+description: "Update a project's settings, including name, custom instructions, and other configuration options."
+openapi: "patch /api/v1/orgs/organizations/{org_id}/projects/{project_id}/"
+---

docs/changelog/highlights.mdx

@@ -46,9 +46,9 @@ Ground-up rewrite of the memory pipeline with 20+ point benchmark improvements:
 - **~3-4x fewer tokens** — Under 7K tokens per retrieval vs 25K+ for full-context approaches
 - **ADD-only extraction** — Memories accumulate; nothing is overwritten or deleted
 - **Hybrid retrieval** — Semantic + BM25 keyword + entity boost, scored in parallel
-- **Entity linking** — Entities extracted, embedded, and linked across memories
+- **Graph memory (built-in)**: entities extracted, embedded, and linked across memories, with no external graph store required
 
-Breaking changes: Graph memory removed from OSS, `search()` defaults changed, deprecated params removed. See [migration guide](/migration/oss-v2-to-v3).
+Breaking changes: external graph stores removed from OSS (replaced by built-in graph memory), `search()` defaults changed, deprecated params removed. See [migration guide](/migration/oss-v2-to-v3).
 
 </Update>
 
@@ -113,7 +113,7 @@ Launched a unified Mem0 plugin across three major AI development environments
 
 Major expansion of the provider ecosystem:
 
-- **Apache AGE** — New graph store support, bringing the total to 4 graph store backends (Neo4j, Memgraph, Kuzu, Apache AGE)
+- **Apache AGE** — New graph store support, bringing the total to 4 graph store backends (Neo4j, Memgraph, Kuzu, Apache AGE). **Note:** All external graph store backends (Neo4j, Memgraph, Kuzu, Apache AGE) were subsequently removed in v2.0.0 (2026-04-14). Graph memory is now built-in entity linking with no external graph store required; see the [v2.0.0 entry above](#mem0-sdk-v2-0-0-v3-0-0).
 - **Turbopuffer** — New vector database provider for Python SDK
 - **MiniMax** — New LLM provider with dedicated AWS Bedrock support
 - **pgvector for Node.js** — PostgreSQL vector support added to the TypeScript OSS SDK

docs/changelog/platform.mdx

@@ -25,7 +25,7 @@ mode: "wide"
 <Update label="2026-04-16" description="">
 
 **Improvements:**
-- **UI:** Removed Graph Memory tab, page, and all references from dashboard, sidebar, project settings, playground, and billing
+- **UI:** Removed the legacy external-graph-store visualization tab, page, and its references from dashboard, sidebar, project settings, playground, and billing
 
 </Update>
 

docs/changelog/sdk.mdx

@@ -7,6 +7,100 @@ mode: "wide"
 <Tabs>
 <Tab title="Python">
 
+<Update label="2026-06-24" description="v2.0.9">
+
+**Bug Fixes:**
+- **Memory (OSS):** Improve entity extraction precision by avoiding sentence-start common noun noise, preserving useful topic phrases, and exact-deduplicating entity links before semantic matching ([#5829](https://github.com/mem0ai/mem0/pull/5829))
+
+</Update>
+
+<Update label="2026-06-24" description="v2.0.8">
+
+**New Features:**
+- **Embeddings:** Add native `embed_batch` to five embedders — LM Studio, Together, HuggingFace, Vertex AI, and Google GenAI — for batched embedding requests ([#5609](https://github.com/mem0ai/mem0/pull/5609))
+
+**Bug Fixes:**
+- **Core:** Guard against malformed `image_url` entries in `parse_vision_messages` to prevent crashes ([#5631](https://github.com/mem0ai/mem0/pull/5631))
+- **Core:** Return `attributed_to` from `get()`, `get_all()`, and `search()` ([#5629](https://github.com/mem0ai/mem0/pull/5629))
+- **Core:** Fix `reset()` only dropping the history table and leaving stale messages behind ([#5541](https://github.com/mem0ai/mem0/pull/5541))
+- **Core:** Guard against an entity `embed_batch` count mismatch in the v3 add pipeline ([#5604](https://github.com/mem0ai/mem0/pull/5604))
+- **Core:** Fix an async `delete_all` race condition that corrupted the entity store's `linked_memory_ids` ([#5553](https://github.com/mem0ai/mem0/pull/5553))
+- **LLMs:** Skip the JSON `response_format` for Groq compound models that reject it ([#5513](https://github.com/mem0ai/mem0/pull/5513))
+- **LLMs:** Preserve reasoning fields during base-to-provider config conversion ([#5638](https://github.com/mem0ai/mem0/pull/5638))
+- **LLMs:** Pass the configured `anthropic_base_url` to the Anthropic client ([#5626](https://github.com/mem0ai/mem0/pull/5626))
+- **LLMs:** Stop the Azure provider from mutating and corrupting caller messages during content rewrite ([#5731](https://github.com/mem0ai/mem0/pull/5731))
+- **LLMs & Embeddings:** Repair HTTP proxy support for `httpx>=0.28` and preserve `proxies` in `LlmFactory` ([#5447](https://github.com/mem0ai/mem0/pull/5447))
+- **Embeddings:** Forward `embedding_dims` to Titan V2 in the AWS Bedrock embedder ([#5671](https://github.com/mem0ai/mem0/pull/5671))
+- **Rerankers:** Log reranking failures instead of swallowing them silently ([#5717](https://github.com/mem0ai/mem0/pull/5717))
+- **Rerankers:** Clamp out-of-range LLM scores instead of mis-parsing them ([#5635](https://github.com/mem0ai/mem0/pull/5635))
+- **Rerankers:** Export all five rerankers from the package root ([#5636](https://github.com/mem0ai/mem0/pull/5636))
+- **Vector Stores:** Point the FastEmbed-missing warning at `mem0ai[extras]` ([#5622](https://github.com/mem0ai/mem0/pull/5622))
+- **Vector Stores:** Preserve empty Azure AI Search update values ([#5524](https://github.com/mem0ai/mem0/pull/5524))
+- **Vector Stores:** Add an `auto_refresh` option for OpenSearch Serverless compatibility ([#3893](https://github.com/mem0ai/mem0/pull/3893))
+- **Vector Stores:** Wrap a scalar `vector_id` in a list for Chroma `delete()` ([#5703](https://github.com/mem0ai/mem0/pull/5703))
+- **Vector Stores:** Wrap Chroma `update()` ids, embeddings, and metadatas in lists ([#5757](https://github.com/mem0ai/mem0/pull/5757))
+- **Vector Stores:** Wrap a scalar `vector_id` in a list for Milvus `delete()` ([#5704](https://github.com/mem0ai/mem0/pull/5704))
+- **Vector Stores:** Map all comparison operators in the Pinecone `_create_filter()` ([#5707](https://github.com/mem0ai/mem0/pull/5707))
+- **Vector Stores:** Return `None` instead of `{}` from Chroma `_generate_where_clause` for empty filters ([#5713](https://github.com/mem0ai/mem0/pull/5713))
+- **Vector Stores:** Return `[[]]` from the OpenSearch `list()` error path to honor the `list()` contract ([#5727](https://github.com/mem0ai/mem0/pull/5727))
+- **Vector Stores:** Return `[[]]` from the Pinecone `list()` error path instead of a dict ([#5706](https://github.com/mem0ai/mem0/pull/5706))
+- **Vector Stores:** Return `[[]]` for an uninitialized FAISS index to honor the `list()` contract ([#5725](https://github.com/mem0ai/mem0/pull/5725))
+- **Vector Stores:** Wrap the MongoDB `list()` return in an outer list to match the interface contract ([#5729](https://github.com/mem0ai/mem0/pull/5729))
+- **Vector Stores:** Deep-copy Redis `DEFAULT_FIELDS` so instances keep distinct dims ([#5633](https://github.com/mem0ai/mem0/pull/5633))
+- **Vector Stores:** Pass the required `vectors` arg in Vertex AI `list()` and similarity search ([#5627](https://github.com/mem0ai/mem0/pull/5627))
+- **Vector Stores:** Return `None` from Redis `get()` for missing IDs ([#5625](https://github.com/mem0ai/mem0/pull/5625))
+- **Vector Stores:** Drop a stray `print` in Weaviate `list_cols` ([#5637](https://github.com/mem0ai/mem0/pull/5637))
+- **Graph:** Keep distinct entities that share a substring prefix ([#5630](https://github.com/mem0ai/mem0/pull/5630))
+- **Client:** Check the HTTP status before parsing the ping response in `_validate_api_key` ([#5639](https://github.com/mem0ai/mem0/pull/5639))
+- **Server:** Fetch filtered dashboard memories beyond the default page ([#5753](https://github.com/mem0ai/mem0/pull/5753))
+- **Server:** Return 404/400 instead of 502 for not-found and invalid input ([#5634](https://github.com/mem0ai/mem0/pull/5634))
+- **Server:** Return 404 instead of 500 for a malformed API key id on revoke ([#5640](https://github.com/mem0ai/mem0/pull/5640))
+- **Server:** Use `127.0.0.1` in the dashboard healthcheck to avoid IPv6 localhost resolution ([#5612](https://github.com/mem0ai/mem0/pull/5612))
+
+**Improvements:**
+- **Vector Stores:** Batch BM25 sparse encoding in Qdrant insert ([#5592](https://github.com/mem0ai/mem0/pull/5592))
+
+**Security:**
+- **Vector Stores:** Sanitize Milvus and Baidu filter values to prevent expression injection ([#5746](https://github.com/mem0ai/mem0/pull/5746))
+- **Vector Stores:** Reject dict filter values in MongoDB to prevent NoSQL operator injection ([#5748](https://github.com/mem0ai/mem0/pull/5748))
+
+</Update>
+
+<Update label="2026-06-17" description="v2.0.7">
+
+**New Features:**
+- **LLMs:** Add Gemini via Vertex AI as LLM provider ([#4030](https://github.com/mem0ai/mem0/pull/4030))
+- **Embeddings:** Add native `embed_batch` to `OllamaEmbedding` for batched embedding requests ([#5415](https://github.com/mem0ai/mem0/pull/5415))
+
+**Bug Fixes:**
+- **Core:** Fix `api_error_handler` silently dropping return values from async methods ([#5540](https://github.com/mem0ai/mem0/pull/5540))
+- **Core:** Fix `AsyncMemory.reset()` not resetting the entity store ([#5535](https://github.com/mem0ai/mem0/pull/5535))
+- **Core:** Fix `async delete_all` aborting on first error, leaving partial deletion ([#5529](https://github.com/mem0ai/mem0/pull/5529))
+- **Core:** Skip messages without a `content` key in message parsers to prevent `KeyError` crashes ([#5575](https://github.com/mem0ai/mem0/pull/5575))
+- **Core:** Preserve custom metadata fields during memory update ([#5480](https://github.com/mem0ai/mem0/pull/5480))
+- **LLMs:** Fix Anthropic `tool_choice` format and tool response parsing ([#5537](https://github.com/mem0ai/mem0/pull/5537))
+- **LLMs:** Fix Ollama `json` format mutating the caller's messages list in-place ([#5539](https://github.com/mem0ai/mem0/pull/5539))
+- **LLMs:** Omit `None` config values from Gemini `GenerateContentConfig` to prevent validation errors ([#5528](https://github.com/mem0ai/mem0/pull/5528))
+- **LLMs:** Honor reasoning-model params in `AzureOpenAIStructuredLLM` ([#5548](https://github.com/mem0ai/mem0/pull/5548))
+- **LLMs:** Honor reasoning-model params in `OpenAIStructuredLLM` ([#5458](https://github.com/mem0ai/mem0/pull/5458))
+- **LLMs:** Send `max_completion_tokens` for the GPT-5 family across all providers ([#5547](https://github.com/mem0ai/mem0/pull/5547))
+- **LLMs:** Accept and forward `**kwargs` in Together, LangChain, and Sarvam providers ([#5556](https://github.com/mem0ai/mem0/pull/5556))
+- **LLMs:** Fix Bedrock AI21 response parse default using `dict` literal instead of `set` ([#5527](https://github.com/mem0ai/mem0/pull/5527))
+- **LLMs:** Fix LiteLLM function-calling check blocking all calls on non-tool models ([#5536](https://github.com/mem0ai/mem0/pull/5536))
+- **LLMs:** Fix HuggingFace provider using `self.config` instead of raw `config` parameter ([#5538](https://github.com/mem0ai/mem0/pull/5538))
+- **Embeddings:** Honor `aws_session_token` in AWS Bedrock embeddings ([#5566](https://github.com/mem0ai/mem0/pull/5566))
+- **Rerankers:** Respect `config.top_k` in Cohere and ZeroEntropy fallback paths ([#5560](https://github.com/mem0ai/mem0/pull/5560))
+- **Vector Stores:** Fix FAISS filtered search dropping over-fetched candidates before filtering ([#5453](https://github.com/mem0ai/mem0/pull/5453))
+- **Vector Stores:** Fix Weaviate `reset()` crashing with missing `vector_size` argument ([#5531](https://github.com/mem0ai/mem0/pull/5531))
+- **Vector Stores:** Pass embedding dims in Weaviate `reset()` to avoid re-init crash ([#5570](https://github.com/mem0ai/mem0/pull/5570))
+- **Vector Stores:** Fix MongoDB `reset()` passing wrong argument to `create_col()` ([#5532](https://github.com/mem0ai/mem0/pull/5532))
+- **Vector Stores:** Fix Pinecone hybrid search crashing when `filters` is `None` ([#5533](https://github.com/mem0ai/mem0/pull/5533))
+- **Vector Stores:** Fix Redis crashing on empty or `None` filters in `search()` and `list()` ([#5446](https://github.com/mem0ai/mem0/pull/5446))
+- **Vector Stores:** Return `None` from `get()` for missing IDs in Milvus, Weaviate, and Supabase ([#5562](https://github.com/mem0ai/mem0/pull/5562))
+- **Vector Stores:** Return `None` from ChromaDB `get()` for missing IDs ([#5561](https://github.com/mem0ai/mem0/pull/5561))
+
+</Update>
+
 <Update label="2026-06-13" description="v2.0.6">
 
 **New Features:**
@@ -27,7 +121,7 @@ mode: "wide"
 
 **New Features:**
 - **Memory:** Warn at init time when hybrid/BM25 search silently degrades to semantic-only because the configured vector store does not implement `keyword_search`. Affected stores: Chroma, FAISS, Cassandra, LangChain, Neptune Analytics, S3 Vectors, Supabase, TurboPuffer, Valkey ([#5444](https://github.com/mem0ai/mem0/pull/5444))
-- **Memory:** Add opt-in `explain=True` parameter to `Memory.search()` and `AsyncMemory.search()`. When enabled, each result includes a `score_breakdown` dict with `semantic`, `keyword` (normalized BM25), `entity_boost`, and `temporal_boost` signals so callers can understand and tune retrieval ranking ([#5102](https://github.com/mem0ai/mem0/pull/5102))
+- **Memory:** Add opt-in `explain=True` parameter to `Memory.search()` and `AsyncMemory.search()`. When enabled, each result includes a `score_details` dict with `semantic_score`, `bm25_score`, `entity_boost`, `raw_score`, `max_possible_score`, `final_score`, and `threshold` so callers can understand and tune retrieval ranking ([#5102](https://github.com/mem0ai/mem0/pull/5102))
 
 **Bug Fixes:**
 - **Vector Stores:** Normalize similarity scores to `[0, 1]` (higher = better) consistently across all backends. 11 adapters previously returned raw distance metrics (lower = better) — FAISS, Chroma, Milvus, Redis, Cassandra, PGVector, S3 Vectors, Supabase, Valkey, Azure MySQL, and Vertex AI Vector Search — causing incorrect ranking in multi-store setups ([#5391](https://github.com/mem0ai/mem0/pull/5391))
@@ -114,8 +208,8 @@ mode: "wide"
 - **`messages` in `Memory.add()` rejects invalid types:** Passing `None` or non-`(str | dict | list)` values raises `Mem0ValidationError` (`error_code="VALIDATION_003"`) ([#4843](https://github.com/mem0ai/mem0/pull/4843))
 - **`qdrant-client>=1.12.0` required** — Upgrade from `>=1.9.1` ([#4805](https://github.com/mem0ai/mem0/pull/4805))
 - **`org_id` and `project_id` removed** — Removed from `MemoryClient` constructor and all method signatures ([#4740](https://github.com/mem0ai/mem0/pull/4740))
-- **Graph Memory Removed (OSS):** `mem0/memory/graph_memory.py`, `memgraph_memory.py`, `kuzu_memory.py`, `apache_age_memory.py`, and `mem0/graphs/` (Neo4j / Memgraph / Kuzu / Apache AGE / Neptune drivers) deleted — ~4,000 lines. Graph memory is no longer supported in the OSS SDK; graph drivers (neo4j, memgraph, kuzu, etc.) can be uninstalled. Use the Platform API for graph features. Remove `enable_graph` and `graph_store` from your config ([#4805](https://github.com/mem0ai/mem0/pull/4805))
-- **`enable_graph` removed from Client SDK** — Graph memory is now a project-level setting on the Platform. Remove `enable_graph` from `MemoryClient.add()` / `search()` / `get_all()` / `update_project()` calls ([#4776](https://github.com/mem0ai/mem0/pull/4776))
+- **External Graph Store Removed (OSS):** `mem0/memory/graph_memory.py`, `memgraph_memory.py`, `kuzu_memory.py`, `apache_age_memory.py`, and `mem0/graphs/` (Neo4j / Memgraph / Kuzu / Apache AGE / Neptune drivers) deleted, about 4,000 lines. The external graph store integration is no longer part of the OSS SDK; graph drivers (neo4j, memgraph, kuzu, etc.) can be uninstalled. Graph memory now runs natively as built-in entity linking. Remove `enable_graph` and `graph_store` from your config ([#4805](https://github.com/mem0ai/mem0/pull/4805))
+- **`enable_graph` removed from Client SDK:** Graph memory now runs automatically and no longer needs a flag. Remove `enable_graph` from `MemoryClient.add()` / `search()` / `get_all()` / `update_project()` calls ([#4776](https://github.com/mem0ai/mem0/pull/4776))
 - **`custom_fact_extraction_prompt` renamed to `custom_instructions`** — Update config and memory module references ([#4740](https://github.com/mem0ai/mem0/pull/4740))
 - **Typed option classes** — Added Pydantic v2 typed classes: `AddMemoryOptions`, `SearchMemoryOptions`, `GetAllMemoryOptions`, `DeleteAllMemoryOptions`, `UpdateMemoryOptions`, `ProjectUpdateOptions` ([#4740](https://github.com/mem0ai/mem0/pull/4740))
 
@@ -135,7 +229,7 @@ mode: "wide"
 **Improvements:**
 - **Telemetry:** Sample OSS hot-path events at 10% via PostHog `before_send` hook to reduce event volume ([#4771](https://github.com/mem0ai/mem0/pull/4771))
 
-See the [OSS v1 to v2 migration guide](https://docs.mem0.ai/migration/oss-v1-to-v2) and [Platform migration guide](https://docs.mem0.ai/migration/platform-v2-to-v3) for upgrade instructions.
+See the [OSS v2 to v3 migration guide](https://docs.mem0.ai/migration/oss-v2-to-v3) and [Platform migration guide](https://docs.mem0.ai/migration/platform-v2-to-v3) for upgrade instructions.
 
 </Update>
 
@@ -976,6 +1070,43 @@ See the [OSS v1 to v2 migration guide](https://docs.mem0.ai/migration/oss-v1-to-
 
 <Tab title="TypeScript">
 
+<Update label="2026-06-24" description="v3.0.11">
+
+**Bug Fixes:**
+- **Memory (OSS):** Align entity extraction with Python by reducing generic entity noise, preserving useful topic phrases, and exact-deduplicating entity links before semantic matching ([#5829](https://github.com/mem0ai/mem0/pull/5829))
+
+</Update>
+
+<Update label="2026-06-24" description="v3.0.10">
+
+**Bug Fixes:**
+- **Memory (OSS):** Guard against malformed `image_url` entries in `parseVisionMessages` to prevent crashes ([#5631](https://github.com/mem0ai/mem0/pull/5631))
+- **Memory (OSS):** Return `attributedTo` from `get()`, `search()`, and `getAll()` ([#5675](https://github.com/mem0ai/mem0/pull/5675))
+- **Memory (OSS):** Preserve message roles in the extraction input so assistant facts aren't attributed to the user ([#5643](https://github.com/mem0ai/mem0/pull/5643))
+- **Memory (OSS):** Reject empty or blank messages in `Memory.add()` to prevent hallucinated memories ([#5545](https://github.com/mem0ai/mem0/pull/5545))
+- **Memory (OSS):** Check `message.role` instead of `content` when detecting system messages ([#3921](https://github.com/mem0ai/mem0/pull/3921))
+- **LLMs:** Honor the configured `baseURL` in `AnthropicLLM` ([#5740](https://github.com/mem0ai/mem0/pull/5740))
+- **Client:** Preserve `customCategories` names through key conversion ([#5741](https://github.com/mem0ai/mem0/pull/5741))
+- **Client:** Prevent hallucinated memories on an empty messages payload ([#5613](https://github.com/mem0ai/mem0/pull/5613))
+- **Client:** Preserve user metadata keys across the case-conversion round-trip ([#5515](https://github.com/mem0ai/mem0/pull/5515))
+
+**Security:**
+- **Dependencies:** Upgrade `form-data` to `>=4.0.6` across pnpm workspaces to remediate CVE-2026-12143 ([#5618](https://github.com/mem0ai/mem0/pull/5618))
+
+</Update>
+
+<Update label="2026-06-17" description="v3.0.9">
+
+**Bug Fixes:**
+- **LLMs:** Fix Anthropic `tool_choice` format — was incorrectly sent as a bare string `"auto"` (rejected by the API); now correctly sent as `{ type: "auto" }`. Also fixes tool response parsing: `tool_use` blocks are now parsed into `toolCalls` objects instead of throwing. Updated default model to `claude-sonnet-4-6` and default `max_tokens` to `2000` to match the Python provider. Added `temperature`, `topP`, and `maxTokens` to `LLMConfig` so Anthropic params can be configured ([#5537](https://github.com/mem0ai/mem0/pull/5537))
+- **Memory (OSS):** Preserve custom metadata fields during `update()` — fields such as `category`, `priority`, and other user-defined keys were previously dropped on update; the existing payload is now spread before applying the new data ([#5480](https://github.com/mem0ai/mem0/pull/5480))
+- **Client:** Preserve user-defined schema keys in `createMemoryExport` ([#5594](https://github.com/mem0ai/mem0/pull/5594))
+
+**Security:**
+- **Dependencies:** Bump `esbuild` to `>=0.28.1` across all npm packages via pnpm overrides to remediate upstream vulnerability ([#5563](https://github.com/mem0ai/mem0/pull/5563))
+
+</Update>
+
 <Update label="2026-06-13" description="v3.0.8">
 
 **New Features:**
@@ -1066,7 +1197,7 @@ See the [OSS v1 to v2 migration guide](https://docs.mem0.ai/migration/oss-v1-to-
 - **Default model:** `gpt-5-mini` is now the default in `OpenAI`, `OpenAIStructured`, and `Azure` LLM providers ([#4829](https://github.com/mem0ai/mem0/pull/4829))
 
 **Breaking Changes:**
-- **Graph Memory Removed (OSS):** `graph_memory.ts` (675 lines), `graphs/tools.ts` (267 lines), `graphs/utils.ts` (116 lines), `graphs/configs.ts` (30 lines) deleted. Graph memory is no longer supported in the OSS SDK — use Platform API for graph features ([#4805](https://github.com/mem0ai/mem0/pull/4805))
+- **External Graph Store Removed (OSS):** `graph_memory.ts` (675 lines), `graphs/tools.ts` (267 lines), `graphs/utils.ts` (116 lines), `graphs/configs.ts` (30 lines) deleted. The external graph store integration is no longer part of the OSS SDK; graph memory now runs natively as built-in entity linking ([#4805](https://github.com/mem0ai/mem0/pull/4805))
 - **camelCase Parameters (Client SDK):** All user-facing parameters converted from snake_case to camelCase. Mapping is transparent at API boundary via `camelToSnakeKeys()` / `snakeToCamelKeys()` ([#4776](https://github.com/mem0ai/mem0/pull/4776))
   ```typescript
   // Before

docs/components/embedders/models/fastembed.mdx

@@ -0,0 +1,50 @@
+---
+title: "FastEmbed"
+description: "Configure FastEmbed as an embedding provider in Mem0 to generate embeddings locally using ONNX-based models without a GPU."
+---
+
+You can use FastEmbed to run embedding models locally in Mem0. FastEmbed is an ONNX-based embedding library that runs efficiently on CPU without requiring a GPU or an external API key.
+
+### Installation
+
+```bash
+pip install fastembed
+```
+
+### Usage
+
+<CodeGroup>
+```python Python
+import os
+from mem0 import Memory
+
+os.environ["OPENAI_API_KEY"] = "your_api_key" # For LLM
+
+config = {
+    "embedder": {
+        "provider": "fastembed",
+        "config": {
+            "model": "thenlper/gte-large"
+        }
+    }
+}
+
+m = Memory.from_config(config)
+messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+]
+m.add(messages, user_id="john")
+```
+</CodeGroup>
+
+### Config
+
+Here are the parameters available for configuring FastEmbed embedder:
+
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `model` | The name of the FastEmbed model to use | `thenlper/gte-large` |
+| `embedding_dims` | Dimensions of the embedding model (auto-derived from the model if not set) | `None` |

docs/components/llms/models/deepseek.mdx

@@ -7,7 +7,8 @@ To use DeepSeek LLM models, you have to set the `DEEPSEEK_API_KEY` environment v
 
 ## Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -36,6 +37,32 @@ messages = [
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  llm: {
+    provider: 'deepseek',
+    config: {
+      apiKey: process.env.DEEPSEEK_API_KEY || '',
+      model: 'deepseek-chat',
+      temperature: 0.2,
+      maxTokens: 2000,
+      top_p: 1.0,
+    },
+  },
+};
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+];
+await memory.add(messages, { userId: 'alice', metadata: { category: 'movies' } });
+``` 
+</CodeGroup>
+
 You can also configure the API base URL in the config:
 
 ```python

docs/components/llms/models/litellm.mdx

@@ -4,9 +4,12 @@ description: "Use LiteLLM as an LLM provider in Mem0 to access over 100 language
 ---
 [Litellm](https://litellm.vercel.app/docs/) is compatible with over 100 large language models (LLMs), all using a standardized input/output format. You can explore the [available models](https://litellm.vercel.app/docs/providers) to use with Litellm. Ensure you set the `API_KEY` for the model you choose to use.
 
+In the TypeScript SDK, run LiteLLM as a [proxy server](https://docs.litellm.ai/docs/simple_proxy) (an OpenAI-compatible endpoint) and point Mem0 at it via `LITELLM_API_BASE` (defaults to `http://localhost:4000`).
+
 ## Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -33,6 +36,33 @@ messages = [
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+// Point Mem0 at your LiteLLM proxy. apiKey defaults to "sk-anything"
+// (the proxy handles real auth); baseURL defaults to http://localhost:4000.
+const config = {
+  llm: {
+    provider: 'litellm',
+    config: {
+      apiKey: process.env.LITELLM_API_KEY || 'sk-anything',
+      baseURL: process.env.LITELLM_API_BASE || 'http://localhost:4000',
+      model: 'gpt-5-mini',
+    },
+  },
+};
+
+const memory = new Memory(config);
+const messages = [
+    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
+    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
+    {"role": "user", "content": "I’m not a big fan of thriller movies but I love sci-fi movies."},
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+];
+await memory.add(messages, { userId: 'alice', metadata: { category: 'movies' } });
+```
+</CodeGroup>
+
 ## Config
 
 All available parameters for the `litellm` config are present in [Master List of All Params in Config](../config).

docs/components/llms/models/minimax.mdx

@@ -7,7 +7,8 @@ To use MiniMax LLM models, you have to set the `MINIMAX_API_KEY` environment var
 
 ## Usage
 
-```python
+<CodeGroup>
+```python Python
 import os
 from mem0 import Memory
 
@@ -36,9 +37,37 @@ messages = [
 m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
+```typescript TypeScript
+import { Memory } from 'mem0ai/oss';
+
+const config = {
+  llm: {
+    provider: 'minimax',
+    config: {
+      apiKey: process.env.MINIMAX_API_KEY || '',
+      model: 'MiniMax-M2.7',
+      temperature: 0.2,
+      maxTokens: 2000,
+      topP: 1.0,
+    },
+  },
+};
+const memory = new Memory(config);
+const messages = [
+  { role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
+  { role: "assistant", content: "How about thriller movies? They can be quite engaging." },
+  { role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
+  { role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." },
+];
+await memory.add(messages, { userId: 'alice', metadata: { category: 'movies' } });
+```
+
+</CodeGroup>
+
 You can also configure the API base URL in the config:
 
-```python
+<CodeGroup>
+```python Python
 config = {
     "llm": {
         "provider": "minimax",
@@ -51,6 +80,20 @@ config = {
 }
 ```
 
+```typescript TypeScript
+const config = {
+  llm: {
+    provider: 'minimax',
+    config: {
+      model: 'MiniMax-M2.7',
+      baseURL: 'https://your-custom-endpoint.com',
+      apiKey: 'your-api-key', // alternatively to using the environment variable
+    },
+  },
+};
+```
+</CodeGroup>
+
 ## Config
 
 All available parameters for the `minimax` config are present in [Master List of All Params in Config](../config).

docs/components/rerankers/models/llm.mdx

@@ -1,226 +0,0 @@
----
-title: LLM as Reranker
-description: "Use any LLM as a flexible reranker in Mem0 with custom prompts and domain-specific scoring logic."
----
-
-<Warning>
-**This page has been superseded.** Please see [LLM Reranker](/components/rerankers/models/llm_reranker) for the complete and up-to-date documentation on using LLMs for reranking.
-</Warning>
-
-LLM-based reranker provides maximum flexibility by using any Large Language Model to score document relevance. This approach allows for custom prompts and domain-specific scoring logic.
-
-## Supported LLM Providers
-
-Any LLM provider supported by Mem0 can be used for reranking:
-
-- **OpenAI**: GPT-4, GPT-3.5-turbo, etc.
-- **Anthropic**: Claude models
-- **Together**: Open-source models
-- **Groq**: Fast inference
-- **Ollama**: Local models
-- And more...
-
-## Configuration
-
-```python Python
-from mem0 import Memory
-
-config = {
-    "vector_store": {
-        "provider": "chroma",
-        "config": {
-            "collection_name": "my_memories",
-            "path": "./chroma_db"
-        }
-    },
-    "llm": {
-        "provider": "openai",
-        "config": {
-            "model": "gpt-4o-mini"
-        }
-    },
-    "reranker": {
-        "provider": "llm",
-        "config": {
-            "model": "gpt-4o-mini",
-            "provider": "openai",
-            "api_key": "your-openai-api-key",  # or set OPENAI_API_KEY
-            "top_k": 5,
-            "temperature": 0.0
-        }
-    }
-}
-
-memory = Memory.from_config(config)
-```
-
-## Custom Scoring Prompt
-
-You can provide a custom prompt for relevance scoring:
-
-```python Python
-custom_prompt = """You are a relevance scoring assistant. Rate how well this document answers the query.
-
-Query: "{query}"
-Document: "{document}"
-
-Score from 0.0 to 1.0 where:
-- 1.0: Perfect match, directly answers the query
-- 0.8-0.9: Highly relevant, good match  
-- 0.6-0.7: Moderately relevant, partial match
-- 0.4-0.5: Slightly relevant, limited useful information
-- 0.0-0.3: Not relevant or no useful information
-
-Provide only a single numerical score between 0.0 and 1.0."""
-
-config["reranker"]["config"]["scoring_prompt"] = custom_prompt
-```
-
-## Usage Example
-
-```python Python
-import os
-from mem0 import Memory
-
-# Set API key
-os.environ["OPENAI_API_KEY"] = "your-api-key"
-
-# Initialize memory with LLM reranker
-config = {
-    "vector_store": {"provider": "chroma"},
-    "llm": {"provider": "openai", "config": {"model": "gpt-4o-mini"}},
-    "reranker": {
-        "provider": "llm",
-        "config": {
-            "model": "gpt-4o-mini",
-            "provider": "openai",
-            "temperature": 0.0
-        }
-    }
-}
-
-memory = Memory.from_config(config)
-
-# Add memories
-messages = [
-    {"role": "user", "content": "I'm learning Python programming"},
-    {"role": "user", "content": "I find object-oriented programming challenging"}, 
-    {"role": "user", "content": "I love hiking in national parks"}
-]
-
-memory.add(messages, user_id="david")
-
-# Search with LLM reranking
-results = memory.search("What programming topics is the user studying?", filters={"user_id": "david"})
-
-for result in results['results']:
-    print(f"Memory: {result['memory']}")
-    print(f"Vector Score: {result['score']:.3f}")
-    print(f"Rerank Score: {result['rerank_score']:.3f}")
-    print()
-```
-
-```text Output
-Memory: I'm learning Python programming
-Vector Score: 0.856
-Rerank Score: 0.920
-
-Memory: I find object-oriented programming challenging
-Vector Score: 0.782
-Rerank Score: 0.850
-```
-
-## Domain-Specific Scoring
-
-Create specialized scoring for your domain:
-
-```python Python
-medical_prompt = """You are a medical relevance expert. Score how relevant this medical record is to the clinical query.
-
-Clinical Query: "{query}"
-Medical Record: "{document}"
-
-Consider:
-- Clinical relevance and accuracy
-- Patient safety implications
-- Diagnostic value
-- Treatment relevance
-
-Score from 0.0 to 1.0. Provide only the numerical score."""
-
-config = {
-    "reranker": {
-        "provider": "llm",
-        "config": {
-            "model": "gpt-4o-mini",
-            "provider": "openai",
-            "scoring_prompt": medical_prompt,
-            "temperature": 0.0
-        }
-    }
-}
-```
-
-## Multiple LLM Providers
-
-Use different LLM providers for reranking:
-
-```python Python
-# Using Anthropic Claude
-anthropic_config = {
-    "reranker": {
-        "provider": "llm",
-        "config": {
-            "model": "claude-3-haiku-20240307",
-            "provider": "anthropic",
-            "temperature": 0.0
-        }
-    }
-}
-
-# Using local Ollama model
-ollama_config = {
-    "reranker": {
-        "provider": "llm",
-        "config": {
-            "model": "llama2:7b",
-            "provider": "ollama",
-            "temperature": 0.0
-        }
-    }
-}
-```
-
-## Configuration Parameters
-
-| Parameter | Description | Type | Default |
-|-----------|-------------|------|---------|
-| `model` | LLM model to use for scoring | `str` | `"gpt-4o-mini"` |
-| `provider` | LLM provider name | `str` | `"openai"` |
-| `api_key` | API key for the LLM provider | `str` | `None` |
-| `top_k` | Maximum documents to return | `int` | `None` |
-| `temperature` | Temperature for LLM generation | `float` | `0.0` |
-| `max_tokens` | Maximum tokens for LLM response | `int` | `100` |
-| `scoring_prompt` | Custom prompt template | `str` | Default prompt |
-
-## Advantages
-
-- **Maximum Flexibility**: Custom prompts for any use case
-- **Domain Expertise**: Leverage LLM knowledge for specialized domains
-- **Interpretability**: Understand scoring through prompt engineering
-- **Multi-criteria**: Score based on multiple relevance factors
-
-## Considerations
-
-- **Latency**: Higher latency than specialized rerankers
-- **Cost**: LLM API costs per reranking operation
-- **Consistency**: May have slight variations in scoring
-- **Prompt Engineering**: Requires careful prompt design
-
-## Best Practices
-
-1. **Temperature**: Use 0.0 for consistent scoring
-2. **Prompt Design**: Be specific about scoring criteria
-3. **Token Efficiency**: Keep prompts concise to reduce costs
-4. **Caching**: Cache results for repeated queries when possible
-5. **Fallback**: Handle API errors gracefully

docs/components/vectordbs/dbs/baidu.mdx

@@ -46,7 +46,7 @@ Here are the parameters available for configuring Baidu VectorDB:
 | `account` | Baidu VectorDB account name | `root` |
 | `api_key` | API key for accessing Baidu VectorDB | Required |
 | `database_name` | Name of the database | `mem0` |
-| `table_name` | Name of the table | `mem0_table` |
+| `table_name` | Name of the table | `mem0` |
 | `embedding_model_dims` | Dimensions of the embedding model | `1536` |
 | `metric_type` | Distance metric for similarity search | `L2` |
 

docs/components/vectordbs/dbs/elasticsearch.mdx

@@ -56,6 +56,8 @@ Here are the parameters available for configuring Elasticsearch:
 | `api_key`              | API key for authentication                         | `None`        |
 | `user`                 | Username for basic authentication                  | `None`        |
 | `password`             | Password for basic authentication                  | `None`        |
+| `use_ssl`              | Whether to use SSL for the connection              | `True`        |
+| `ca_certs`             | Path to CA bundle for SSL certificate verification | `None`        |
 | `verify_certs`         | Whether to verify SSL certificates                 | `True`        |
 | `auto_create_index`    | Whether to automatically create the index          | `True`        |
 | `custom_search_query`  | Function returning a custom search query           | `None`        |

docs/components/vectordbs/dbs/faiss.mdx

@@ -55,6 +55,7 @@ Here are the parameters available for configuring FAISS:
 | `path` | Path to store FAISS index and metadata | `/tmp/faiss/<collection_name>` |
 | `distance_strategy` | Distance metric strategy to use (options: 'euclidean', 'inner_product', 'cosine') | `euclidean` |
 | `normalize_L2` | Whether to normalize L2 vectors (only applicable for euclidean distance) | `False` |
+| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
 
 ### Performance Considerations
 

docs/components/vectordbs/dbs/langchain.mdx

@@ -47,12 +47,12 @@ m.add(messages, user_id="alice", metadata={"category": "movies"})
 ```
 
 ```typescript TypeScript
-import { Memory } from "mem0ai";
+import { Memory } from "mem0ai/oss";
 import { OpenAIEmbeddings } from "@langchain/openai";
-import { MemoryVectorStore as LangchainMemoryStore } from "langchain/vectorstores/memory";
+import { MemoryVectorStore } from "langchain/vectorstores/memory";
 
 const embeddings = new OpenAIEmbeddings();
-const vectorStore = new LangchainVectorStore(embeddings);
+const vectorStore = new MemoryVectorStore(embeddings);
 
 const config = {
     "vector_store": {

docs/components/vectordbs/dbs/mongodb.mdx

@@ -42,8 +42,8 @@ Here are the parameters available for configuring MongoDB:
 | Parameter | Description | Default Value |
 | --- | --- | --- |
 | db_name | Name of the MongoDB database | `"mem0_db"` |
-| collection_name | Name of the MongoDB collection | `"mem0_collection"` |
+| collection_name | Name of the MongoDB collection | `"mem0"` |
 | embedding_model_dims | Dimensions of the embedding vectors | `1536` |
-| mongo_uri | The MongoDB URI connection string | `mongodb://username:password@localhost:27017` |
+| mongo_uri | The MongoDB URI connection string | `mongodb://localhost:27017` |
 
-> **Note**: If `mongo_uri` is not provided, it will default to `mongodb://username:password@localhost:27017`.
+> **Note**: If `mongo_uri` is not provided, it will default to `mongodb://localhost:27017`.

docs/components/vectordbs/dbs/neon.mdx

@@ -53,17 +53,14 @@ print(results)
 import "dotenv/config";
 import { Memory } from "mem0ai/oss";
 
-const databaseUrl = new URL(process.env.DATABASE_URL!);
-
 const m = new Memory({
   vectorStore: {
     provider: "pgvector",
     config: {
-      user: decodeURIComponent(databaseUrl.username),
-      password: decodeURIComponent(databaseUrl.password),
-      host: databaseUrl.hostname,
-      port: Number(databaseUrl.port || 5432),
-      dbname: databaseUrl.pathname.slice(1) || "neondb",
+      connectionString: process.env.DATABASE_URL!,
+      ssl: {
+        rejectUnauthorized: false,
+      },
       collectionName: "memories",
       dimension: 1536,
       embeddingModelDims: 1536,
@@ -90,6 +87,7 @@ const results = await m.search("What movies should I recommend?", {
 
 console.log(results);
 ```
+
 </CodeGroup>
 
 ## SQL Migration
@@ -116,20 +114,19 @@ DATABASE_URL=postgresql://user:password@ep-example.us-east-2.aws.neon.tech/neond
 | `sslmode` | PostgreSQL SSL mode. Use `require` for Neon. | Driver default |
 </Tab>
 <Tab title="TypeScript">
-The current Mem0 TypeScript `pgvector` adapter takes individual Postgres fields,
-so parse `DATABASE_URL` before creating `Memory`.
+Use the Neon `DATABASE_URL` directly with `connectionString`. Set `ssl` if your runtime needs an explicit TLS config object.
+
+| Parameter            | Description                                    | Default        |
+| -------------------- | ---------------------------------------------- | -------------- |
+| `connectionString`   | Neon Postgres connection string.               | Required       |
+| `ssl`                | Optional TLS settings passed directly to `pg`. | Driver default |
+| `collectionName`     | Name for the vector collection.                | `memories`     |
+| `dimension`          | Vector dimension for Mem0 config.              | Auto-detected  |
+| `embeddingModelDims` | Embedding model dimensions for table creation. | Required       |
+| `hnsw`               | Enables HNSW indexing.                         | `false`        |
+
+**TLS note:** `ssl: true` is sufficient for most Neon connections since Neon uses valid certificates. Use `ssl: { rejectUnauthorized: false }` only when connecting through Neon's connection pooler on certain edge runtimes (e.g. Cloudflare Workers) that require it, or when your environment does not trust the Neon CA chain.
 
-| Parameter | Description | Default |
-| --- | --- | --- |
-| `user` | Database user. | Required |
-| `password` | Database password. | Required |
-| `host` | Database host. | Required |
-| `port` | Database port. | `5432` |
-| `dbname` | Database name. | `vector_store` |
-| `collectionName` | Name for the vector collection. | `memories` |
-| `dimension` | Vector dimension for Mem0 config. | Auto-detected |
-| `embeddingModelDims` | Embedding model dimensions for table creation. | Required |
-| `hnsw` | Enables HNSW indexing. | `false` |
 </Tab>
 </Tabs>
 

docs/components/vectordbs/dbs/neptune_analytics.mdx

@@ -10,7 +10,7 @@ description: "Use AWS Neptune Analytics as a vector store in Mem0, combining gra
 ## Installation
 
 ```bash
-pip install mem0ai[vector_stores]
+pip install mem0ai[vector-stores]
 ```
 
 ## Usage

docs/components/vectordbs/dbs/opensearch.mdx

@@ -56,6 +56,30 @@ config = {
 }
 ```
 
+### Configuration Options
+
+| Parameter | Type | Default | Description |
+|-----------|------|---------|-------------|
+| `collection_name` | string | required | Name of the OpenSearch index |
+| `host` | string | required | OpenSearch endpoint URL |
+| `port` | int | 9200 | Port number |
+| `http_auth` | object | None | Authentication credentials (e.g., AWSV4SignerAuth) |
+| `embedding_model_dims` | int | 1536 | Dimension of embedding vectors |
+| `use_ssl` | bool | False | Enable SSL/TLS connection |
+| `verify_certs` | bool | False | Verify SSL certificates |
+| `auto_refresh` | bool | False | Automatically refresh index after insert. OpenSearch refreshes every ~1 second by default, so this is rarely needed. |
+
+<Note>
+  The defaults above match a local OpenSearch instance. The AWS OpenSearch Serverless
+  example earlier on this page intentionally overrides them with `port=443`, `use_ssl=True`,
+  and `verify_certs=True`, which are required when connecting to a Serverless collection.
+</Note>
+
+<Note>
+  For **AWS OpenSearch Serverless**, keep `auto_refresh=False` (the default).
+  The `indices.refresh()` API is not supported on Serverless collections.
+</Note>
+
 ### Add Memories
 
 ```python

docs/components/vectordbs/dbs/pgvector.mdx

@@ -2,6 +2,7 @@
 title: "pgvector"
 description: "Use pgvector as a vector store in Mem0 for PostgreSQL-based vector similarity search with open-source simplicity."
 ---
+
 [pgvector](https://github.com/pgvector/pgvector) is an open-source vector similarity search extension for Postgres. After connecting to Postgres, run `CREATE EXTENSION IF NOT EXISTS vector;` to create the vector extension.
 
 ### Usage
@@ -21,7 +22,7 @@ config = {
             "password": "123",
             "host": "127.0.0.1",
             "port": "5432",
-        }
+        },
     }
 }
 
@@ -30,25 +31,22 @@ messages = [
     {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
     {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
     {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
-    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
+    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."},
 ]
 m.add(messages, user_id="alice", metadata={"category": "movies"})
+
 ```
 
 ```typescript TypeScript
-import { Memory } from 'mem0ai/oss';
+import { Memory } from "mem0ai/oss";
 
 const config = {
   vectorStore: {
-    provider: 'pgvector',
+    provider: "pgvector",
     config: {
-      collectionName: 'memories',
+      collectionName: "memories",
       embeddingModelDims: 1536,
-      user: 'test',
-      password: '123',
-      host: '127.0.0.1',
-      port: 5432,
-      dbname: 'vector_store', // Optional; TypeScript OSS defaults to `vector_store` when omitted
+      connectionString: "postgresql://test:123@localhost:5432/vector_store",
       diskann: false, // Optional, requires pgvectorscale extension
       hnsw: false, // Optional, for HNSW indexing
     },
@@ -57,37 +55,44 @@ const config = {
 
 const memory = new Memory(config);
 const messages = [
-    {"role": "user", "content": "I'm planning to watch a movie tonight. Any recommendations?"},
-    {"role": "assistant", "content": "How about thriller movies? They can be quite engaging."},
-    {"role": "user", "content": "I'm not a big fan of thriller movies but I love sci-fi movies."},
-    {"role": "assistant", "content": "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future."}
-]
+  { role: "user", content: "I'm planning to watch a movie tonight. Any recommendations?" },
+  { role: "assistant", content: "How about thriller movies? They can be quite engaging." },
+  { role: "user", content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
+  { role: "assistant", content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." },
+];
+
 await memory.add(messages, { userId: "alice", metadata: { category: "movies" } });
 ```
+
 </CodeGroup>
 
 ### Config
 
 Here are the parameters available for configuring pgvector:
 
-| Parameter | Description | Default Value |
-| --- | --- | --- |
-| `dbname` | The name of the database | `postgres` |
-| `collection_name` | The name of the collection | `mem0` |
-| `embedding_model_dims` | Dimensions of the embedding model | `1536` |
-| `user` | User name to connect to the database | `None` |
-| `password` | Password to connect to the database | `None` |
-| `host` | The host where the Postgres server is running | `None` |
-| `port` | The port where the Postgres server is running | `None` |
-| `diskann` | Whether to use diskann for vector similarity search (requires pgvectorscale) | `True` |
-| `hnsw` | Whether to use hnsw for vector similarity search | `False` |
-| `sslmode` | SSL mode for PostgreSQL connection (e.g., 'require', 'prefer', 'disable') | `None` |
-| `connection_string` | PostgreSQL connection string (overrides individual connection parameters) | `None` |
-| `connection_pool` | psycopg2 connection pool object (overrides connection string and individual parameters) | `None` |
+| Parameter            | SDK                     | Description                                                                                                                                                    | Default Value                           |
+| -------------------- | ----------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------------------------------------- |
+| `connectionString`   | TypeScript OSS          | PostgreSQL connection string for direct connections. When set, Mem0 connects to the target database directly and skips the bootstrap `postgres` database flow. | `None`                                  |
+| `ssl`                | TypeScript OSS          | SSL option passed directly to `pg`, either `true` or an SSL config object, for both `connectionString` and split-field connections.                            | `None`                                  |
+| `dbname`             | TypeScript OSS          | Split-field database name. This is only used when `connectionString` is absent.                                                                                | `vector_store`                          |
+| `collectionName`     | TypeScript OSS          | Collection name.                                                                                                                                               | `memories`                              |
+| `embeddingModelDims` | TypeScript OSS          | Dimensions of the embedding model.                                                                                                                             | Required                                |
+| `user`               | TypeScript OSS + Python | Database user for split-field connections.                                                                                                                     | `None`                                  |
+| `password`           | TypeScript OSS + Python | Database password for split-field connections.                                                                                                                 | `None`                                  |
+| `host`               | TypeScript OSS + Python | Database host for split-field connections.                                                                                                                     | `None`                                  |
+| `port`               | TypeScript OSS + Python | Database port for split-field connections.                                                                                                                     | `None`                                  |
+| `diskann`            | TypeScript OSS + Python | Whether to use DiskANN for vector similarity search, requires pgvectorscale.                                                                                   | `False`                                 |
+| `hnsw`               | TypeScript OSS + Python | Whether to use HNSW for vector similarity search.                                                                                                              | TypeScript OSS: `False`, Python: `True` |
+| `connection_string`  | Python only             | PostgreSQL connection string, overrides individual connection parameters.                                                                                      | `None`                                  |
+| `sslmode`            | Python only             | SSL mode for PostgreSQL connections, such as `require`, `prefer`, or `disable`.                                                                                | `None`                                  |
+| `connection_pool`    | Python only             | psycopg connection pool object, overrides connection string and individual connection parameters.                                                              | `None`                                  |
 
-**Note (TypeScript OSS):** If you omit `dbname`, the TypeScript client uses the database name `vector_store`. Python defaults to `postgres` for `dbname`, as in the table above.
+**TypeScript OSS:** Use `connectionString` plus optional `ssl` for managed Postgres setups. If you omit `connectionString`, Mem0 falls back to split fields and uses `dbname`, `user`, `password`, `host`, `port`, and optional `ssl`.
+
+**Python:** The Python SDK uses snake_case keys such as `connection_string`, `sslmode`, `collection_name`, and `embedding_model_dims`.
+
+**Python connection priority**:
 
-**Note**: The connection parameters have the following priority:
 1. `connection_pool` (highest priority)
 2. `connection_string`
-3. Individual connection parameters (`user`, `password`, `host`, `port`, `sslmode`)
+3. Individual connection parameters (`user`, `password`, `host`, `port`, `sslmode`)

docs/components/vectordbs/dbs/upstash-vector.mdx

@@ -18,7 +18,9 @@ os.environ["UPSTASH_VECTOR_REST_TOKEN"] = "..."
 config = {
     "vector_store": {
         "provider": "upstash_vector",
-        "enable_embeddings": True,
+        "config": {
+            "enable_embeddings": True,
+        }
     }
 }
 

docs/components/vectordbs/dbs/valkey.mdx

@@ -9,7 +9,7 @@ description: "Use Valkey as an open-source vector store in Mem0 for high-perform
 ## Installation
 
 ```bash
-pip install mem0ai[vector_stores]
+pip install mem0ai[vector-stores]
 ```
 
 ## Usage
@@ -51,7 +51,7 @@ Here are the parameters available for configuring Valkey:
 | `hnsw_ef_construction` | Size of dynamic candidate list for HNSW | `200` |
 | `hnsw_ef_runtime` | Size of dynamic candidate list for search | `10` |
 | `cluster_mode` | Enable cluster mode for Valkey cluster (CME) deployments | `false` |
-| `distance_metric` | Distance metric for vector similarity | `cosine` |
+| `timezone` | Timezone for timestamp handling | `UTC` |
 
 ## Cluster Mode
 

docs/components/vectordbs/dbs/vertex_ai.mdx

@@ -24,7 +24,7 @@ config = {
             "deployment_index_id": "YOUR_DEPLOYMENT_INDEX_ID",  # Required: Deployment-specific ID
             "project_id": "YOUR_PROJECT_ID",              # Required: Google Cloud project ID
             "project_number": "YOUR_PROJECT_NUMBER",      # Required: Google Cloud project number
-            "region": "YOUR_REGION",                      # Optional: Defaults to GOOGLE_CLOUD_REGION
+            "region": "YOUR_REGION",                      # Required: Google Cloud region
             "credentials_path": "path/to/credentials.json", # Optional: Defaults to GOOGLE_APPLICATION_CREDENTIALS
             "vector_search_api_endpoint": "YOUR_API_ENDPOINT" # Required for get operations
         }
@@ -45,5 +45,6 @@ m.add("Your text here", user_id="user", metadata={"category": "example"})
 | `project_id` | Google Cloud project ID | Yes |
 | `project_number` | Google Cloud project number | Yes |
 | `vector_search_api_endpoint` | Vector search API endpoint | Yes (for get operations) |
-| `region` | Google Cloud region | No (defaults to GOOGLE_CLOUD_REGION) |
+| `region` | Google Cloud region | Yes |
 | `credentials_path` | Path to service account credentials | No (defaults to GOOGLE_APPLICATION_CREDENTIALS) |
+| `service_account_json` | Service account credentials as a dictionary (alternative to `credentials_path`) | `None` |

docs/components/vectordbs/dbs/weaviate.mdx

@@ -7,7 +7,7 @@ description: "Use Weaviate as an open-source vector search engine in Mem0 for st
 
 ### Installation
 ```bash
-pip install weaviate weaviate-client
+pip install weaviate-client
 ```
 
 ### Usage
@@ -48,4 +48,5 @@ Here are the parameters available for configuring Weaviate:
 | `collection_name` | The name of the collection to store the vectors | `mem0` |
 | `embedding_model_dims` | Dimensions of the embedding model | `1536` |
 | `cluster_url` | URL for the Weaviate server | `None` |
-| `auth_client_secret` | API key for Weaviate authentication | `None` |
+| `auth_client_secret` | API key for Weaviate authentication | `None` |
+| `additional_headers` | Additional headers to include in requests (`Dict[str, str]`) | `None` |

docs/components/vectordbs/overview.mdx

@@ -10,7 +10,7 @@ Mem0 includes built-in support for various popular databases. Memory can utilize
 See the list of supported vector databases below.
 
 <Note>
-  The following vector databases are supported in the Python implementation. The TypeScript implementation currently only supports Qdrant, Redis, Valkey, Vectorize and in-memory vector database.
+  The following vector databases are supported in the Python implementation. The TypeScript implementation currently supports Qdrant, Redis, PGVector, Supabase, LangChain, Azure AI Search, Vectorize, and an in-memory store.
 </Note>
 
 <CardGroup cols={3}>

docs/contributing/development.mdx

@@ -1,32 +1,65 @@
 ---
 title: Development
-description: "Guide to contributing code to Mem0, covering the fork and clone workflow, PR submission, and code quality checks."
+description: "Guide to contributing code to Mem0, covering the issue-first workflow, the CLA, environment setup for the Python and TypeScript SDKs, and code quality checks."
 icon: "code"
 ---
 
 # Development Contributions
 
-We strive to make contributions **easy, collaborative, and enjoyable**. Follow the steps below to ensure a smooth contribution process.
+We strive to make contributions **easy, collaborative, and enjoyable**. Mem0 is a
+polyglot monorepo containing the **Python SDK** (`mem0/`), the **TypeScript SDK**
+(`mem0-ts/`), CLIs, integrations, the self-hosted server, and the docs site.
+Follow the steps below for a smooth contribution process.
 
-## Submitting Your Contribution through PR
+<Note>
+  For the complete contributor checklist, see
+  [CONTRIBUTING.md](https://github.com/mem0ai/mem0/blob/main/CONTRIBUTING.md) in
+  the repository root.
+</Note>
 
-To contribute, follow these steps:
+## Before You Start
+
+### 1. Open an Issue First
+
+**Always open an issue before opening a pull request.** This lets us discuss the
+change, avoid duplicate work, and agree on the approach before you write code.
+
+- Search [existing issues](https://github.com/mem0ai/mem0/issues) first.
+- If none match, open a
+  [bug report](https://github.com/mem0ai/mem0/issues/new?template=bug_report.yml)
+  or [feature request](https://github.com/mem0ai/mem0/issues/new?template=feature_request.yml).
+- For anything beyond a trivial fix, wait for a maintainer to confirm the approach.
+
+Every pull request must link to an issue using `Closes #<issue-number>`.
+
+### 2. Sign the Contributor License Agreement (CLA)
+
+**We cannot merge any pull request until you have signed our Contributor License
+Agreement (CLA).** When you open your first PR, the CLA bot will comment with a
+link to sign — it takes less than a minute and only needs to be done once.
+
+## Submitting Your Contribution through a PR
 
 1. **Fork & Clone** the repository: [Mem0 on GitHub](https://github.com/mem0ai/mem0)
-2. **Create a Feature Branch**: Use a dedicated branch for your changes, e.g., `feature/my-new-feature`
-3. **Implement Changes**: If adding a feature or fixing a bug, ensure to:
+2. **Create a Feature Branch**: Use a dedicated branch, e.g., `feature/my-new-feature`
+3. **Implement Changes**: If adding a feature or fixing a bug, be sure to:
    - Write necessary **tests**
    - Add **documentation, docstrings, and runnable examples**
 4. **Code Quality Checks**:
    - Run **linting** to catch style issues
    - Ensure **all tests pass**
-5. **Submit a Pull Request**
+5. **Commit** using [Conventional Commits](https://www.conventionalcommits.org/)
+   (`feat:`, `fix:`, `docs:`, `refactor:`, `test:`)
+6. **Submit a Pull Request** against `main`, linking the issue and filling out the
+   PR template.
 
 For detailed guidance on pull requests, refer to [GitHub's documentation](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request).
 
 ---
 
-## Dependency Management
+## Python SDK (`mem0/`)
+
+### Dependency Management
 
 We use `hatch` as our package manager. Install it by following the [official instructions](https://hatch.pypa.io/latest/install/).
 
@@ -44,13 +77,9 @@ hatch -e dev_py_3_11 shell  # For dev_py_3_11 (differences are mentioned in pypr
 make install_all
 ```
 
----
-
-## Development Standards
-
 ### Pre-commit Hooks
 
-Ensure `pre-commit` is installed before contributing:
+Ensure `pre-commit` is installed before contributing (hooks run ruff + isort):
 
 ```bash
 pre-commit install
@@ -58,7 +87,7 @@ pre-commit install
 
 ### Linting with `ruff`
 
-Run the linter and fix any reported issues before submitting your PR:
+Run the linter and fix any reported issues before submitting your PR (line length **120**):
 
 ```bash
 make lint
@@ -66,10 +95,11 @@ make lint
 
 ### Code Formatting
 
-To maintain a consistent code style, format your code:
+To maintain a consistent code style, format your code and sort imports (isort, `profile = "black"`):
 
 ```bash
 make format
+make sort
 ```
 
 ### Testing with `pytest`
@@ -84,10 +114,46 @@ make test
 
 ---
 
-## Release Process
+## TypeScript SDK (`mem0-ts/`)
 
-Currently, releases are handled manually. We aim for frequent releases, typically when new features or bug fixes are introduced.
+We use [`pnpm`](https://pnpm.io/) (v10+) for all TypeScript packages. **Do NOT use
+`npm` or `yarn`.**
+
+```bash
+cd mem0-ts
+pnpm install
+
+pnpm run build        # tsup (CJS + ESM)
+pnpm run test         # jest (all tests)
+pnpm run test:unit    # unit tests with coverage
+```
+
+### Standards
+
+- **Build:** tsup
+- **Formatter:** Prettier
+- **Tests:** jest
+- Always run type checking after changes: `pnpm run typecheck` (or `tsc --noEmit`)
+- Use ES module `import` syntax — never `require()`
 
 ---
 
-Thank you for contributing to Mem0!
+## Reporting Security Issues
+
+**Do not report security vulnerabilities through public issues or pull requests.**
+Please follow our [Security Policy](https://github.com/mem0ai/mem0/blob/main/SECURITY.md)
+to report them privately.
+
+---
+
+## Release Process
+
+Packages are published automatically via GitHub Actions when a GitHub Release is
+created with the correct tag prefix (e.g. `v*` for the Python SDK, `ts-v*` for the
+TypeScript SDK). See
+[CONTRIBUTING.md](https://github.com/mem0ai/mem0/blob/main/CONTRIBUTING.md#releasing)
+for the full tag-prefix table and publishing details.
+
+---
+
+Thank you for contributing to Mem0!

docs/core-concepts/memory-evaluation.mdx

@@ -17,7 +17,7 @@ Some benchmarks today — particularly smaller ones like LoCoMo and LongMemEval
 
 ## Architecture Overview
 
-Mem0's memory system operates across two phases — **extraction** (writing) and **retrieval** (reading) — with an entity linking layer connecting them.
+Mem0's memory system operates across two phases, **extraction** (writing) and **retrieval** (reading), with a graph memory layer (entity linking) connecting them.
 
 ### Memory Extraction (Distillation)
 
@@ -27,14 +27,14 @@ When new conversations arrive, the extraction pipeline processes them through fi
 2. **Context Lookup** — Find related existing memories to avoid duplicates
 3. **Distill Memories** — Single-pass LLM extraction produces ADD-only facts from input + context
 4. **Deduplicate + Embed** — Hash-based deduplication, then vectorize new memories
-5. **Entity Linking** — Identify entities (proper nouns, quoted text, compound noun phrases) and link them across memories
+5. **Graph Memory (Entity Linking)**: Identify entities (proper nouns, quoted text, compound noun phrases) and link them across memories into a graph
 
 Memories are distributed across three storage layers, each tuned for a specific retrieval pattern:
 
 | Store | Contents | Purpose |
 |---|---|---|
 | **Vector Database** | Memory text, embeddings, metadata (timestamps, hash, categories, attributed_to) | Primary fact storage + semantic retrieval |
-| **Entity Store** | Entities + embeddings + linked memory IDs | Entity-based retrieval boost |
+| **Graph / Entity Store** | Entities + embeddings + linked memory IDs | Graph connections across memories + entity-based retrieval boost |
 | **SQL Database** | History log (ADD events) + rolling message window | Audit trail + extraction dedup context |
 
 <Info>
@@ -76,7 +76,7 @@ The combined score outperformed every individual signal across every category te
 
 *Mean tokens: 6,956*
 
-The two largest gains are **temporal queries (+29.6)** and **multi-hop reasoning (+23.1)**. Both categories directly test the ADD-only architecture (preserving temporal context) and entity linking (connecting facts across memories).
+The two largest gains are **temporal queries (+29.6)** and **multi-hop reasoning (+23.1)**. Both categories directly test the ADD-only architecture (preserving temporal context) and graph memory / entity linking (connecting facts across memories).
 
 ### LongMemEval
 
@@ -345,7 +345,7 @@ When evaluating memory systems, keep these considerations in mind:
   <Card title="Research" icon="flask" href="https://mem0.ai/research">
     Published research papers and technical reports
   </Card>
-  <Card title="Blog Post" icon="newspaper" href="https://mem0.ai/blog/new-algorithm">
+  <Card title="Blog Post" icon="newspaper" href="https://mem0.ai/blog/the-token-efficient-memory-algorithm-now-has-temporal-reasoning">
     Detailed writeup of the new algorithm design and results
   </Card>
   <Card title="Platform Migration" icon="arrow-right" href="/migration/platform-v2-to-v3">

docs/core-concepts/memory-operations/add.mdx

@@ -21,7 +21,7 @@ Adding memory is how Mem0 captures useful details from a conversation so your ag
 - **Messages** – The ordered list of user/assistant turns you send to `add`.
 - **Infer** – Controls whether Mem0 extracts structured memories (`infer=True`, default) or stores raw messages.
 - **Metadata** – Optional filters (e.g., `{"category": "movie_recommendations"}`) that improve retrieval later.
-- **User / Session identifiers** – `user_id`, `agent_id`, or `run_id` that scope the memory for future searches.
+- **User / Session identifiers** – `user_id`, `agent_id`, `app_id`, or `run_id` that scope the memory for future searches.
 
 ## How does it work?
 
@@ -30,22 +30,22 @@ Mem0 offers two flows:
 - **Mem0 Platform** – Fully managed API with dashboard and scaling.
 - **Mem0 Open Source** – Local SDK that you run in your own environment.
 
-Both flows take the same payload and pass it through the same pipeline.
+Both flows take the same payload and add memories through an additive pipeline.
 
 <Steps>
 <Step title="Information extraction">
 Mem0 sends the messages through an LLM that pulls out key facts, decisions, or preferences to remember.
 </Step>
-<Step title="Conflict resolution">
-Existing memories are checked for duplicates or contradictions so the latest truth wins.
+<Step title="Additive storage">
+New memories are added without overwriting or deleting existing memories.
 </Step>
-<Step title="Storage">
-The resulting memories land in managed vector storage so future searches return them quickly.
+<Step title="Retrieval">
+Future searches rank the most relevant memories for the query.
 </Step>
 </Steps>
 
 <Warning>
-Duplicate protection only runs during that conflict-resolution step when you let Mem0 infer memories (`infer=True`, the default). If you switch to `infer=False`, Mem0 stores your payload exactly as provided, so duplicates will land. Mixing both modes for the same fact will save it twice.
+When you switch to `infer=False`, Mem0 stores your payload exactly as provided, so duplicates can land. Mixing both modes for the same fact can save it twice.
 </Warning>
 
 You trigger this pipeline with a single `add` call—no manual orchestration needed.
@@ -80,13 +80,13 @@ const messages = [
 ];
 
 await client.add(messages, {
-  user_id: "alice",
+  userId: "alice",
 });
 ```
 </CodeGroup>
 
 <Info icon="check">
-  Expect a `memory_id` (or list of IDs) in the response. Check the Mem0 dashboard to confirm the new entry under the correct user.
+  Expect a `status: "PENDING"` response with an `event_id`. Poll `GET /v1/event/{event_id}/` to confirm completion.
 </Info>
 
 ## Add with Mem0 Open Source
@@ -138,7 +138,7 @@ const result = memory.add(messages, {
 </Tip>
 
 <Warning>
-If you do choose `infer=False`, keep it consistent. Raw inserts skip conflict resolution, so a later `infer=True` call with the same content will create a second memory instead of updating the first.
+If you do choose `infer=False`, keep it consistent. Raw inserts skip inference, so a later `infer=True` call with the same content can create a second memory.
 </Warning>
 
 ## When Should You Add Memory?
@@ -167,7 +167,7 @@ For full list of supported fields, required formats, and advanced options, see t
 
 | Capability | Mem0 Platform | Mem0 OSS |
 | --- | --- | --- |
-| Conflict resolution | Automatic with dashboard visibility | SDK handles merges locally; you control storage |
+| Add behavior | ADD-only; memories accumulate | ADD-only; you control storage |
 | Rate limits | Managed quotas per workspace | Limited by your hardware and provider APIs |
 | Dashboard visibility | Yes — inspect memories visually | Inspect via CLI, logs, or custom UI |
 

docs/docs.json

@@ -71,6 +71,7 @@
                         "pages": [
                           "platform/features/v2-memory-filters",
                           "platform/features/entity-scoped-memory",
+                          "platform/features/graph-memory",
                           "platform/features/async-client",
                           "platform/features/multimodal-support",
                           "platform/features/custom-categories",
@@ -122,8 +123,7 @@
                     "icon": "arrow-right",
                     "pages": [
                       "migration/platform-v2-to-v3",
-                      "migration/oss-to-platform",
-                      "migration/api-changes"
+                      "migration/oss-to-platform"
                     ]
                   },
                   {
@@ -272,7 +272,8 @@
                               "components/embedders/models/lmstudio",
                               "components/embedders/models/together",
                               "components/embedders/models/langchain",
-                              "components/embedders/models/aws_bedrock"
+                              "components/embedders/models/aws_bedrock",
+                              "components/embedders/models/fastembed"
                             ]
                           }
                         ]
@@ -440,7 +441,7 @@
                       "integrations/flowise",
                       "integrations/langchain-tools",
                       "integrations/agentops",
-                      "integrations/keywords",
+                      "integrations/respan",
                       "integrations/raycast"
                     ]
                   }
@@ -532,6 +533,8 @@
                       "api-reference/organization/get-org",
                       "api-reference/organization/get-org-members",
                       "api-reference/organization/add-org-member",
+                      "api-reference/organization/update-org-member",
+                      "api-reference/organization/remove-org-member",
                       "api-reference/organization/delete-org"
                     ]
                   },
@@ -544,6 +547,9 @@
                       "api-reference/project/get-project",
                       "api-reference/project/get-project-members",
                       "api-reference/project/add-project-member",
+                      "api-reference/project/update-project",
+                      "api-reference/project/update-project-member",
+                      "api-reference/project/remove-project-member",
                       "api-reference/project/delete-project"
                     ]
                   },
@@ -623,6 +629,10 @@
     ]
   },
   "redirects": [
+    {
+      "source": "/components/rerankers/models/llm",
+      "destination": "/components/rerankers/models/llm_reranker"
+    },
     {
       "source": "/migration/breaking-changes",
       "destination": "/"
@@ -631,6 +641,10 @@
       "source": "/migration/v0-to-v1",
       "destination": "/"
     },
+    {
+      "source": "/migration/api-changes",
+      "destination": "/migration/oss-v2-to-v3"
+    },
     {
       "source": "/platform/features/expiration-date",
       "destination": "/"
@@ -647,10 +661,6 @@
       "source": "/open-source/features/custom-fact-extraction-prompt",
       "destination": "/open-source/features/custom-instructions"
     },
-    {
-      "source": "/platform/features/graph-memory",
-      "destination": "/migration/oss-v2-to-v3"
-    },
     {
       "source": "/cookbooks/essentials/choosing-memory-architecture-vector-vs-graph",
       "destination": "/migration/oss-v2-to-v3"
@@ -1025,7 +1035,7 @@
     },
     {
       "source": "/features/graph-memory",
-      "destination": "/migration/oss-v2-to-v3"
+      "destination": "/platform/features/graph-memory"
     },
     {
       "source": "/features/:slug",

docs/integrations.mdx

@@ -309,19 +309,21 @@ Here are the available integrations for Mem0:
   </Card>
 
   <Card
-    title="Keywords AI"
+    title="Respan"
     icon={
       <svg
         xmlns="http://www.w3.org/2000/svg"
         width="24"
         height="24"
-        viewBox="0 0 24 24"
+        viewBox="0 0 200 200"
         fill="none"
       >
-        <path fill-rule="evenodd" clip-rule="evenodd" d="M9.07513 1.1863C9.21663 1.07722 9.39144 1.01009 9.56624 1.01009C9.83261 1.01009 10.0823 1.12756 10.2405 1.33734L15.0101 7.4964V12.4136L16.4335 13.8401C16.7582 14.1673 16.7582 14.7043 16.4335 15.0316C16.1089 15.3588 15.5762 15.3588 15.2515 15.0316L13.3453 13.1016V8.07538L8.92529 2.36944V2.36105C8.64228 2.00024 8.70887 1.4716 9.07513 1.1863ZM18.976 14.4133C18.8344 14.3778 18.7003 14.3042 18.5894 14.1925L16.9163 12.5059C16.7249 12.3129 16.6416 12.0528 16.6749 11.8094V6.88385H16.6499L11.8553 0.691225C11.7282 0.529117 11.6716 0.333133 11.6803 0.140562C11.134 0.0481292 10.5726 0 10 0C4.47715 0 0 4.47715 0 10C0 15.5228 4.47715 20 10 20C13.9387 20 17.3456 17.7229 18.976 14.4133Z" fill="currentColor"></path>
+        <path d="M2.00635 190.234V9.76584H53.3558V29.5101H26.7223V170.562H53.3558V190.234H2.00635Z" fill="currentColor"></path>
+        <path d="M120.692 160.902C116.383 160.902 112.691 159.387 109.612 156.357C106.535 153.327 105.02 149.633 105.067 145.277C105.02 141.016 106.535 137.37 109.612 134.34C112.691 131.309 116.383 129.794 120.692 129.794C124.859 129.794 128.481 131.309 131.559 134.34C134.684 137.37 136.27 141.016 136.317 145.277C136.27 148.166 135.512 150.793 134.045 153.161C132.624 155.528 130.73 157.422 128.362 158.842C126.042 160.216 123.486 160.902 120.692 160.902Z" fill="currentColor"></path>
+        <path d="M197.993 9.76584V190.234H146.643V170.562H173.278V29.5101H146.643V9.76584H197.993Z" fill="currentColor"></path>
       </svg>
     }
-    href="/integrations/keywords"
+    href="/integrations/respan"
   >
     Build AI applications with persistent memory and comprehensive LLM observability.
   </Card>

docs/integrations/agno.mdx

@@ -73,7 +73,7 @@ client = MemoryClient()
 # Define the agent
 agent = Agent(
     name="Personal Agent",
-    model=OpenAIChat(id="gpt-4"),
+    model=OpenAIChat(id="gpt-5-mini"),
     description="You are a helpful personal agent that helps me with day to day activities."
                 "You can process both text and images.",
     markdown=True

docs/integrations/antigravity.mdx

@@ -65,6 +65,7 @@ The plugin uses the same shell scripts as Claude Code, Cursor, and Codex — hoo
 | **User prompt** | `UserPromptSubmit` | Searches relevant memories before each message |
 | **Pre-tool** | `PreToolUse` | Blocks MEMORY.md writes, enforces `user_id`/`app_id` on mem0 tools |
 | **Post-tool** | `PostToolUse` | Tracks stats, scans bash errors for related memories |
+| **Stop** | `Stop` | Stores a session summary when the session ends |
 
 ## Troubleshooting
 

docs/integrations/autogen.mdx

@@ -43,7 +43,7 @@ OPENAI_API_KEY = os.environ.get('OPENAI_API_KEY')
 memory_client = MemoryClient()
 agent = ConversableAgent(
     "chatbot",
-    llm_config={"config_list": [{"model": "gpt-4", "api_key": OPENAI_API_KEY}]},
+    llm_config={"config_list": [{"model": "gpt-5-mini", "api_key": OPENAI_API_KEY}]},
     code_execution_config=False,
     human_input_mode="NEVER",
 )
@@ -99,7 +99,7 @@ For more complex scenarios, you can create multiple agents:
 manager = ConversableAgent(
     "manager",
     system_message="You are a manager who helps in resolving complex customer issues.",
-    llm_config={"config_list": [{"model": "gpt-4", "api_key": OPENAI_API_KEY}]},
+    llm_config={"config_list": [{"model": "gpt-5-mini", "api_key": OPENAI_API_KEY}]},
     human_input_mode="NEVER"
 )
 

docs/integrations/claude-code.mdx

@@ -64,7 +64,7 @@ Add the Mem0 MCP server directly with a single command:
 npx mcp-add \
   --name mem0-mcp \
   --type http \
-  --url "https://mcp.mem0.ai/mcp" \
+  --url "https://mcp.mem0.ai/mcp/" \
   --clients "claude code"
 ```
 
@@ -138,11 +138,13 @@ When installed via the plugin marketplace, Mem0 hooks into Claude Code's lifecyc
 
 | Hook | Event | What it does |
 |------|-------|-------------|
+| **Setup** | `Setup` | Installs the mem0 SDK and dependencies (runs on init and maintenance) |
 | **Session start** | `SessionStart` | Loads prior memories and displays status banner |
 | **User prompt** | `UserPromptSubmit` | Searches relevant memories before each message; skips short prompts |
-| **Pre-tool** | `PreToolUse` | Blocks MEMORY.md writes, enforces `user_id`/`app_id` on mem0 tool calls |
+| **Pre-tool (3 handlers)** | `PreToolUse` | Blocks MEMORY.md writes; enforces `user_id`/`app_id` on mem0 tool calls; scans files being read for relevant memory context |
 | **Post-tool** | `PostToolUse` | Tracks stats, scans bash errors for related memories |
-| **Pre-compact** | `PreCompact` | Stores a session summary before context compaction |
+| **Stop** | `Stop` | Stores a session summary when the session ends |
+| **Pre-compact** | `PreCompact` | Stores a summary before the context is compacted |
 
 ## Example Workflow
 

docs/integrations/codex.mdx

@@ -41,7 +41,17 @@ Install the full plugin including MCP server, lifecycle hooks, and SDK skill.
    codex plugin marketplace add mem0ai/mem0
    ```
 
-2. Restart Codex, open the Plugin Directory, browse the **Mem0 Plugins** marketplace, and install **Mem0**.
+2. Install the plugin:
+
+   ```bash
+   codex plugin add mem0@mem0-plugins
+   ```
+
+   Or, in the app: restart Codex, open the Plugin Directory, browse the **Mem0 Plugins** marketplace, and install **Mem0**.
+
+<Note>
+  Step 1 is required for the app UI. Mem0 isn't in OpenAI's curated directory yet, so **without `codex plugin marketplace add`, Mem0 won't appear in the Codex app's Plugin Directory** — searching for it returns nothing. Adding the marketplace surfaces it (under **Created by you**) and makes it installable.
+</Note>
 
 <Info>
   Do not combine with Option B. The plugin manifest auto-registers the `mem0` MCP server, so adding both will create a duplicate registration.
@@ -49,27 +59,30 @@ Install the full plugin including MCP server, lifecycle hooks, and SDK skill.
 
 ### Option B — Direct MCP
 
-The fastest way to connect Codex to Mem0 — no plugin, no marketplace. Add to `~/.codex/config.toml`:
+The fastest way to connect Codex to Mem0 — no plugin, no marketplace. Add the MCP server with a single command:
+
+```bash
+codex mcp add mem0 --url https://mcp.mem0.ai/mcp/ --bearer-token-env-var MEM0_API_KEY
+```
+
+Or add it manually to `~/.codex/config.toml`:
 
 ```toml
 [mcp_servers.mem0]
-url = "https://mcp.mem0.ai/mcp"
+url = "https://mcp.mem0.ai/mcp/"
 bearer_token_env_var = "MEM0_API_KEY"
 ```
 
 Make sure `MEM0_API_KEY` is exported in the shell you launch Codex from, then restart Codex.
 
-<Info>
-  Codex's `codex mcp add` CLI only supports stdio MCP servers. Because Mem0's MCP is HTTP/streamable, you configure it by editing `config.toml` directly (or via the **Plugins → Connect to a custom MCP → Streamable HTTP** UI in the Codex app).
-</Info>
-
 This gives you the MCP tools but not the lifecycle hooks or SDK skill.
 
 ### Managing the Plugin
 
 ```bash
 codex plugin marketplace upgrade               # pull latest plugin versions
-codex plugin marketplace remove mem0-plugins   # unregister the marketplace
+codex plugin remove mem0@mem0-plugins          # uninstall the plugin (keeps the marketplace)
+codex plugin marketplace remove mem0-plugins   # unregister the marketplace entirely
 ```
 
 To update, run `codex plugin marketplace upgrade` to pull the latest from the Mem0 repo.
@@ -110,9 +123,10 @@ When installed via the plugin marketplace, Mem0 hooks into Codex's lifecycle to
 |------|-------|-------------|
 | **Session start** | `SessionStart` | Loads prior memories and displays status banner |
 | **User prompt** | `UserPromptSubmit` | Searches relevant memories before each message |
-| **Pre-tool** | `PreToolUse` | Blocks MEMORY.md writes, enforces `user_id`/`app_id` on mem0 tool calls |
+| **Pre-tool (3 handlers)** | `PreToolUse` | Blocks MEMORY.md writes; enforces `user_id`/`app_id` on mem0 tool calls; scans files being read for relevant memory context |
 | **Post-tool** | `PostToolUse` | Tracks stats, scans bash errors for related memories |
-| **Pre-compact** | `PreCompact` | Stores a session summary before context compaction |
+| **Stop** | `Stop` | Stores a session summary when the session ends |
+| **Pre-compact** | `PreCompact` | Stores a summary before the context is compacted |
 
 ## Example Workflow
 

docs/integrations/cursor.mdx

@@ -47,7 +47,7 @@ The fastest way to get started. Click the link below to install the Mem0 MCP ser
 npx mcp-add \
   --name mem0-mcp \
   --type http \
-  --url "https://mcp.mem0.ai/mcp" \
+  --url "https://mcp.mem0.ai/mcp/" \
   --clients "cursor"
 ```
 
@@ -108,9 +108,10 @@ When installed via the Cursor Marketplace, Mem0 hooks into Cursor's lifecycle:
 |------|-------|-------------|
 | **Session start** | `sessionStart` | Loads prior memories and displays status banner |
 | **User prompt** | `beforeSubmitPrompt` | Searches relevant memories before each message; skips short prompts |
-| **Pre-tool (2 handlers)** | `preToolUse` | Blocks MEMORY.md writes, enforces `user_id`/`app_id` on mem0 tool calls |
+| **Pre-tool (3 handlers)** | `preToolUse` | Blocks MEMORY.md writes; enforces `user_id`/`app_id` on mem0 tool calls; scans files being read for relevant memory context |
 | **Post-tool (2 handlers)** | `postToolUse` | Tracks stats, scans bash errors for related memories |
-| **Pre-compact** | `preCompact` | Stores a session summary before context compaction |
+| **Stop** | `stop` | Stores a session summary when the session ends |
+| **Pre-compact** | `preCompact` | Stores a summary before the context is compacted |
 
 ## Example Workflow
 

docs/integrations/elevenlabs.mdx

@@ -100,12 +100,12 @@ This section:
 Initialize both the ElevenLabs and Mem0 clients:
 
 ```python
-    # Initialize ElevenLabs client
-    client = ElevenLabs(api_key=API_KEY)
+# Initialize ElevenLabs client
+client = ElevenLabs(api_key=API_KEY)
 
-    # Initialize memory client and tools
-    client_tools = ClientTools()
-    mem0_client = AsyncMemoryClient()
+# Initialize memory client and tools
+client_tools = ClientTools()
+mem0_client = AsyncMemoryClient()
 ```
 
 Here we:
@@ -118,36 +118,36 @@ Here we:
 Define the two key memory functions that will be registered as tools:
 
 ```python
-    # Define memory-related functions for the agent
-    async def add_memories(parameters):
-        """Add a message to the memory store"""
-        message = parameters.get("message")
-        await mem0_client.add(
-            messages=message,
-            user_id=USER_ID
-        )
-        return "Memory added successfully"
+# Define memory-related functions for the agent
+async def add_memories(parameters):
+    """Add a message to the memory store"""
+    message = parameters.get("message")
+    await mem0_client.add(
+        messages=message,
+        user_id=USER_ID
+    )
+    return "Memory added successfully"
 
-    async def retrieve_memories(parameters):
-        """Retrieve relevant memories based on the input message"""
-        message = parameters.get("message")
+async def retrieve_memories(parameters):
+    """Retrieve relevant memories based on the input message"""
+    message = parameters.get("message")
 
-        # For Platform API, user_id goes in filters
-        filters = {"user_id": USER_ID}
+    # For Platform API, user_id goes in filters
+    filters = {"user_id": USER_ID}
 
-        # Search for relevant memories using the message as a query
-        results = await mem0_client.search(
-            query=message,
-            filters=filters
-        )
+    # Search for relevant memories using the message as a query
+    results = await mem0_client.search(
+        query=message,
+        filters=filters
+    )
 
-        # Extract and join the memory texts
-        memories = ' '.join([result["memory"] for result in results.get('results', [])])
-        print("[ Memories ]", memories)
+    # Extract and join the memory texts
+    memories = ' '.join([result["memory"] for result in results.get('results', [])])
+    print("[ Memories ]", memories)
 
-        if memories:
-            return memories
-        return "No memories found"
+    if memories:
+        return memories
+    return "No memories found"
 ```
 
 These functions:
@@ -171,9 +171,9 @@ These functions:
 Register the memory functions with the ElevenLabs ClientTools system:
 
 ```python
-    # Register the memory functions as tools for the agent
-    client_tools.register("addMemories", add_memories, is_async=True)
-    client_tools.register("retrieveMemories", retrieve_memories, is_async=True)
+# Register the memory functions as tools for the agent
+client_tools.register("addMemories", add_memories, is_async=True)
+client_tools.register("retrieveMemories", retrieve_memories, is_async=True)
 ```
 
 This allows the ElevenLabs agent to:
@@ -186,19 +186,19 @@ This allows the ElevenLabs agent to:
 Configure the conversation with ElevenLabs:
 
 ```python
-    # Initialize the conversation
-    conversation = Conversation(
-        client,
-        AGENT_ID,
-        # Assume auth is required when API_KEY is set
-        requires_auth=bool(API_KEY),
-        audio_interface=DefaultAudioInterface(),
-        client_tools=client_tools,
-        callback_agent_response=lambda response: print(f"Agent: {response}"),
-        callback_agent_response_correction=lambda original, corrected: print(f"Agent: {original} -> {corrected}"),
-        callback_user_transcript=lambda transcript: print(f"User: {transcript}"),
-        # callback_latency_measurement=lambda latency: print(f"Latency: {latency}ms"),
-    )
+# Initialize the conversation
+conversation = Conversation(
+    client,
+    AGENT_ID,
+    # Assume auth is required when API_KEY is set
+    requires_auth=bool(API_KEY),
+    audio_interface=DefaultAudioInterface(),
+    client_tools=client_tools,
+    callback_agent_response=lambda response: print(f"Agent: {response}"),
+    callback_agent_response_correction=lambda original, corrected: print(f"Agent: {original} -> {corrected}"),
+    callback_user_transcript=lambda transcript: print(f"User: {transcript}"),
+    # callback_latency_measurement=lambda latency: print(f"Latency: {latency}ms"),
+)
 ```
 
 This sets up the conversation with:
@@ -217,16 +217,16 @@ This sets up the conversation with:
 Start and manage the conversation:
 
 ```python
-    # Start the conversation
-    print(f"Starting conversation with user_id: {USER_ID}")
-    conversation.start_session()
+# Start the conversation
+print(f"Starting conversation with user_id: {USER_ID}")
+conversation.start_session()
 
-    # Handle Ctrl+C to gracefully end the session
-    signal.signal(signal.SIGINT, lambda sig, frame: conversation.end_session())
+# Handle Ctrl+C to gracefully end the session
+signal.signal(signal.SIGINT, lambda sig, frame: conversation.end_session())
 
-    # Wait for the conversation to end and get the conversation ID
-    conversation_id = conversation.wait_for_session_end()
-    print(f"Conversation ID: {conversation_id}")
+# Wait for the conversation to end and get the conversation ID
+conversation_id = conversation.wait_for_session_end()
+print(f"Conversation ID: {conversation_id}")
 
 
 if __name__ == '__main__':
@@ -445,4 +445,3 @@ By integrating ElevenLabs Conversational AI with Mem0, you can create voice agen
     Create voice-first AI applications
   </Card>
 </CardGroup>
-

docs/integrations/hermes.mdx

@@ -1,35 +1,42 @@
 ---
 title: Hermes Agent
-description: "Add long-term memory to Hermes agents using Mem0 as a pluggable memory provider with automatic background sync and zero-latency prefetch."
+description: "Add long-term memory to Hermes agents with Mem0, on managed Mem0 Cloud or fully self-hosted (OSS), with automatic background sync and zero-latency prefetch."
 ---
 
-Add long-term memory to [Hermes Agent](https://github.com/NousResearch/hermes-agent) — a self-improving AI agent CLI by Nous Research. Hermes has a pluggable memory system, and Mem0 is one of the supported providers. Once enabled, Mem0 automatically learns facts from your conversations and surfaces relevant ones before each turn — all without slowing down the chat.
+Add long-term memory to [Hermes Agent](https://github.com/NousResearch/hermes-agent), a self-improving AI agent CLI by Nous Research. Hermes has a pluggable memory system, and Mem0 is one of the supported providers. Once enabled, Mem0 learns facts from your conversations and surfaces relevant ones before each turn, without slowing down the chat.
 
-## Overview
+You can run Mem0 in two ways:
 
-Hermes runs a built-in memory system (file-based `MEMORY.md` and `USER.md`) alongside one external provider. When Mem0 is active, it works additively with the built-in system at three key moments in every conversation turn:
+- **Platform mode** (default): managed Mem0 Cloud. Add your API key and you are ready.
+- **OSS mode**: fully self-hosted with your own LLM, embedder, and vector store. No data leaves your machine.
 
-### 1. Before the Agent Responds (Prefetch)
+## How It Works
 
-When you send a message, Hermes checks if it already has cached Mem0 search results from the previous turn. If so, those memories are injected into the system prompt so the LLM can see them. This is **zero-latency** — no waiting for an API call.
+Hermes runs a built-in memory system (file-based `MEMORY.md` and `USER.md`) alongside one external provider. When Mem0 is active, it works additively with the built-in system at three points in every conversation turn.
 
-### 2. After the Agent Responds (Sync)
+### 1. Before the agent responds (prefetch)
 
-Once the LLM finishes responding, Hermes sends the `(user message, assistant response)` pair to Mem0's API in a **background thread**. Mem0's server-side LLM automatically extracts facts (e.g., "user prefers Python", "user works at Acme Corp") — you don't have to tell it what to remember.
+When you send a message, Hermes checks for cached Mem0 search results from the previous turn. If they exist, those memories are injected into the system prompt so the model can see them. This is zero-latency, with no waiting on an API call.
 
-### 3. Background Prefetch for Next Turn
+### 2. After the agent responds (sync)
 
-At the same time as sync, Hermes kicks off a background search on Mem0 to pre-load relevant memories for the next turn. By the time you type your next message, the memories are already cached.
+Once the model finishes, Hermes sends the `(user message, assistant response)` pair to Mem0 in a background thread. Mem0 extracts facts automatically (for example, "user prefers Python" or "user works at Acme Corp"), so you never have to tell it what to remember. Each write is tagged with the gateway channel it came from.
+
+### 3. Background prefetch for the next turn
+
+At the same time, Hermes runs a background search to pre-load relevant memories for your next message. By the time you type, the results are already cached.
 
 ## Agent Tools
 
-When Mem0 is active, the LLM gets three extra tools it can call during conversations:
+When Mem0 is active, the model gets five tools it can call during a conversation:
 
-| Tool | Description |
-|------|-------------|
-| `mem0_profile` | Fetch all stored memories about the user |
-| `mem0_search` | Semantic search through memories (supports optional reranking via `rerank` and `top_k` parameters) |
-| `mem0_conclude` | Store a specific fact verbatim — uses `infer=False` so no server-side LLM extraction happens |
+| Tool | Description | Parameters |
+|------|-------------|------------|
+| `mem0_list` | List all stored memories, for a full overview | `page`, `page_size` (default 100, max 200) |
+| `mem0_search` | Semantic search by meaning, ranked by relevance | `query` (required), `top_k` (default 10, max 50), `rerank` (default `true`, Platform mode only) |
+| `mem0_add` | Store a fact verbatim, with no LLM extraction | `content` (required) |
+| `mem0_update` | Update a memory's text by ID | `memory_id`, `text` (both required) |
+| `mem0_delete` | Delete a memory by ID | `memory_id` (required) |
 
 ## Installation
 
@@ -40,17 +47,19 @@ curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scri
 source ~/.bashrc
 ```
 
-The `mem0ai` Python package is automatically installed when you enable the Mem0 provider — no manual pip install needed.
+The `mem0ai` package is installed automatically when you enable the Mem0 provider, so there is no manual pip step. OSS providers may need extra packages (for example `qdrant-client`, `psycopg2-binary`, or `ollama`), which the setup flow installs for you when you pick them.
 
-## Setup
+## Platform Setup
 
-### Option 1: Interactive Setup Wizard (Recommended)
+Platform mode uses managed Mem0 Cloud and is the fastest way to start.
+
+### Option 1: Interactive wizard (recommended)
 
 ```bash
 hermes memory setup
 ```
 
-Select **mem0** as the provider and enter your Mem0 API key when prompted. The wizard writes your config to `~/.hermes/mem0.json`.
+Select **mem0**, choose **Platform**, and paste your API key when prompted. The wizard writes the non-secret settings to `~/.hermes/mem0.json` and keeps the key in `~/.hermes/.env`.
 
 <Note>Get your API key from <a href="https://app.mem0.ai?utm_source=oss&utm_medium=integration-hermes" rel="nofollow">app.mem0.ai</a>.</Note>
 
@@ -68,33 +77,151 @@ memory:
   provider: mem0
 ```
 
-That's it — Mem0 runs automatically from this point.
+That's it. Mem0 runs automatically from here.
 
-## Configuration Options
+## OSS (Self-Hosted) Setup
 
-Configuration is stored in `~/.hermes/mem0.json`. Values can also be set via environment variables.
+OSS mode runs Mem0 entirely on your own infrastructure: your LLM, your embedder, and your vector store. No data is sent to Mem0 Cloud, and no Mem0 API key is required.
 
-| Key | Env Variable | Default | Description |
-|-----|-------------|---------|-------------|
-| `api_key` | `MEM0_API_KEY` | — | **Required.** Mem0 Platform API key |
-| `user_id` | `MEM0_USER_ID` | `hermes-user` | User identifier for scoping memories |
-| `agent_id` | `MEM0_AGENT_ID` | `hermes` | Agent identifier |
-| `rerank` | — | `true` | Enable reranking for memory recall |
+### Interactive
+
+```bash
+hermes memory setup
+# Select "mem0", then "Open Source (self-hosted)"
+# Follow the prompts for LLM, embedder, and vector store
+```
+
+### With flags
+
+```bash
+hermes memory setup mem0 --mode oss \
+  --oss-llm openai --oss-llm-key sk-... \
+  --oss-vector qdrant
+```
+
+### Supported providers
+
+| Component | Providers |
+|-----------|-----------|
+| LLM | `openai` (default model `gpt-5-mini`), `ollama` (local, default `llama3.1:8b`) |
+| Embedder | `openai` (default `text-embedding-3-small`), `ollama` (local, default `nomic-embed-text`) |
+| Vector store | `qdrant` (local path or server), `pgvector` |
+
+### Flag reference
+
+| Flag | Description |
+|------|-------------|
+| `--mode` | `platform` or `oss` |
+| `--oss-llm` | LLM provider (`openai` or `ollama`, default `openai`) |
+| `--oss-llm-key` | LLM API key (for `openai`) |
+| `--oss-llm-model` | Override the LLM model |
+| `--oss-llm-url` | LLM base URL (for `ollama` or a custom endpoint) |
+| `--oss-embedder` | Embedder provider (default `openai`) |
+| `--oss-embedder-key` | Embedder API key |
+| `--oss-vector` | Vector store (`qdrant` or `pgvector`, default `qdrant`) |
+| `--oss-vector-path` | Local Qdrant storage path |
+| `--oss-vector-host`, `--oss-vector-port` | PGVector or remote Qdrant host and port |
+| `--oss-vector-user`, `--oss-vector-password`, `--oss-vector-dbname` | PGVector connection details |
+| `--user-id` | Canonical user identifier |
+| `--dry-run` | Preview the resolved config without writing it |
+
+## Switching Modes
+
+You can move between Platform and OSS at any time. Run the setup command again, or edit `~/.hermes/mem0.json` directly.
+
+```bash
+# Platform to OSS
+hermes memory setup mem0 --mode oss --oss-llm-key sk-...
+
+# OSS to Platform
+hermes memory setup mem0 --mode platform --api-key sk-...
+
+# Preview without writing anything
+hermes memory setup mem0 --mode oss --oss-llm-key sk-... --dry-run
+```
+
+A self-hosted `~/.hermes/mem0.json` looks like this:
+
+```json
+{
+  "mode": "oss",
+  "oss": {
+    "llm": {"provider": "openai", "config": {"model": "gpt-5-mini"}},
+    "embedder": {"provider": "openai", "config": {"model": "text-embedding-3-small"}},
+    "vector_store": {"provider": "qdrant", "config": {"path": "~/.hermes/mem0_qdrant"}}
+  }
+}
+```
+
+## Configuration
+
+Behavioral settings live in `~/.hermes/mem0.json` and are written for you by `hermes memory setup`. Only the secret `MEM0_API_KEY` belongs in `~/.hermes/.env`.
+
+| Key | Default | Description |
+|-----|---------|-------------|
+| `mode` | `platform` | `platform` (Mem0 Cloud) or `oss` (self-hosted) |
+| `api_key` | none | Mem0 Platform API key, required in Platform mode. Stored in `.env` as `MEM0_API_KEY` |
+| `user_id` | `hermes-user` | Identifier that scopes memories. See cross-channel behavior below |
+| `agent_id` | `hermes` | Agent identifier attached to writes |
+| `rerank` | `true` | Rerank search results for relevance (Platform mode only) |
+
+### Cross-channel memories
+
+Hermes can run from the CLI and from gateways like Telegram, Slack, and Discord. The `user_id` setting controls how memories are scoped across them:
+
+- **Set a `user_id`** and it applies to every gateway, so one person gets a single merged memory store no matter where they talk to the agent.
+- **Leave it unset** (or at the default `hermes-user`) and each gateway uses its own native id, keeping per-platform memories separate.
+
+Either way, every write is tagged with `metadata.channel` (for example `telegram` or `cli`), so per-channel views are still possible at query time.
 
 
 ## Reliability
 
-- **Circuit Breaker** — If Mem0's API fails 5 times in a row, Hermes stops calling it for 2 minutes, then retries. The agent keeps working fine without memory during that time.
-- **Non-blocking** — All Mem0 API calls happen in background daemon threads. A slow or failed API call never blocks your conversation.
-- **Thread-safe** — The Mem0 client uses lazy initialization with locking, safe for concurrent access.
+- **Circuit breaker**: if Mem0 fails five times in a row, Hermes pauses calls for two minutes, then retries. The agent keeps working without memory during that window. Expected client errors, like a 404 on a missing memory id, do not count toward tripping the breaker.
+- **Non-blocking**: every Mem0 call runs in a background daemon thread, so a slow or failed call never blocks your conversation.
+- **Thread-safe**: the client uses lazy initialization with locking, and the background sync and prefetch threads are guarded so concurrent gateway messages cannot produce duplicate memories.
+
+## Troubleshooting
+
+### "Mem0 temporarily unavailable"
+
+The circuit breaker tripped after five consecutive failures and resets after two minutes.
+
+- **Platform mode**: check your API key and internet connection.
+- **OSS mode**: make sure your vector store (Qdrant or PGVector) is running and reachable.
+
+### OSS: vector store connection refused
+
+```bash
+# Local Qdrant: confirm the storage path is writable
+ls -la ~/.hermes/mem0_qdrant
+
+# Qdrant server: confirm it is reachable
+curl http://localhost:6333/healthz
+
+# PGVector: confirm PostgreSQL is accepting connections
+pg_isready -h localhost -p 5432
+```
+
+### OSS: Ollama not reachable
+
+```bash
+curl http://localhost:11434/api/tags
+```
+
+### Memories not appearing
+
+- `mem0_add` stores text verbatim with no extraction. Ordinary conversation turns are extracted automatically by the background sync.
+- Search is semantic, so try a broader query.
+- Confirm `user_id` is the same across sessions (check `~/.hermes/mem0.json`).
 
 ## Key Features
 
-1. **Zero-Latency Recall** — Memories are prefetched in the background and cached, ready before you type
-2. **Server-side Extraction** — Mem0's API automatically extracts and deduplicates facts from each exchange
-3. **Non-blocking** — All API calls run in background daemon threads
-4. **Fault Tolerant** — Circuit breaker ensures the agent works even if Mem0 is temporarily unreachable
-5. **Additive Memory** — Works alongside Hermes' built-in file-based memory system (MEMORY.md, USER.md)
+1. **Two ways to run**: managed Platform or fully self-hosted OSS, switchable at any time.
+2. **Zero-latency recall**: memories are prefetched in the background and cached before you type.
+3. **Automatic extraction**: Mem0 extracts and deduplicates facts from each exchange for you.
+4. **Non-blocking and fault tolerant**: background threads plus a circuit breaker keep the agent responsive even when Mem0 is unreachable.
+5. **Additive memory**: works alongside Hermes' built-in file memory (`MEMORY.md`, `USER.md`).
 
 <CardGroup cols={2}>
   <Card title="OpenClaw Integration" icon={<svg width="24" height="24" viewBox="0 0 500 500" fill="none" xmlns="http://www.w3.org/2000/svg"><path fill-rule="evenodd" d="m153.5 173.5q24.62 1.46 46 13.5 12.11 8.1 17.5 21.5 0.74 2.45 0.5 5 0.09 0.81 1 1 1.48-4.9 1-10 5.04 10.48 1.5 22-9.81 27.86-35.5 42.5-26.17 14.97-56 19.5-2.77-0.4-2 1 2.86 1.27 6 1 25.64 1.53 48.5-10 0.34 10.08 2 20 1.08 5.76 5 10 1 1.5 0 3-31.11 20.84-68.5 17.5-23.7-5.7-32.5-28.5-4.39-9.18-3.5-19 15.41 6.23 32 4.5-20.68-6.39-39-18-34.81-27.22-12.5-65.5 11.84-14.83 29-23 4.21 7.66 11.5 12.5 3 1 6 0-26.04-34.62-29-78-0.13-8.46 2-16.5 1 6.5 2 13 3.43 39.53 24.5 73 2.03 2.28 4.5 4 0.5-1.25 1-2.5-1.27-6.54-5-12 0.5-0.75 1-1.5 9.72-3.43 20-4 0.55 10.34 8 17.5 1.94 0.74 4 0.5-17.8-64.6 16.5-122 0.98-1.79 1.5 0-28.21 56.64-13.5 118 1.08 1.43 2.5 0.5 2.21-4.98 2-10.5z" fill="currentColor"/><path fill-rule="evenodd" d="m454.5 97.5q-1.33 11.18-8.5 20-21.81 26.28-55.5 32-1.11-0.2-2 0.5 2.31 2.82 5.5 4.5 1 2 0 4-9.56 11.3-19.5 20 19.71-8.72 31-27 2.68-0.43 5 1-14.24 30.97-48 36.5-9.93 1.71-20 1.5-6.8-0.48-13 1 5.81 6.92 14 11-10.78 16.03-27 26.5 27.16-7.4 38-33.5 4.34 1.35 9 1-9.08 23.84-33 33.5-18.45 6.41-38 7 22.59 8.92 45-1 12.05-5.52 24-11 9.01-1.79 17 2.5 5.28-4.38 11-8 12.8-6.07 27-5 0 0.5 0 1-19.34 2.69-34 15.5 0.5 0.25 1 0.5 17.79-8.09 36-15 2.71-0.79 5-2 2.5-1 5-2 5.53-4.04 11-8 11.7-4.18 24-6.5 7.78-1.36 15 1.5-2.97 18.45-13.5 34-34.92 49.37-94.5 62.5-59.27 12.45-108-23-15.53-12.52-21.5-31.5-2.47-14.26 4-27-3.15 24.41 14 42-4.92-10.28-7-22-1.97-17.63 7-33 47.28-69.5 125.5-100 15.86-3.42 32-5.5 18.63-1.47 37 1.5z" fill="currentColor"/><path fill-rule="evenodd" d="m231.5 238.5q1.31-0.2 2 1-3.13 28.62 15 51-16.25 6.75-27-7.5-1-1-2 0 14.73 29.34 46 18.5 1.79 0.52 0 1.5-37.63 16.82-50.5-22.5-5.1-26.48 16.5-42z" fill="currentColor"/><path fill-rule="evenodd" d="m203.5 266.5q1.31-0.2 2 1-2.48 22.08 12 39-6.99 1.35-14 0.5 4.59 4.08 10 7-8.71 0.28-14.5-6.5-16.98-22.76 4.5-41z" fill="currentColor"/><path fill-rule="evenodd" d="m58.5 284.5q9.6-2.17 14.5 6 5.15 14.18-1 28-11.05-13.14-27.5-17.5 5.15-9.9 14-16.5z" fill="currentColor"/><path fill-rule="evenodd" d="m56.5 313.5q3.43 5.43 8 10-4.88 0.44-8 4-1.11-0.2-2 0.5 28.91 1.65 38 28.5 0.45 3.16-1 6-11.02-7.01-23-12.5-4.75-3.75-9.5-7.5 1.47 7.42 7 13 8.34 27.18 32 43 0.99 2.41-1.5 3.5-40.25 5.58-66.5-25.5-15.67-22.01-8-48 10.46-23.87 34.5-15z" fill="currentColor"/><path fill-rule="evenodd" d="m198.5 319.5q1.44 0.68 2.5 2 2.41 8.23 6 16 1.2 2.64-0.5 5-30.65 21.41-68 18.5-25.16-6.17-32.5-30.5 6.96 4.99 15.5 6.5 8.99 0.75 18 0.5 16.25 2.38 32-2.5 15.9-3.94 27-15.5z" fill="currentColor"/><path fill-rule="evenodd" d="m239.5 342.5q7.02-0.25 14 0.5 4.46 1.06 8 3.5-5.2 2.35-10 5.5-3.88 4.65-9 7.5-9.89-3.09-9.5-13 2.36-3.63 6.5-4z" fill="currentColor"/><path fill-rule="evenodd" d="m214.5 349.5q5.96 7.2 13.5 13 1 1 0 2-28.58 23.34-65.5 20.5-18.15-4.24-27.5-19.5 1.13 0.94 2.5 1.5 14.7 1.42 29-1.5 26.57-0.52 48-16z" fill="currentColor"/><path fill-rule="evenodd" d="m302.5 373.5q0.21 2.44-2 3.5-28.69 7.6-50.5-12.5-0.06-6.71 6.5-9 4.45-0.75 9-1 22.26 2.27 37 19z" fill="currentColor"/><path fill-rule="evenodd" d="m232.5 365.5q17.6 6.19 10.5 23-10.6 10.42-25.5 11.5-25.94 3.21-49-9 36.75-1.65 64-25.5z" fill="currentColor"/><path fill-rule="evenodd" d="m113.5 367.5q7.7-0.01 9.5 7-9.69 7.19-18.5 15.5-7.23 5.76-5.5-3.5 3.12-12.84 14.5-19z" fill="currentColor"/><path fill-rule="evenodd" d="m126.5 380.5q7.88-0.4 12 6.5-8.5 7.25-17 14.5-5.62-12.55 5-21z" fill="currentColor"/><path fill-rule="evenodd" d="m283.5 385.5q3.22 2.95 7 5.5 2.8 4.03 6 7.5 0.42 2.77-2 4-15.5-9.75-31-19.5-1.79-0.98 0-1.5 9.96 2.49 20 4z" fill="currentColor"/></svg>} href="/integrations/openclaw">

docs/integrations/langchain-tools.mdx

@@ -98,20 +98,9 @@ add_result = add_tool.invoke(add_input)
 
 ```json Output
 {
-  "results": [
-    {
-      "memory": "Name is Alex",
-      "event": "ADD"
-    },
-    {
-      "memory": "Is a vegetarian", 
-      "event": "ADD"
-    },
-    {
-      "memory": "Is allergic to nuts",
-      "event": "ADD"
-    }
-  ]
+  "message": "Memory processing has been queued for background execution",
+  "status": "PENDING",
+  "event_id": "3a1b2c3d-4e5f-6789-abcd-ef0123456789"
 }
 ```
 </CodeGroup>
@@ -173,23 +162,25 @@ result = search_tool.invoke(search_input)
 ```
 
 ```json Output
-[
-  {
-    "id": "1a75e827-7eca-45ea-8c5c-cfd43299f061",
-    "memory": "Name is Alex",
-    "user_id": "alex", 
-    "hash": "d0fccc8fa47f7a149ee95750c37bb0ca",
-    "metadata": {
-      "food": "vegan"
-    },
-    "categories": [
-      "personal_details"
-    ],
-    "created_at": "2024-11-27T16:53:43.276872-08:00",
-    "updated_at": "2024-11-27T16:53:43.276885-08:00",
-    "score": 0.3810526501504994
-  }
-]
+{
+  "results": [
+    {
+      "id": "1a75e827-7eca-45ea-8c5c-cfd43299f061",
+      "memory": "Name is Alex",
+      "user_id": "alex",
+      "hash": "d0fccc8fa47f7a149ee95750c37bb0ca",
+      "metadata": {
+        "food": "vegan"
+      },
+      "categories": [
+        "personal_details"
+      ],
+      "created_at": "2024-11-27T16:53:43.276872-08:00",
+      "updated_at": "2024-11-27T16:53:43.276885-08:00",
+      "score": 0.3810526501504994
+    }
+  ]
+}
 ```
 </CodeGroup>
 

docs/integrations/langgraph.mdx

@@ -41,7 +41,7 @@ load_dotenv()
 # MEM0_API_KEY = 'your-mem0-key'  # Replace with your actual Mem0 API key
 
 # Initialize LangChain and Mem0
-llm = ChatOpenAI(model="gpt-4")
+llm = ChatOpenAI(model="gpt-5-mini")
 mem0 = MemoryClient()
 ```
 

docs/integrations/opencode.mdx

@@ -1,6 +1,6 @@
 ---
 title: OpenCode
-description: "Add persistent memory to OpenCode with the Mem0 plugin — MCP server, lifecycle hooks, and slash commands."
+description: "Add persistent memory to OpenCode with the Mem0 plugin — native SDK-backed memory tools, lifecycle hooks, and skills."
 ---
 
 Add persistent memory to [**OpenCode**](https://opencode.ai) with the Mem0 plugin. Your agent forgets everything between sessions — Mem0 fixes that by storing decisions, preferences, and learnings so they carry over automatically.
@@ -30,27 +30,17 @@ echo 'export MEM0_API_KEY="m0-your-api-key"' >> ~/.bashrc && source ~/.bashrc
 opencode plugin @mem0/opencode-plugin
 ```
 
-
-Or using this command which does the same thing:
-
-
-```bash
-bunx @mem0/opencode-plugin@latest install
-```
-
-
-
 **Or let your agent do it** — paste this into OpenCode:
 
 ```
 Install @mem0/opencode-plugin by following https://raw.githubusercontent.com/mem0ai/mem0/main/integrations/mem0-plugin/.opencode-plugin/README.md
 ```
 
-All commands auto-add the plugin and MCP server to your `~/.config/opencode/opencode.json`. Restart OpenCode — you get the MCP server, lifecycle hooks, and all `/mem0:` slash commands.
+This adds the plugin to your `~/.config/opencode/opencode.json`. Restart OpenCode — you get the native memory tools, lifecycle hooks, and all `/mem0-*` slash commands. The memory tools are registered by the plugin itself via the `mem0ai` SDK — no MCP server to configure.
 
-### Option B — MCP Only
+### Option B — Standalone MCP Server
 
-If you only need the memory tools without hooks or skills, add this to your `opencode.json` (project-level or global at `~/.config/opencode/opencode.json`):
+If you only need the memory tools without the plugin's hooks or skills, point OpenCode at Mem0's hosted MCP server directly. Add this to your `opencode.json` (project-level or global at `~/.config/opencode/opencode.json`):
 
 ```json
 {
@@ -69,13 +59,13 @@ If you only need the memory tools without hooks or skills, add this to your `ope
 
 ## What's Included
 
-| Component | Plugin (A) | MCP Only (B) |
-|-----------|:----------:|:------------:|
-| MCP Server (9 memory tools) | Yes | Yes |
+| Component | Plugin (A) | Standalone MCP (B) |
+|-----------|:----------:|:------------------:|
+| 9 memory tools | Native (SDK) | Remote MCP server |
 | Lifecycle Hooks | Yes | No |
-| 16 Slash Commands | Yes | No |
+| 9 Skills | Yes | No |
 
-## Available MCP Tools
+## Available Memory Tools
 
 | Tool | Description |
 |------|-------------|
@@ -89,25 +79,70 @@ If you only need the memory tools without hooks or skills, add this to your `ope
 | `delete_entities` | Delete a user/agent/app/run entity and its memories |
 | `list_entities` | List users/agents/apps/runs stored in Mem0 |
 
+## Memory scope
+
+`search_memories`, `get_memories`, `add_memory`, and `delete_all_memories` accept an optional **`scope`** that controls how widely they read or write:
+
+| Scope | Reads | Writes |
+|-------|-------|--------|
+| `project` *(default)* | this repo (`user_id` + `app_id`) | this repo |
+| `session` | this run only (`+ run_id`) | this run |
+| `global` | **all your projects in the workspace** (`app_id: "*"`) | user-wide |
+
+Just ask naturally — e.g. *"search my memories across all my projects"* — and the agent passes `scope: "global"`. For normal questions it stays scoped to the current project automatically.
+
+To change the **default** scope (used when no scope is passed), run the `/mem0-scope` skill:
+
+```
+/mem0-scope            # show the current default scope + identity
+/mem0-scope global     # save & search across all your projects by default
+/mem0-scope project    # back to repo-only (the default)
+```
+
+The default persists in `~/.mem0/settings.json` (`default_scope`) and is read fresh on each memory operation, so a change applies immediately — no restart. `delete_all_memories` always requires an explicit `scope: "global"` to delete user-wide, so changing the default can't trigger a cross-project wipe.
+
+The project id (`app_id`) is derived from your git remote (`owner-repo`), falling back to the git repo's root directory name, then the current directory. Launch OpenCode from inside your repo so memories scope to the project rather than your home directory.
+
 ## Lifecycle Hooks
 
 The plugin uses the [mem0ai](https://www.npmjs.com/package/mem0ai) TypeScript SDK directly — pure TypeScript, no Python, no shell scripts.
 
 | OpenCode Event | Hook | What happens |
 |----------------|------|-------------|
+| `config` | **Config** | Registers the `/mem0-*` slash commands (`config.command`) and adds the plugin's own `opencode-skills/` dir to OpenCode's `skills.paths` for in-place skill discovery (no copying) |
 | `chat.message` | **Chat message** | Searches prior memories on session start, searches relevant memories before each prompt, auto-captures learnings periodically |
-| `tool.execute.before` | **Pre-tool** | Blocks MEMORY.md writes, injects `user_id`/`app_id` on mem0 tool calls |
-| `tool.execute.after` | **Post-tool** | Tracks stats, scans Bash errors and pre-fetches related error memories |
-| `experimental.chat.system.transform` | **System transform** | Injects memory context (session memories, search results, error lookups) into the system prompt |
+| `tool.execute.before` | **Pre-tool** | Blocks MEMORY.md writes, steering them to the `add_memory` tool |
+| `tool.execute.after` | **Post-tool** | Scans Bash errors and pre-fetches related error memories |
+| `experimental.chat.messages.transform` | **Messages transform** | Injects memory context (session memories, search results, error lookups) into the prompt |
 | `experimental.session.compacting` | **Compaction** | Stores session state memory, then injects prior memories into compaction context so nothing is lost |
 | `shell.env` | **Shell env** | Exports `MEM0_USER_ID`, `MEM0_APP_ID`, `MEM0_SESSION_ID`, and `MEM0_BRANCH` to all shell executions |
 
+## Auto-dream (memory consolidation)
+
+The plugin can automatically consolidate stored memories — merging duplicates, dropping stale/sensitive entries, and rewriting vague ones — so your memory set stays clean over time. It runs at most once per session, and only when **all** gates pass:
+
+- **Time** — at least `minHours` (default 24) since the last consolidation
+- **Sessions** — at least `minSessions` (default 5) sessions since then
+- **Memories** — at least `minMemories` (default 20) stored for the project
+
+A filesystem lock (`~/.mem0/mem0-dream.lock`) keeps two sessions from consolidating at once. Tune the thresholds with a `dream` block in `~/.mem0/settings.json`, or disable entirely with `MEM0_DREAM=false`:
+
+```json
+{
+  "dream": { "enabled": true, "auto": true, "minHours": 24, "minSessions": 5, "minMemories": 20 }
+}
+```
+
+If auto-dream hasn't run yet, it's almost always because a gate hasn't been met (most often too few memories). Run `/mem0-status` to see the exact gate progress (e.g. `sessions 2/5, memories 3/20`), `/mem0-dream` to consolidate **now** regardless of the gates, or lower the thresholds above.
+
 ## Troubleshooting
 
 - **No tools appearing** — Restart OpenCode after installing
 - **"Connection failed"** — Verify your key is set: `echo $MEM0_API_KEY`
 - **Plugin not loading** — Run `opencode plugin @mem0/opencode-plugin` again, then restart
 - **Hooks not firing** — Hooks require the plugin install (Option A). MCP-only installs don't include hooks.
+- **Auto-dream never runs** — It's gated (time + sessions + memories). Run `/mem0-status` to see which gate is blocking, or `/mem0-dream` to consolidate now.
+- **Wrong project name / memories not found** — The project id comes from your git remote; launch OpenCode from inside the repo (not your home directory). Check the resolved id with `/mem0-status`.
 
 <CardGroup cols={2}>
   <Card title="Mem0 MCP Setup" icon="puzzle-piece" href="/platform/mem0-mcp">

docs/integrations/pipecat.mdx

@@ -121,7 +121,7 @@ async def websocket_endpoint(websocket: WebSocket):
     # LLM for response generation
     llm = OpenAILLMService(
         api_key=os.getenv("OPENAI_API_KEY"),
-        model="gpt-3.5-turbo",
+        model="gpt-5-mini",
         system_prompt="You are a helpful assistant that remembers past conversations."
     )
     

docs/integrations/respan.mdx

@@ -1,22 +1,22 @@
 ---
-title: Keywords AI
-description: "Combine Mem0 persistent memory with Keywords AI observability for tracked, cost-optimized AI applications."
+title: Respan
+description: "Combine Mem0 persistent memory with Respan observability for tracked, cost-optimized AI applications."
 ---
 
-Build AI applications with persistent memory and comprehensive LLM observability by integrating Mem0 with Keywords AI.
+Build AI applications with persistent memory and comprehensive LLM observability by integrating Mem0 with Respan.
 
 ## Overview
 
-Mem0 is a self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users. Keywords AI provides complete LLM observability.
+Mem0 is a self-improving memory layer for LLM applications, enabling personalized AI experiences that save costs and delight users. Respan (formerly Keywords AI) provides complete LLM observability.
 
-Combining Mem0 with Keywords AI allows you to:
+Combining Mem0 with Respan allows you to:
 1. Add persistent memory to your AI applications
 2. Track interactions across sessions
-3. Monitor memory usage and retrieval with Keywords AI observability
+3. Monitor memory usage and retrieval with Respan observability
 4. Optimize token usage and reduce costs
 
 <Note>
-You can get your Mem0 API key from the <a href="https://app.mem0.ai/?utm_source=oss&utm_medium=integration-keywords" rel="nofollow">Mem0 dashboard</a>.
+You can get your Mem0 API key from the <a href="https://app.mem0.ai/?utm_source=oss&utm_medium=integration-respan" rel="nofollow">Mem0 dashboard</a>.
 </Note>
 
 ## Setup and Configuration
@@ -24,7 +24,7 @@ You can get your Mem0 API key from the <a href="https://app.mem0.ai/?utm_source=
 Install the necessary libraries:
 
 ```bash
-pip install mem0ai keywordsai-sdk
+pip install mem0ai openai
 ```
 
 Set up your environment variables:
@@ -34,13 +34,13 @@ import os
 
 # Set your API keys
 os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
-os.environ["KEYWORDSAI_API_KEY"] = "your-keywords-api-key"
-os.environ["KEYWORDSAI_BASE_URL"] = "https://api.keywordsai.co/api/"
+os.environ["RESPAN_API_KEY"] = "your-respan-api-key"
+os.environ["RESPAN_BASE_URL"] = "https://api.respan.ai/api/"
 ```
 
 ## Basic Integration Example
 
-Here's a simple example of using Mem0 with Keywords AI:
+Here's a simple example of using Mem0 with Respan:
 
 ```python
 from mem0 import Memory
@@ -48,17 +48,17 @@ import os
 
 # Configuration
 api_key = os.getenv("MEM0_API_KEY")
-keywordsai_api_key = os.getenv("KEYWORDSAI_API_KEY")
-base_url = os.getenv("KEYWORDSAI_BASE_URL") # "https://api.keywordsai.co/api/"
+respan_api_key = os.getenv("RESPAN_API_KEY")
+base_url = os.getenv("RESPAN_BASE_URL") # "https://api.respan.ai/api/"
 
-# Set up Mem0 with Keywords AI as the LLM provider
+# Set up Mem0 with Respan as the LLM provider
 config = {
     "llm": {
         "provider": "openai",
         "config": {
             "model": "gpt-5-mini",
             "temperature": 0.0,
-            "api_key": keywordsai_api_key,
+            "api_key": respan_api_key,
             "openai_base_url": base_url,
         },
     }
@@ -79,7 +79,7 @@ print(result)
 
 ## Advanced Integration with OpenAI SDK
 
-For more advanced use cases, you can integrate Keywords AI with Mem0 through the OpenAI SDK:
+For more advanced use cases, you can integrate Respan with Mem0 through the OpenAI SDK:
 
 ```python
 from openai import OpenAI
@@ -88,8 +88,8 @@ import json
 
 # Initialize client
 client = OpenAI(
-    api_key=os.environ.get("KEYWORDSAI_API_KEY"),
-    base_url=os.environ.get("KEYWORDSAI_BASE_URL"),
+    api_key=os.environ.get("RESPAN_API_KEY"),
+    base_url=os.environ.get("RESPAN_BASE_URL"),
 )
 
 # Sample conversation messages
@@ -118,18 +118,18 @@ response = client.chat.completions.create(
 print(json.dumps(response.model_dump(), indent=4))
 ```
 
-For detailed information on this integration, refer to the official [Keywords AI Mem0 integration documentation](https://docs.keywordsai.co/integration/development-frameworks/mem0).
+For detailed information on this integration, refer to the official [Respan Mem0 integration documentation](https://www.respan.ai/docs/integrations/mem0).
 
 ## Key Features
 
 1. **Memory Integration**: Store and retrieve relevant information from past interactions
-2. **LLM Observability**: Track memory usage and retrieval patterns with Keywords AI
+2. **LLM Observability**: Track memory usage and retrieval patterns with Respan
 3. **Session Persistence**: Maintain context across multiple user sessions
 4. **Cost Optimization**: Reduce token usage through efficient memory retrieval
 
 ## Conclusion
 
-Integrating Mem0 with Keywords AI provides a powerful combination for building AI applications with persistent memory and comprehensive observability. This integration enables more personalized user experiences while providing insights into your application's memory usage.
+Integrating Mem0 with Respan provides a powerful combination for building AI applications with persistent memory and comprehensive observability. This integration enables more personalized user experiences while providing insights into your application's memory usage.
 
 <CardGroup cols={2}>
   <Card title="OpenAI Agents SDK" icon="cube" href="/integrations/openai-agents-sdk">
@@ -139,4 +139,3 @@ Integrating Mem0 with Keywords AI provides a powerful combination for building A
     Monitor agent performance with AgentOps
   </Card>
 </CardGroup>
-

docs/integrations/vercel-ai-sdk.mdx

@@ -26,12 +26,12 @@ Install the SDK provider and AI SDK:
 npm install @mem0/vercel-ai-provider ai@^6
 ```
 
-### Peer Dependencies
+### Dependencies
 
-`@mem0/vercel-ai-provider` v3.0.0 requires:
-- `ai` v6+ (`^6.0.199`)
-- `@ai-sdk/provider` v3+ (`^3.0.10`)
-- Provider packages at v3+: `@ai-sdk/openai@^3`, `@ai-sdk/anthropic@^3`, `@ai-sdk/google@^3`, `@ai-sdk/groq@^3`, `@ai-sdk/cohere@^3`
+`@mem0/vercel-ai-provider` bundles `ai`, all `@ai-sdk/*` provider packages, and `@ai-sdk/provider` as regular dependencies — you do **not** need to install them separately. The install command above (`npm install @mem0/vercel-ai-provider ai@^6`) is sufficient.
+
+The only true peer dependency is `zod` (optional):
+- `zod` v3+ (`^3.0.0`) — required only if you use Zod schemas in tool definitions
 
 ## Getting Started
 
@@ -305,6 +305,8 @@ These options can be passed per-request when creating a model instance:
 | `rerank` | `boolean` | Enable reranking of results |
 | `page` | `number` | Page number for pagination |
 | `page_size` | `number` | Results per page |
+| `mem0ApiKey` | `string` | Mem0 API key; overrides the `MEM0_API_KEY` env var |
+| `host` | `string` | Custom Mem0 API base URL for self-hosted deployments |
 
 ## Key Features
 
@@ -312,6 +314,7 @@ These options can be passed per-request when creating a model instance:
 - `retrieveMemories()`: Retrieves memory context for prompts as a formatted system prompt string.
 - `getMemories()`: Get memories from your profile in array format.
 - `addMemories()`: Adds user memories to enhance contextual responses.
+- `searchMemories()`: Searches memories and returns the raw results array (semantic search rather than the full retrieval pipeline).
 
 ## Migrating from v2.x
 

docs/llms.txt

@@ -197,6 +197,7 @@ If the user is on a pre-current major (Python < 2, TS < 3, or Platform `output_f
 - [Platform Features Overview](https://docs.mem0.ai/platform/features/platform-overview) [Platform]: Use when surveying what managed offers beyond CRUD.
 - [V2 Memory Filters](https://docs.mem0.ai/platform/features/v2-memory-filters) [Platform]: Use when compound filters (AND/OR on metadata, entity, time) are needed at search.
 - [Entity-Scoped Memory](https://docs.mem0.ai/platform/features/entity-scoped-memory) [Platform]: Use when partitioning memories by user, agent, app, or run.
+- [Graph Memory](https://docs.mem0.ai/platform/features/graph-memory) [Platform]: Use when connecting facts across memories through shared entities for entity-centric or multi-hop questions.
 - [Async Client](https://docs.mem0.ai/platform/features/async-client) [Platform]: Use when the app issues many concurrent Mem0 calls and needs non-blocking I/O.
 - [Multimodal Support](https://docs.mem0.ai/platform/features/multimodal-support) [Platform]: Use when storing images or PDFs as memory input.
 - [Custom Categories](https://docs.mem0.ai/platform/features/custom-categories) [Platform]: Use when the default categories do not match the domain.
@@ -227,7 +228,6 @@ If the user is on a pre-current major (Python < 2, TS < 3, or Platform `output_f
 - [OSS to Platform Migration](https://docs.mem0.ai/migration/oss-to-platform) [Both]: Use when moving from self-hosted to managed.
 - [OSS v2 to v3 Migration](https://docs.mem0.ai/migration/oss-v2-to-v3) [OSS]: Use when upgrading a self-hosted deployment across major versions.
 - [Platform v2 to v3 Migration](https://docs.mem0.ai/migration/platform-v2-to-v3) [Platform]: Use when upgrading a Platform integration across major versions.
-- [API Changes](https://docs.mem0.ai/migration/api-changes) [Both]: Use when the upgrade involves API surface changes.
 - [Server pgvector Image Upgrade](https://docs.mem0.ai/migration/server-pgvector-upgrade) [OSS]: Use when upgrading the self-hosted server Docker image from ankane/pgvector to pgvector/pgvector.
 - [Changelog](https://docs.mem0.ai/changelog/highlights) [Both]: Use when the user asks what shipped recently.
 
@@ -285,7 +285,7 @@ If the user is on a pre-current major (Python < 2, TS < 3, or Platform `output_f
 - [Dify](https://docs.mem0.ai/integrations/dify) [Both]: Use when the user is on Dify LLMOps.
 - [Flowise](https://docs.mem0.ai/integrations/flowise) [Both]: Use when the user is on Flowise no-code.
 - [AgentOps](https://docs.mem0.ai/integrations/agentops) [Both]: Use when tracking agent observability with memory metadata.
-- [Keywords AI](https://docs.mem0.ai/integrations/keywords) [Both]: Use when monitoring with Keywords AI.
+- [Respan](https://docs.mem0.ai/integrations/respan) [Both]: Use when monitoring Mem0 with Respan (formerly Keywords AI) LLM observability.
 - [Raycast](https://docs.mem0.ai/integrations/raycast) [Both]: Use when the user wants quick memory access via Raycast.
 
 ## Cookbooks
@@ -366,6 +366,8 @@ All API Reference docs describe Mem0 Platform REST endpoints (requires API key).
 - [Get Organization](https://docs.mem0.ai/api-reference/organization/get-org) [Platform]: Use when fetching one org.
 - [Get Organization Members](https://docs.mem0.ai/api-reference/organization/get-org-members) [Platform]: Use when listing org members.
 - [Add Organization Member](https://docs.mem0.ai/api-reference/organization/add-org-member) [Platform]: Use when inviting a member to an org.
+- [Update Organization Member](https://docs.mem0.ai/api-reference/organization/update-org-member) [Platform]: Use when updating an org member's role.
+- [Remove Organization Member](https://docs.mem0.ai/api-reference/organization/remove-org-member) [Platform]: Use when removing a member from an organization.
 - [Delete Organization](https://docs.mem0.ai/api-reference/organization/delete-org) [Platform]: Use when removing an org.
 
 ### Projects
@@ -374,6 +376,9 @@ All API Reference docs describe Mem0 Platform REST endpoints (requires API key).
 - [Get Project](https://docs.mem0.ai/api-reference/project/get-project) [Platform]: Use when fetching one project.
 - [Get Project Members](https://docs.mem0.ai/api-reference/project/get-project-members) [Platform]: Use when listing project members.
 - [Add Project Member](https://docs.mem0.ai/api-reference/project/add-project-member) [Platform]: Use when inviting a member to a project.
+- [Update Project](https://docs.mem0.ai/api-reference/project/update-project) [Platform]: Use when updating project settings.
+- [Update Project Member](https://docs.mem0.ai/api-reference/project/update-project-member) [Platform]: Use when updating a project member's role.
+- [Remove Project Member](https://docs.mem0.ai/api-reference/project/remove-project-member) [Platform]: Use when removing a member from a project.
 - [Delete Project](https://docs.mem0.ai/api-reference/project/delete-project) [Platform]: Use when removing a project.
 
 ### Webhooks
@@ -459,6 +464,7 @@ Everything below is OSS-only provider configuration. Skip this entire section wh
 - [LM Studio Embeddings](https://docs.mem0.ai/components/embedders/models/lmstudio) [OSS]: Use when embeddings run through LM Studio.
 - [Together Embeddings](https://docs.mem0.ai/components/embedders/models/together) [OSS]: Use when embeddings run on Together.
 - [LangChain Embeddings](https://docs.mem0.ai/components/embedders/models/langchain) [OSS]: Use when embeddings are wrapped behind a LangChain adapter.
+- [FastEmbed](https://docs.mem0.ai/components/embedders/models/fastembed) [OSS]: Use when embeddings run locally via FastEmbed (ONNX).
 
 ### Vector Databases [OSS]
 - [Vector Database Overview](https://docs.mem0.ai/components/vectordbs/overview) [OSS]: Use when choosing a vector store.
@@ -497,7 +503,5 @@ Everything below is OSS-only provider configuration. Skip this entire section wh
 - [Custom Reranker Prompts](https://docs.mem0.ai/components/rerankers/custom-prompts) [OSS]: Use when rewriting reranker prompts.
 - [Cohere Reranker](https://docs.mem0.ai/components/rerankers/models/cohere) [OSS]: Use for Cohere Rerank.
 - [Sentence Transformer Reranker](https://docs.mem0.ai/components/rerankers/models/sentence_transformer) [OSS]: Use for local cross-encoder rerankers.
-- [Hugging Face Reranker](https://docs.mem0.ai/components/rerankers/models/huggingface) [OSS]: Use for HF-hosted reranker models.
-- [LLM Reranker (prompt)](https://docs.mem0.ai/components/rerankers/models/llm) [OSS]: Use when the reranker is a prompted LLM (config guide).
-- [LLM Reranker](https://docs.mem0.ai/components/rerankers/models/llm_reranker) [OSS]: Use when the reranker is a prompted LLM (implementation reference).
+- [Hugging Face Reranker](https://docs.mem0.ai/components/rerankers/models/huggingface) [OSS]: Use for HF-hosted reranker models.- [LLM Reranker](https://docs.mem0.ai/components/rerankers/models/llm_reranker) [OSS]: Use when the reranker is a prompted LLM (implementation reference).
 - [Zero Entropy Reranker](https://docs.mem0.ai/components/rerankers/models/zero_entropy) [OSS]: Use for the Zero Entropy reranker.

docs/migration/api-changes.mdx

@@ -1,566 +0,0 @@
----
-title: API Reference Changes
-description: "Comprehensive reference of all API changes between Mem0 v0.x and v1.0.0 Beta, organized by component and method."
-icon: "code"
-iconType: "solid"
----
-
-## Overview
-
-This page documents all API changes between Mem0 v0.x and v1.0.0 Beta, organized by component and method.
-
-## Memory Class Changes
-
-### Constructor
-
-#### v0.x
-```python
-from mem0 import Memory
-
-# Basic initialization
-m = Memory()
-
-# With configuration
-config = {
-    "version": "v1.0",  # Supported in v0.x
-    "vector_store": {...}
-}
-m = Memory.from_config(config)
-```
-
-#### v1.0.0 
-```python
-from mem0 import Memory
-
-# Basic initialization (same)
-m = Memory()
-
-# With configuration
-config = {
-    "version": "v1.1",  # v1.1+ only
-    "vector_store": {...},
-    # New optional features
-    "reranker": {
-        "provider": "cohere",
-        "config": {...}
-    }
-}
-m = Memory.from_config(config)
-```
-
-### add() Method
-
-#### v0.x Signature
-```python
-def add(
-    self,
-    messages,
-    user_id: str = None,
-    agent_id: str = None,
-    run_id: str = None,
-    metadata: dict = None,
-    filters: dict = None,
-    output_format: str = None,  # ❌ REMOVED
-    version: str = None         # ❌ REMOVED
-) -> Union[List[dict], dict]
-```
-
-#### v1.0.0  Signature
-```python
-def add(
-    self,
-    messages,
-    user_id: str = None,
-    agent_id: str = None,
-    run_id: str = None,
-    metadata: dict = None,
-    filters: dict = None,
-    infer: bool = True          # ✅ NEW: Control memory inference
-) -> dict  # Always returns dict with "results" key
-```
-
-#### Changes Summary
-
-| Parameter | v0.x | v1.0.0  | Change |
-|-----------|------|-----------|---------|
-| `messages` | ✅ | ✅ | Unchanged |
-| `user_id` | ✅ | ✅ | Unchanged |
-| `agent_id` | ✅ | ✅ | Unchanged |
-| `run_id` | ✅ | ✅ | Unchanged |
-| `metadata` | ✅ | ✅ | Unchanged |
-| `filters` | ✅ | ✅ | Unchanged |
-| `output_format` | ✅ | ❌ | **REMOVED** |
-| `version` | ✅ | ❌ | **REMOVED** |
-| `infer` | ❌ | ✅ | **NEW** |
-
-#### Response Format Changes
-
-**v0.x Response (variable format):**
-```python
-# With output_format="v1.0"
-[
-    {
-        "id": "mem_123",
-        "memory": "User loves pizza",
-        "event": "ADD"
-    }
-]
-
-# With output_format="v1.1"
-{
-    "results": [
-        {
-            "id": "mem_123",
-            "memory": "User loves pizza",
-            "event": "ADD"
-        }
-    ]
-}
-```
-
-**v1.0.0  Response (standardized):**
-```python
-# Always returns this format
-{
-    "results": [
-        {
-            "id": "mem_123",
-            "memory": "User loves pizza",
-            "metadata": {...},
-            "event": "ADD"
-        }
-    ]
-}
-```
-
-### search() Method
-
-#### v0.x Signature
-```python
-def search(
-    self,
-    query: str,
-    user_id: str = None,
-    agent_id: str = None,
-    run_id: str = None,
-    limit: int = 100,
-    filters: dict = None,       # Basic key-value only
-    output_format: str = None,  # ❌ REMOVED
-    version: str = None         # ❌ REMOVED
-) -> Union[List[dict], dict]
-```
-
-#### v1.0.0  Signature
-```python
-def search(
-    self,
-    query: str,
-    user_id: str = None,
-    agent_id: str = None,
-    run_id: str = None,
-    limit: int = 100,
-    filters: dict = None,       # ✅ ENHANCED: Advanced operators
-    rerank: bool = True         # ✅ NEW: Reranking support
-) -> dict  # Always returns dict with "results" key
-```
-
-#### Enhanced Filtering
-
-**v0.x Filters (basic):**
-```python
-# Simple key-value filtering only
-filters = {
-    "category": "food",
-    "user_id": "alice"
-}
-```
-
-**v1.0.0  Filters (enhanced):**
-```python
-# Advanced filtering with operators
-filters = {
-    "AND": [
-        {"category": "food"},
-        {"score": {"gte": 0.8}},
-        {
-            "OR": [
-                {"priority": "high"},
-                {"urgent": True}
-            ]
-        }
-    ]
-}
-
-# Comparison operators
-filters = {
-    "score": {"gt": 0.5},      # Greater than
-    "priority": {"gte": 5},     # Greater than or equal
-    "rating": {"lt": 3},        # Less than
-    "confidence": {"lte": 0.9}, # Less than or equal
-    "status": {"eq": "active"}, # Equal
-    "archived": {"ne": True},   # Not equal
-    "tags": {"in": ["work", "personal"]},     # In list
-    "category": {"nin": ["spam", "deleted"]}  # Not in list
-}
-```
-
-### get_all() Method
-
-#### v0.x Signature
-```python
-def get_all(
-    self,
-    user_id: str = None,
-    agent_id: str = None,
-    run_id: str = None,
-    filters: dict = None,
-    output_format: str = None,  # ❌ REMOVED
-    version: str = None         # ❌ REMOVED
-) -> Union[List[dict], dict]
-```
-
-#### v1.0.0  Signature
-```python
-def get_all(
-    self,
-    user_id: str = None,
-    agent_id: str = None,
-    run_id: str = None,
-    filters: dict = None        # ✅ ENHANCED: Advanced operators
-) -> dict  # Always returns dict with "results" key
-```
-
-### update() Method
-
-#### No Breaking Changes
-```python
-# Same signature in both versions
-def update(
-    self,
-    memory_id: str,
-    data: str
-) -> dict
-```
-
-### delete() Method
-
-#### No Breaking Changes
-```python
-# Same signature in both versions
-def delete(
-    self,
-    memory_id: str
-) -> dict
-```
-
-### delete_all() Method
-
-#### Breaking Change — Empty filter no longer silently deletes everything
-
-**Before:** calling `delete_all()` with no filters silently deleted **all memories in the project**.
-
-**After:**
-- No filters → raises a validation error (prevents accidental full-project wipe).
-- Concrete ID (e.g. `user_id="alice"`) → deletes memories for that entity (unchanged).
-- `"*"` for a filter → deletes all memories for that entity type across the project (new).
-- All four filters set to `"*"` → explicit full project wipe (new, requires opt-in on every parameter).
-
-This change replaces the silent full-project delete (triggered by an empty or missing filter) with a validation error, and introduces `"*"` wildcards as the intentional path for bulk deletion.
-
-```python
-# v0.x — no filter silently wiped all project memories
-m.delete_all()                      # DANGER: deleted everything
-m.delete_all(user_id="alice")       # deleted alice's memories
-
-# v1.x — no filter now raises an error; use "*" for intentional bulk deletes
-m.delete_all()                                                       # ERROR: at least one filter required
-m.delete_all(user_id="alice")                                        # unchanged
-m.delete_all(user_id="*")                                            # NEW — delete all users' memories
-m.delete_all(user_id="*", agent_id="*", app_id="*", run_id="*")     # NEW — full project wipe
-```
-
-## Platform Client (MemoryClient) Changes
-
-### async_mode Default Changed
-
-#### v0.x
-```python
-from mem0 import MemoryClient
-
-client = MemoryClient(api_key="your-key")
-
-# async_mode had to be explicitly set or had different default
-result = client.add("content", user_id="alice", async_mode=True)
-```
-
-#### v1.0.0
-```python
-from mem0 import MemoryClient
-
-client = MemoryClient(api_key="your-key")
-
-# async_mode defaults to True now (better performance)
-result = client.add("content", user_id="alice")  # Uses async_mode=True by default
-
-# Can still override if needed
-result = client.add("content", user_id="alice", async_mode=False)
-```
-
-## Configuration Changes
-
-### Memory Configuration
-
-#### v0.x Config Options
-```python
-config = {
-    "vector_store": {...},
-    "llm": {...},
-    "embedder": {...},
-    "graph_store": {...},
-    "version": "v1.0",              # ❌ v1.0 no longer supported
-    "history_db_path": "...",
-    "custom_instructions": "..."
-}
-```
-
-#### v1.0.0  Config Options
-```python
-config = {
-    "vector_store": {...},
-    "llm": {...},
-    "embedder": {...},
-    "graph_store": {...},
-    "reranker": {                   # ✅ NEW: Reranker support
-        "provider": "cohere",
-        "config": {...}
-    },
-    "version": "v1.1",              # ✅ v1.1+ only
-    "history_db_path": "...",
-    "custom_instructions": "...",
-    "custom_update_memory_prompt": "..."  # ✅ NEW: Custom update prompt
-}
-```
-
-### New Configuration Options
-
-#### Reranker Configuration
-```python
-# Cohere reranker
-"reranker": {
-    "provider": "cohere",
-    "config": {
-        "model": "rerank-english-v3.0",
-        "api_key": "your-api-key",
-        "top_k": 10
-    }
-}
-
-# Sentence Transformer reranker
-"reranker": {
-    "provider": "sentence_transformer",
-    "config": {
-        "model": "cross-encoder/ms-marco-MiniLM-L-6-v2",
-        "device": "cuda"
-    }
-}
-
-# Hugging Face reranker
-"reranker": {
-    "provider": "huggingface",
-    "config": {
-        "model": "BAAI/bge-reranker-base",
-        "device": "cuda"
-    }
-}
-
-# LLM-based reranker
-"reranker": {
-    "provider": "llm_reranker",
-    "config": {
-        "llm": {
-            "provider": "openai",
-            "config": {
-                "model": "gpt-4",
-                "api_key": "your-api-key"
-            }
-        }
-    }
-}
-```
-
-## Error Handling Changes
-
-### New Error Types
-
-#### v0.x Errors
-```python
-# Generic exceptions
-try:
-    result = m.add("content", user_id="alice", version="v1.0")
-except Exception as e:
-    print(f"Error: {e}")
-```
-
-#### v1.0.0  Errors
-```python
-# More specific error handling
-try:
-    result = m.add("content", user_id="alice")
-except ValueError as e:
-    if "v1.0 API format is no longer supported" in str(e):
-        # Handle version compatibility error
-        pass
-    elif "Invalid filter operator" in str(e):
-        # Handle filter syntax error
-        pass
-except TypeError as e:
-    # Handle parameter errors
-    pass
-except Exception as e:
-    # Handle unexpected errors
-    pass
-```
-
-### Validation Changes
-
-#### Stricter Parameter Validation
-
-**v0.x (Lenient):**
-```python
-# Unknown parameters might be ignored
-result = m.add("content", user_id="alice", unknown_param="value")
-```
-
-**v1.0.0  (Strict):**
-```python
-# Unknown parameters raise TypeError
-try:
-    result = m.add("content", user_id="alice", unknown_param="value")
-except TypeError as e:
-    print(f"Invalid parameter: {e}")
-```
-
-## Response Schema Changes
-
-### Memory Object Schema
-
-#### v0.x Schema
-```python
-{
-    "id": "mem_123",
-    "memory": "User loves pizza",
-    "user_id": "alice",
-    "metadata": {...},
-    "created_at": "2024-01-01T00:00:00Z",
-    "updated_at": "2024-01-01T00:00:00Z",
-    "score": 0.95  # In search results
-}
-```
-
-#### v1.0.0  Schema (Enhanced)
-```python
-{
-    "id": "mem_123",
-    "memory": "User loves pizza",
-    "user_id": "alice",
-    "agent_id": "assistant",     # ✅ More context
-    "run_id": "session_001",     # ✅ More context
-    "metadata": {...},
-    "categories": ["food"],      # ✅ NEW: Auto-categorization
-    "immutable": false,          # ✅ NEW: Immutability flag
-    "created_at": "2024-01-01T00:00:00Z",
-    "updated_at": "2024-01-01T00:00:00Z",
-    "score": 0.95,              # In search results
-    "rerank_score": 0.98        # ✅ NEW: If reranking used
-}
-```
-
-## Migration Code Examples
-
-### Simple Migration
-
-#### Before (v0.x)
-```python
-from mem0 import Memory
-
-m = Memory()
-
-# Add with deprecated parameters
-result = m.add(
-    "I love pizza",
-    user_id="alice",
-    output_format="v1.1",
-    version="v1.0"
-)
-
-# Handle variable response format
-if isinstance(result, list):
-    memories = result
-else:
-    memories = result.get("results", [])
-
-for memory in memories:
-    print(memory["memory"])
-```
-
-#### After (v1.0.0 )
-```python
-from mem0 import Memory
-
-m = Memory()
-
-# Add without deprecated parameters
-result = m.add(
-    "I love pizza",
-    user_id="alice"
-)
-
-# Always dict format with "results" key
-for memory in result["results"]:
-    print(memory["memory"])
-```
-
-### Advanced Migration
-
-#### Before (v0.x)
-```python
-# Basic filtering
-results = m.search(
-    "food preferences",
-    user_id="alice",
-    filters={"category": "food"},
-    output_format="v1.1"
-)
-```
-
-#### After (v1.0.0 )
-```python
-# Enhanced filtering with reranking
-results = m.search(
-    "food preferences",
-    user_id="alice",
-    filters={
-        "AND": [
-            {"category": "food"},
-            {"score": {"gte": 0.8}}
-        ]
-    },
-    rerank=True
-)
-```
-
-## Summary
-
-| Component | v0.x | v1.0.0  | Status |
-|-----------|------|-----------|---------|
-| `add()` method | Variable response | Standardized response | ⚠️ Breaking |
-| `search()` method | Basic filtering | Enhanced filtering + reranking | ⚠️ Breaking |
-| `get_all()` method | Variable response | Standardized response | ⚠️ Breaking |
-| Response format | Variable | Always `{"results": [...]}` | ⚠️ Breaking |
-| Reranking | ❌ Not available | ✅ Full support | ✅ New feature |
-| Advanced filtering | ❌ Basic only | ✅ Full operators | ✅ Enhancement |
-| Error handling | Generic | Specific error types | ✅ Improvement |
-
-<Info>
-Use this reference to systematically update your codebase. Test each change thoroughly before deploying to production.
-</Info>

docs/migration/oss-to-platform.mdx

@@ -120,13 +120,14 @@ client = MemoryClient(api_key="m0-...")
 
 | Method | Open Source | Platform |
 | ------ | ----------- | -------- |
-| `search()` | `m.search(query, user_id="alex")` | `client.search(query, filters={"user_id": "alex"})` |
-| `get_all()` | `m.get_all(user_id="alex")` | `client.get_all(filters={"user_id": "alex"})` |
+| `search()` | `m.search(query, filters={"user_id": "alex"})` | `client.search(query, filters={"user_id": "alex"})` |
+| `get_all()` | `m.get_all(filters={"user_id": "alex"})` | `client.get_all(filters={"user_id": "alex"})` |
 | `add()` | `m.add(memory, user_id="alex")` | `client.add(memory, user_id="alex")` |
+| `update()` | `m.update(memory_id, data="Updated content")` | `client.update(memory_id, text="Updated content")` |
 | `delete()` | `m.delete(memory_id)` | `client.delete(memory_id)` |
 | `delete_all()` | `m.delete_all(user_id="alex")` | `client.delete_all(user_id="alex")` |
 
-Note: `add()` and `delete()` methods remain unchanged. The `update()` method is not available in Platform - use delete + add pattern instead.
+Note: `add()` and `delete()` methods remain unchanged. The `update()` method is available in Platform via `client.update(memory_id, text="Updated content")`.
 
 <AccordionGroup>
   <Accordion title="Search Memories">
@@ -158,18 +159,15 @@ Note: `add()` and `delete()` methods remain unchanged. The `update()` method is
     <CodeGroup>
     ```python Open Source (Old)
     # Get all memories for a user
-    memories = m.get_all(user_id="alex", top_k=10)
-
-    # Get memories with pagination
-    memories = m.get_all(user_id="alex", top_k=5, offset=10)
+    memories = m.get_all(filters={"user_id": "alex"}, top_k=10)
     ```
 
     ```python Platform (New)
     # Get all memories for a user
     memories = client.get_all(filters={"user_id": "alex"}, top_k=10)
 
-    # Get memories with pagination
-    memories = client.get_all(filters={"user_id": "alex"}, top_k=5, offset=10)
+    # Get memories with pagination (Platform supports page/page_size)
+    memories = client.get_all(filters={"user_id": "alex"}, page=2, page_size=10)
     ```
     </CodeGroup>
   </Accordion>
@@ -218,16 +216,18 @@ Note: `add()` and `delete()` methods remain unchanged. The `update()` method is
     <CodeGroup>
     ```python Open Source (Old)
     # Update memory content
-    m.update(memory_id="mem_123", new_memory="Updated content")
+    m.update(memory_id="mem_123", data="Updated content")
     ```
 
     ```python Platform (New)
-    # Update memory (not available in Platform)
-    # Use delete + add pattern instead
-    client.delete(memory_id="mem_123")
-    client.add("Updated content", user_id="alex")
+    # Update memory content
+    client.update(memory_id="mem_123", text="Updated content")
     ```
     </CodeGroup>
+
+    <Note>
+      The parameter name differs between SDKs: OSS `Memory.update()` takes `data=`, while the Platform `MemoryClient.update()` (Python and JS/TS) takes `text=`. When migrating, rename this keyword argument.
+    </Note>
   </Accordion>
 </AccordionGroup>
 
@@ -392,7 +392,7 @@ The Platform introduces powerful capabilities not available in OSS:
 | **Add Method** | `m.add(memory, user_id="x")` | `client.add(memory, user_id="x")` | No change |
 | **Delete Method** | `m.delete(memory_id)` | `client.delete(memory_id)` | No change |
 | **Delete All** | `m.delete_all(user_id="x")` | `client.delete_all(user_id="x")` | No change |
-| **Update Method** | `m.update(memory_id, new_memory)` | Use delete + add pattern | Replace with delete then add |
+| **Update Method** | `m.update(memory_id, data="Updated content")` | `client.update(memory_id, text="Updated content")` | Rename `data=` kwarg to `text=` |
 | **Config** | Local vector store + LLM config | Managed cloud infrastructure | Remove local config setup |
 
 ## Rollback plan

docs/migration/oss-v2-to-v3.mdx

@@ -62,7 +62,7 @@ These changes produce a **+20 point improvement on LoCoMo** (71.4 → 91.6) and
 |---|---|---|---|
 | Constructor | `MemoryClient(api_key, org_id, project_id)` | `MemoryClient(api_key)` | Remove `org_id`, `project_id` from constructor |
 | Method options | `client.add(messages, **kwargs)` | `client.add(messages, options=AddMemoryOptions(...))` | Use typed option classes (or `**kwargs` still works) |
-| Removed params | `api_version`, `output_format`, `async_mode`, `filter_memories`, `expiration_date`, `keyword_search`, `force_add_only`, `batch_size`, `immutable`, `includes`, `excludes`, `enable_graph`, `org_name`, `project_name` | — | Remove from all calls |
+| Removed params | `api_version`, `output_format`, `async_mode`, `filter_memories`, `keyword_search`, `force_add_only`, `batch_size`, `immutable`, `includes`, `excludes`, `enable_graph`, `org_name`, `project_name` | — | Remove from all calls |
 
 ### TypeScript Client SDK
 
@@ -70,7 +70,7 @@ These changes produce a **+20 point improvement on LoCoMo** (71.4 → 91.6) and
 |---|---|---|---|
 | Constructor | `new MemoryClient({ apiKey, organizationId, projectId })` | `new MemoryClient({ apiKey })` | Remove `organizationId`, `projectId`, `organizationName`, `projectName` |
 | All params | snake_case: `user_id`, `agent_id`, `top_k` | camelCase: `userId`, `agentId`, `topK` | Rename all params to camelCase |
-| Removed params | `api_version`, `output_format`, `async_mode`, `enable_graph`, `org_id`, `project_id`, `org_name`, `project_name`, `filter_memories`, `batch_size`, `force_add_only`, `immutable`, `expiration_date`, `includes`, `excludes`, `keyword_search` | — | Remove from all calls |
+| Removed params | `api_version`, `output_format`, `async_mode`, `enable_graph`, `org_id`, `project_id`, `org_name`, `project_name`, `filter_memories`, `batch_size`, `force_add_only`, `immutable`, `includes`, `excludes`, `keyword_search` | — | Remove from all calls |
 | Output format enum | `OutputFormat.V1`, `OutputFormat.V1_1` | Removed | v1.1 is now always used |
 | API version enum | `API_VERSION.V1`, `API_VERSION.V2` | Removed | Handled internally |
 
@@ -328,27 +328,27 @@ The new algorithm automatically creates a parallel entity store collection named
 Make sure your vector store user/credentials have permission to create new collections. If you're using a managed vector database with restricted permissions, pre-create the `{collection_name}_entities` collection with the same embedding dimensions as your main collection.
 </Warning>
 
-## Graph Memory → Entity Linking
+## Graph Memory: Now Built-In
 
-Graph store support has been removed from the open-source SDK. It is replaced by **built-in entity linking**, which runs natively with no external dependencies.
+External graph **store** support has been removed from the open-source SDK and replaced by **built-in graph memory** (entity linking), which runs natively with no external dependencies.
 
 **What was removed:**
 - `enable_graph` / `enableGraph` config flag
 - `graph_store` / `graphStore` configuration block (Neo4j, Memgraph, Kuzu, Apache AGE, Neptune)
-- All graph memory code paths (~4000 lines)
+- All external graph store code paths (~4000 lines)
 
 **What replaces it:**
 
-Entity linking extracts entities (proper nouns, quoted text, compound noun phrases) from every memory during the add pipeline and stores them in a parallel collection (`{collection}_entities`) inside your existing vector store. At search time, entities from the query are matched against this collection and used to boost relevant memories. The boost is folded into the combined `score` on each result.
+Mem0 now builds the graph itself. It extracts entities (proper nouns, quoted text, compound noun phrases) from every memory during the add pipeline and stores them in a parallel collection (`{collection}_entities`) inside your existing vector store. Memories that share an entity are linked, and at search time entities from the query are matched against this collection to boost connected memories. The boost is folded into the combined `score` on each result.
 
 **Migration:**
 - Remove `enable_graph` / `enableGraph` from your config
 - Remove the `graph_store` / `graphStore` block — it is no longer read
-- Uninstall graph drivers (neo4j, memgraph, etc.) if you were using them only for Mem0
-- No data migration is required. Entity linking activates automatically on the next `add()` call.
+- Uninstall external graph drivers (neo4j, memgraph, etc.) if you were using them only for Mem0
+- No data migration is required. Built-in graph memory activates automatically on the next `add()` call.
 
 <Warning>
-Graph relationships exposed via the old `relations` field on search results are no longer populated. Entity relationships are consumed indirectly through retrieval ranking, not exposed as a queryable graph structure. If your application depended on traversing graph relationships directly, you will need to redesign that part against the new API.
+The old `relations` field on search results (populated by the external graph store) is no longer returned. Entity connections are now applied through retrieval ranking rather than exposed as a separate, directly traversable structure. If your application read or traversed the `relations` array, you will need to redesign that part against the new API.
 </Warning>
 
 ## How the New Algorithm Works
@@ -423,7 +423,7 @@ These parameters have been removed across all SDKs. Remove them from your code:
 
 **All methods:** `api_version`, `output_format`, `async_mode`, `org_name`, `project_name`, `org_id`, `project_id`
 
-**add():** `enable_graph`, `immutable`, `expiration_date`, `filter_memories`, `batch_size`, `force_add_only`, `includes`, `excludes`, `keyword_search`
+**add():** `enable_graph`, `immutable`, `filter_memories`, `batch_size`, `force_add_only`, `includes`, `excludes`, `keyword_search`
 
 **search():** `enable_graph`
 
@@ -437,7 +437,7 @@ These parameters have been removed across all SDKs. Remove them from your code:
 
 **All methods:** `OutputFormat` enum, `API_VERSION` enum
 
-**add():** `enable_graph` / `enableGraph`, `async_mode` / `asyncMode`, `output_format` / `outputFormat`, `immutable`, `expiration_date` / `expirationDate`, `filter_memories` / `filterMemories`, `batch_size` / `batchSize`, `force_add_only` / `forceAddOnly`, `includes`, `excludes`, `keyword_search` / `keywordSearch`
+**add():** `enable_graph` / `enableGraph`, `async_mode` / `asyncMode`, `output_format` / `outputFormat`, `immutable`, `filter_memories` / `filterMemories`, `batch_size` / `batchSize`, `force_add_only` / `forceAddOnly`, `includes`, `excludes`, `keyword_search` / `keywordSearch`
 
 **search():** `enable_graph` / `enableGraph`
 

docs/migration/platform-v2-to-v3.mdx

@@ -1,6 +1,6 @@
 ---
 title: "Platform: Migrating to the New Memory Algorithm"
-description: "Guide for Mem0 Platform users to adopt the new memory algorithm with single-pass extraction, entity linking, and multi-signal retrieval."
+description: "Guide for Mem0 Platform users to adopt the new memory algorithm with single-pass extraction, built-in graph memory, and multi-signal retrieval."
 icon: "arrow-right"
 iconType: "solid"
 ---
@@ -18,8 +18,7 @@ The new Mem0 memory algorithm is a ground-up redesign of how memories are extrac
 | **Extraction** | Two LLM passes (extract + merge) | Single-pass ADD-only (one LLM call) |
 | **Memory mutations** | ADD, UPDATE, DELETE | ADD only — nothing is overwritten or deleted |
 | **Agent-generated facts** | Often ignored | First-class, stored with equal weight |
-| **Entity linking** | Not available | Entities extracted and linked across memories |
-| **Graph memory** | Separate graph store + dashboard visualization | Replaced by built-in entity linking, no graph visuals on platform dashboard |
+| **Graph memory** | External graph store (Neo4j, etc.) + manual setup | Built-in and automatic; entities extracted and linked across memories natively, no external store |
 | **Retrieval** | Semantic (vector) only | Hybrid retrieval combining multiple signals |
 
 ## What This Means for Your Application
@@ -216,7 +215,7 @@ client.add(messages, user_id="alice")
 # async_mode and output_format removed (async by default, v1.1 always)
 ```
 
-**Removed parameters:** `org_id`, `project_id`, `api_version`, `output_format`, `async_mode`, `enable_graph`, `immutable`, `expiration_date`, `filter_memories`, `batch_size`, `force_add_only`, `includes`, `excludes`, `keyword_search`, `org_name`, `project_name`
+**Removed parameters:** `org_id`, `project_id`, `api_version`, `output_format`, `async_mode`, `enable_graph`, `immutable`, `filter_memories`, `batch_size`, `force_add_only`, `includes`, `excludes`, `keyword_search`, `org_name`, `project_name`
 
 ### TypeScript Client SDK
 
@@ -243,25 +242,24 @@ await client.search("query", {
 });
 ```
 
-**Removed:** `OutputFormat` enum, `API_VERSION` enum, `organizationId`, `projectId`, `organizationName`, `projectName`, `enableGraph`, `asyncMode`, `outputFormat`, `immutable`, `expirationDate`, `filterMemories`, `batchSize`, `forceAddOnly`, `includes`, `excludes`, `keywordSearch`
+**Removed:** `OutputFormat` enum, `API_VERSION` enum, `organizationId`, `projectId`, `organizationName`, `projectName`, `enableGraph`, `asyncMode`, `outputFormat`, `immutable`, `filterMemories`, `batchSize`, `forceAddOnly`, `includes`, `excludes`, `keywordSearch`
 
 <Info>
 For the full list of parameter changes across all SDKs, see the [OSS migration guide](/migration/oss-v2-to-v3#removed-parameters-reference).
 </Info>
 
-## Graph Memory → Entity Linking
+## Graph Memory Is Now Built-In
 
-Graph memory has been replaced by **built-in entity linking**. The changes:
+Graph memory no longer requires an external graph database. It is now **native to the platform** and automatic. The changes:
 
-- **Graph visualizations removed from the platform dashboard.** The graph view in your project dashboard is no longer available.
-- **`enable_graph` project setting removed.** The toggle is gone from the dashboard; the API parameter is ignored.
-- **No external graph store to configure.** Previously graph memory required a separate Neo4j (or similar) deployment. Entity linking runs natively inside the platform — nothing to provision, no connection strings to manage.
-- **Entity linking is the native replacement.** Entities (proper nouns, quoted text, compound noun phrases) are automatically extracted from every memory and linked across memories belonging to the same user. At search time, entities from the query are matched against this index and used to boost ranking. The boost is folded into the combined `score` returned on each result.
+- **No external graph store to configure.** Previously, graph memory required a separate Neo4j (or similar) deployment. Mem0 now builds the graph itself from your memories, so there is nothing to provision and no connection strings to manage.
+- **Always on, no flag.** The `enable_graph` project setting is no longer needed; graph memory activates automatically. (The API parameter is now ignored if sent.)
+- **Connections power retrieval directly.** Entities (proper nouns, quoted text, compound noun phrases) are automatically extracted from every memory and linked across memories belonging to the same user. At search time, entities from the query are matched against the graph and used to boost ranking. The boost is folded into the combined `score` returned on each result.
 
-**No migration work is required.** Entity linking activates automatically for all projects on the new algorithm. Existing memories are not re-processed, but any new memories you add will be indexed for entity-based retrieval going forward.
+**No migration work is required.** Graph memory activates automatically for all projects on the new algorithm. Existing memories are not re-processed, but any new memories you add are added to the graph going forward. See [Graph Memory](/platform/features/graph-memory) for how the built-in graph works.
 
 <Note>
-If your application previously read graph relations from the API response (`relations` field on search results), note that this field is no longer populated. Entity relationships are now consumed indirectly through retrieval ranking, not exposed as a separate graph structure.
+If your application previously read graph relations from the API response (`relations` field on search results), note that this field is no longer populated. Entity connections are now applied through retrieval ranking rather than returned as a separate `relations` array.
 </Note>
 
 ## Migration Checklist

docs/open-source/configuration.mdx

@@ -130,7 +130,7 @@ memory = Memory.from_config_file("config.yaml")
 </Tabs>
 
 <Info icon="check">
-  Run `memory.add(["Remember my favorite cafe in Tokyo."], user_id="alex")` and then `memory.search("favorite cafe", filters={"user_id": "alex"})`. You should see the Qdrant collection populate and the reranker mark the memory as a top hit.
+  Run `memory.add("Remember my favorite cafe in Tokyo.", user_id="alex")` and then `memory.search("favorite cafe", filters={"user_id": "alex"})`. You should see the Qdrant collection populate and the reranker mark the memory as a top hit.
 </Info>
 
 ## Tune component settings

docs/open-source/features/async-memory.mdx

@@ -18,7 +18,7 @@ icon: "bolt"
 </Warning>
 
 <Note>
-  Working in TypeScript? The Node SDK still uses synchronous calls—use `Memory` there and rely on Python’s `AsyncMemory` when you need awaited operations.
+  Working in TypeScript? The OSS `Memory` class in the Node SDK (`mem0ai/oss`) is also fully async — every method returns a `Promise` and must be `await`ed. Python’s `AsyncMemory` serves the same purpose within Python async frameworks like FastAPI. Both runtimes support awaited memory operations; choose the SDK that matches your language.
 </Note>
 
 ## Feature anatomy

docs/open-source/features/custom-instructions.mdx

@@ -165,8 +165,7 @@ await memory.add("Yesterday, I ordered a laptop, the order id is 12345", { userI
     {"memory": "Ordered a laptop", "event": "ADD"},
     {"memory": "Order ID: 12345", "event": "ADD"},
     {"memory": "Order placed yesterday", "event": "ADD"}
-  ],
-  "relations": []
+  ]
 }
 ```
 </CodeGroup>
@@ -188,8 +187,7 @@ await memory.add("I like going to hikes", { userId: "user123" });
 
 ```json Output
 {
-  "results": [],
-  "relations": []
+  "results": []
 }
 ```
 </CodeGroup>

docs/open-source/features/multimodal-support.mdx

@@ -41,6 +41,14 @@ Multimodal support lets Mem0 extract facts from images alongside regular text. A
 
 ## Configure it
 
+<Warning>
+  You must set `enable_vision: True` in your LLM config for image content to be processed. Without it, image turns are silently dropped and no vision memories are created. Example:
+  ```python
+  config = {"llm": {"provider": "openai", "config": {"enable_vision": True, "vision_details": "auto"}}}
+  client = Memory.from_config(config)
+  ```
+</Warning>
+
 ### Add image messages from URLs
 
 <CodeGroup>
@@ -66,7 +74,7 @@ client.add(messages, user_id="alice")
 ```
 
 ```ts TypeScript
-import { Memory } from "mem0ai";
+import { Memory } from "mem0ai/oss";
 
 const client = new Memory();
 
@@ -123,7 +131,7 @@ client.add(messages, user_id="alice")
 
 ```ts TypeScript
 import fs from "fs";
-import { Memory } from "mem0ai";
+import { Memory } from "mem0ai/oss";
 
 function encodeImage(imagePath: string) {
   const buffer = fs.readFileSync(imagePath);
@@ -226,7 +234,7 @@ client.add(messages, user_id="user123")
 <CodeGroup>
 ```python Python
 from mem0 import Memory
-from mem0.exceptions import InvalidImageError, FileSizeError
+from mem0.exceptions import ValidationError
 
 client = Memory()
 
@@ -242,16 +250,14 @@ try:
     client.add(messages, user_id="user123")
     print("Image processed successfully")
 
-except InvalidImageError:
-    print("Invalid image format or corrupted file")
-except FileSizeError:
-    print("Image file too large")
+except ValidationError as exc:
+    print(f"Image validation error: {exc}")
 except Exception as exc:
     print(f"Unexpected error: {exc}")
 ```
 
 ```ts TypeScript
-import { Memory } from "mem0ai";
+import { Memory } from "mem0ai/oss";
 
 const client = new Memory();
 

docs/open-source/features/reranker-search.mdx

@@ -124,7 +124,7 @@ config = {
         "provider": "llm_reranker",
         "config": {
             "provider": "openai",
-            "model": "gpt-4o-mini",
+            "model": "gpt-5-mini",
             "api_key": "your-openai-api-key",
             "top_k": 5
         }
@@ -150,7 +150,7 @@ config = {
     "llm": {
         "provider": "openai",
         "config": {
-            "model": "gpt-4",
+            "model": "gpt-5-mini",
             "api_key": "your-openai-api-key"
         }
     },

docs/openapi.json

@@ -1779,6 +1779,11 @@
 										"type": "object",
 										"description": "Entity and metadata filters. Must include at least one entity ID (`user_id`, `agent_id`, `app_id`, or `run_id`).",
 										"additionalProperties": true
+									},
+									"show_expired": {
+										"type": "boolean",
+										"default": false,
+										"description": "When true, include memories whose `expiration_date` has passed. Expired memories are hidden by default."
 									}
 								}
 							},
@@ -1977,6 +1982,12 @@
 										"additionalProperties": true,
 										"description": "User-supplied metadata to attach to each extracted memory."
 									},
+									"expiration_date": {
+										"type": "string",
+										"format": "date",
+										"nullable": true,
+										"description": "Optional expiration date in YYYY-MM-DD format. After this date, memories are hidden from search and get-all unless `show_expired` is true."
+									},
 									"custom_instructions": {
 										"type": "string",
 										"description": "Project-level instructions that guide extraction for this call."
@@ -2094,6 +2105,11 @@
 										"description": "Entity and metadata filters. Must include at least one entity ID (`user_id`, `agent_id`, `app_id`, or `run_id`). Supports `AND`, `OR`, `NOT`, and comparison operators (`in`, `gte`, `lte`, `gt`, `lt`, `contains`, `icontains`, `ne`).",
 										"additionalProperties": true
 									},
+									"show_expired": {
+										"type": "boolean",
+										"default": false,
+										"description": "When true, include memories whose `expiration_date` has passed. Expired memories are hidden by default."
+									},
 									"top_k": {
 										"type": "integer",
 										"minimum": 1,
@@ -2432,6 +2448,12 @@
 									"metadata": {
 										"type": "object",
 										"description": "Additional metadata associated with the memory"
+									},
+									"expiration_date": {
+										"type": "string",
+										"format": "date",
+										"nullable": true,
+										"description": "Expiration date in YYYY-MM-DD format, or null to clear the expiration date."
 									}
 								}
 							}
@@ -4861,8 +4883,7 @@
 										"items": {
 											"type": "object",
 											"required": [
-												"memory_id",
-												"text"
+												"memory_id"
 											],
 											"properties": {
 												"memory_id": {
@@ -4873,6 +4894,11 @@
 												"text": {
 													"type": "string",
 													"description": "The new text content for the memory"
+												},
+												"metadata": {
+													"type": "object",
+													"additionalProperties": true,
+													"description": "Updated metadata to associate with the memory."
 												}
 											}
 										},
@@ -4948,18 +4974,27 @@
 							"schema": {
 								"type": "object",
 								"properties": {
-									"memory_ids": {
+									"memories": {
 										"type": "array",
 										"items": {
-											"type": "string",
-											"format": "uuid"
+											"type": "object",
+											"properties": {
+												"memory_id": {
+													"type": "string",
+													"format": "uuid",
+													"description": "The unique identifier of the memory to delete."
+												}
+											},
+											"required": [
+												"memory_id"
+											]
 										},
 										"maxItems": 1000,
-										"description": "Array of memory IDs to delete."
+										"description": "Array of memory objects to delete."
 									}
 								},
 								"required": [
-									"memory_ids"
+									"memories"
 								]
 							}
 						}
@@ -6256,4 +6291,4 @@
 		}
 	},
 	"x-original-swagger-version": "2.0"
-}
+}

docs/platform/features/criteria-retrieval.mdx

@@ -117,7 +117,7 @@ results_without_criteria = client.search(
 ### Compare Results
 
 ### Search Results (with Criteria)
-```python
+```text
 [
     {"memory": "User feels refreshed and ready to take on anything on a beautiful sunny day", "score": 0.666, ...},
     {"memory": "User finally has time to draw something after a long time", "score": 0.616, ...},
@@ -128,7 +128,7 @@ results_without_criteria = client.search(
 ```
 
 ### Search Results (without Criteria)
-```python
+```text
 [
     {"memory": "User is happy today", "score": 0.607, ...},
     {"memory": "User feels refreshed and ready to take on anything on a beautiful sunny day", "score": 0.512, ...},

docs/platform/features/custom-categories.mdx

@@ -190,7 +190,7 @@ messages = [
 client.add(messages, user_id='alice')
 ```
 
-```python Memories with categories
+```text Memories with categories
 # Following categories will be created for the memories added
 Sometimes draws and sketches in free time (hobbies)
 Is quite athletic (sports)

docs/platform/features/entity-scoped-memory.mdx

@@ -5,6 +5,10 @@ description: Scope conversations by user, agent, app, and session so memories la
 
 Mem0's Platform API lets you separate memories for different users, agents, and apps. By tagging each write and query with the right identifiers, you can prevent data from mixing between them, maintain clear audit trails, and control data retention.
 
+<Note>
+**Entity IDs vs. graph entities.** This page covers the `user_id` / `agent_id` / `app_id` / `run_id` identifiers used to *scope* memories. These are different from the **graph entities** (the people, places, and concepts surfaced in [Graph Memory](/platform/features/graph-memory)).
+</Note>
+
 <Tip icon="layers">
 Want the long-form tutorial? The <Link href="/cookbooks/essentials/entity-partitioning-playbook">Partition Memories by Entity</Link> cookbook walks through multi-agent storage, debugging, and cleanup step by step.
 </Tip>

docs/platform/features/graph-memory.mdx

@@ -0,0 +1,93 @@
+---
+title: "Graph Memory"
+description: "Mem0 Platform builds a native graph linking people, places, and concepts across your memories, with no external graph database to provision."
+icon: "circle-nodes"
+iconType: "solid"
+---
+
+Mem0 Platform automatically organizes your memories into a **graph**: the **graph entities** mentioned across your memories (the people, places, organizations, and concepts they refer to) become nodes, and memories that share an entity are connected. This is how Mem0 reasons across separate facts, for example linking everything it knows about a person, a company, or a project, without you defining any schema.
+
+Graph Memory is **built in**. There is no Neo4j, Memgraph, or other graph store to deploy, no connection strings to manage, and nothing to enable. It runs natively inside the platform and is always on.
+
+<Info>
+  **Graph Memory matters when…**
+  - You ask entity-centric questions like "what do we know about Alice?" and expect facts pulled from many different conversations
+  - Your app needs multi-hop recall, connecting a fact in one memory to a related fact in another
+  - You previously used an external graph store and want the same cross-memory connections with zero infrastructure
+</Info>
+
+<Note>
+  **Graph entities vs. entity IDs.** The entities in your graph (people, places, and concepts extracted from memory text) are different from the *entity IDs* (`user_id`, `agent_id`, `app_id`, `run_id`) used to scope memories. Those are covered in [Entity-Scoped Memory](/platform/features/entity-scoped-memory).
+</Note>
+
+<Note>
+  Graph Memory is the native successor to Mem0's earlier graph store integration. Earlier versions connected an external graph database (Neo4j and others) and exposed a `relations` field. Mem0 now builds the graph itself from your memories. See [What changed from the external graph store](#what-changed-from-the-external-graph-store) below.
+</Note>
+
+## How it works
+
+Graph Memory is built and used across the two phases of the memory pipeline: **extraction** (when you add memories) and **retrieval** (when you search).
+
+### 1. Entities become nodes
+
+Every time you add a memory, Mem0 extracts the **entities** it contains: the proper nouns, names, and key phrases that identify a specific person, place, organization, product, or concept (for example *Alice*, *San Francisco*, *Acme Corp*, *the Q1 roadmap*). Each distinct entity is stored once and embedded, so entities that refer to the same thing can be matched even when they are phrased differently.
+
+### 2. Shared entities become connections
+
+When the same entity appears in more than one memory, those memories are **linked** through that entity. Over time this forms a graph: a web of entities, each connecting all the memories that mention it. The connections are derived directly from your data. There is no relationship schema to define and nothing to label by hand.
+
+### 3. The graph powers retrieval
+
+At search time, Mem0 extracts the entities from your query and matches them against the graph. Memories connected to those entities receive a ranking boost, which is combined with semantic (vector) and keyword (BM25) scores into the single `score` returned on each result.
+
+This is what lets Mem0 answer entity-centric and multi-hop questions: a query about *Alice* surfaces facts about Alice that live in completely different memories, because the graph connects them. The connecting-facts-across-memories behavior contributes to Mem0's gains on multi-hop and temporal benchmarks. See [Memory Evaluation](/core-concepts/memory-evaluation).
+
+<Info>
+Graph Memory affects **ranking**, not the response shape. Search results come back in the normal format with a combined `score`; there is no separate graph payload to parse.
+</Info>
+
+## What's in the graph
+
+| Element | What it is |
+| --- | --- |
+| **Graph entity** (node) | A distinct person, place, organization, product, or concept extracted from your memories (e.g. *Alice*, *Acme Corp*). Distinct from the user/agent/app/run *entity IDs* used to scope memories. |
+| **Memory node** | An individual memory (fact) stored for a user, agent, or session. |
+| **Connection** | A link between an entity and every memory that mentions it. Two entities are related when they co-occur in one or more memories. |
+
+Graph Memory captures **which entities your memories are about and how they connect through shared context**. It does not assign typed, labeled relationships between entities (it won't, for example, record a "manages" edge from one person to another); connections are inferred from co-occurrence rather than declared. This is what makes it schema-free and zero-configuration.
+
+## Availability
+
+Graph Memory is **automatic and included on all plans**. It activates on the new memory algorithm with no flag, no configuration, and no external dependencies. You don't need to do anything to benefit from it.
+
+```python
+from mem0 import MemoryClient
+
+client = MemoryClient(api_key="your-api-key")
+
+# Entities are extracted and linked into the graph automatically on add
+client.add(
+    messages=[
+        {"role": "user", "content": "I work at Acme Corp with Alice on the Q1 roadmap"}
+    ],
+    user_id="jordan",
+)
+
+# Entity matches from the query are used to connect and boost related memories
+results = client.search(
+    query="who does jordan work with?",
+    filters={"user_id": "jordan"},
+)
+```
+
+## What changed from the external graph store
+
+Earlier versions of Mem0 offered graph memory by connecting an **external graph database** (Neo4j, Memgraph, Kuzu, Apache AGE, or Neptune) through an `enable_graph` flag and a `graph_store` configuration block. That integration has been replaced by **native, built-in Graph Memory**:
+
+- **No external graph store.** The graph is built inside Mem0 from your memories. There is nothing to provision or connect.
+- **Always on, all plans.** The `enable_graph` flag is no longer needed; Graph Memory is automatic. (If you still send the parameter, it is ignored.)
+- **Connections power retrieval directly.** Entity connections are folded into the combined `score` on each result. The standalone `relations` field that the external graph store returned is no longer populated. If your application read that field, see the migration guide below.
+
+<Card title="Platform Migration Guide" icon="arrow-right" href="/migration/platform-v2-to-v3">
+  Full details on the move to the new algorithm, including the `relations` field change.
+</Card>

docs/platform/features/memory-export.mdx

@@ -108,10 +108,10 @@ print(response)
 
 ```javascript JavaScript
 // Basic Export request
-const filters = {"user_id": "alice"};
+const basicFilters = {"user_id": "alice"};
 const response = await client.createMemoryExport({
     schema: json_schema,
-    filters: filters
+    filters: basicFilters
 });
 
 // Export with custom instructions and additional filters
@@ -124,16 +124,16 @@ const export_instructions = `
 `;
 
 // For create operation, using only user_id filter as requested
-const filters = {
+const exportFilters = {
     "AND": [
         {"user_id": "alex"},
         {"created_at": {"gte": "2024-01-01"}}
     ]
-}
+};
 
 const responseWithInstructions = await client.createMemoryExport({
     schema: json_schema,
-    filters: filters,
+    filters: exportFilters,
     exportInstructions: export_instructions
 });
 

examples/mem0-demo/package.json

@@ -23,7 +23,7 @@
     "@types/js-cookie": "^3.0.6",
     "@types/react-syntax-highlighter": "^15.5.13",
     "@types/uuid": "^10.0.0",
-    "ai": "^4.1.46",
+    "ai": "^5.0.52",
     "class-variance-authority": "^0.7.1",
     "clsx": "^2.1.1",
     "js-cookie": "^3.0.6",

examples/multimodal-demo/package.json

@@ -18,7 +18,7 @@
     "@radix-ui/react-scroll-area": "^1.2.0",
     "@radix-ui/react-select": "^2.1.2",
     "@radix-ui/react-slot": "^1.1.0",
-    "ai": "4.1.42",
+    "ai": "^5.0.52",
     "buffer": "^6.0.3",
     "class-variance-authority": "^0.7.0",
     "clsx": "^2.1.1",

examples/vercel-ai-sdk-chat-app/package.json

@@ -18,7 +18,7 @@
       "@radix-ui/react-scroll-area": "^1.2.0",
       "@radix-ui/react-select": "^2.1.2",
       "@radix-ui/react-slot": "^1.1.0",
-      "ai": "4.1.42",
+      "ai": "^5.0.52",
       "buffer": "^6.0.3",
       "class-variance-authority": "^0.7.0",
       "clsx": "^2.1.1",

integrations/mem0-plugin/.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "mem0",
-  "version": "0.2.10",
+  "version": "0.2.11",
   "description": "Persistent memory for Claude Code. Remembers decisions, patterns, and preferences across sessions.",
   "author": {
     "name": "Mem0",

integrations/mem0-plugin/.codex-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "mem0",
-  "version": "0.2.10",
+  "version": "0.2.11",
   "description": "Persistent memory for Codex. Remembers decisions, patterns, and preferences across sessions.",
   "author": {
     "name": "Mem0",

integrations/mem0-plugin/.cursor-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "mem0",
-  "version": "0.2.10",
+  "version": "0.2.11",
   "description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search using the Mem0 Platform MCP server.",
   "author": {
     "name": "Mem0",

integrations/mem0-plugin/.opencode-plugin/CHANGELOG.md

@@ -2,6 +2,36 @@
 
 All notable changes to the `@mem0/opencode-plugin` will be documented in this file.
 
+## 0.2.0 — Native SDK tools, MCP-free, leaner skill set
+
+### Changed (breaking)
+
+- **Memory tools are now native OpenCode tools** registered via the `@opencode-ai/plugin` `tool()` helper and backed by the `mem0ai` SDK directly. The plugin no longer registers or depends on the remote MCP server (`mcp.mem0.ai`); the bundled `opencode.json` and the regex-based MCP call interception have been removed. Tools: `add_memory`, `search_memories`, `get_memories`, `get_memory`, `update_memory`, `delete_memory`, `delete_all_memories`, `delete_entities`, `list_entities`, plus a `get_event_status` helper for async-write status.
+- **Skills load via the `config` hook (`skills.paths`)** instead of being copied into the project's `.opencode/` directory on startup. The `installSkills()` filesystem copy and the `cli.ts` installer (`mem0-opencode` bin) have been removed — install with `opencode plugin @mem0/opencode-plugin`.
+- **Trimmed to 9 focused skills** (`context-loader`, `dream`, `forget`, `status`, `search`, `scope`, `pin`, `remember`, `tour`). Removed `import`, `export`, `memory-reviewer`, `mem0` (SDK reference), `list-projects`, `stats`, and `onboard`. The old stateful `switch-project` skill is superseded by the project/session/global scope model and the new `/mem0-scope` skill.
+
+### Added
+
+- **Expanded telemetry to the full shared `plugin.*` schema.** In addition to `plugin.session_start` and `plugin.tool_use`, the plugin now emits `plugin.user_prompt`, `plugin.bash_error`, `plugin.pre_compact`, and `plugin.session_stop`. `tool_use` now fires from inside each native tool. Every event also carries `project_hash` (anonymized `sha256(app_id)`) and `os_version`, matching the editor plugin's `telemetry.py`.
+- **Auto-dream — gated automatic memory consolidation** (ported from the pi-agent plugin). When the time (`minHours`, default 24), session-count (`minSessions`, default 5), and memory-count (`minMemories`, default 20) gates all pass, the plugin injects a consolidation protocol so the agent merges duplicates, drops stale/sensitive entries, and rewrites vague ones before answering. A filesystem lock (`~/.mem0/mem0-dream.lock`) prevents concurrent sessions from dreaming at once, and completion resets the gates. Tune via the `dream` block in `~/.mem0/settings.json`; disable with `MEM0_DREAM=false`. Emits `plugin.dream_triggered` / `plugin.dream_completed`.
+- **Memory `scope` — per-call parameter and a persistent default.** `search_memories`, `get_memories`, `add_memory`, and `delete_all_memories` accept an optional `scope`: `"project"` (this repo, default), `"session"` (this run, adds `run_id`), or `"global"` (across all the user's projects — `app_id: "*"` for reads, user-wide for writes). The new **`/mem0-scope` skill** views and changes the *default* scope (used when no scope is passed), persisted to `~/.mem0/settings.json` (`default_scope`) and read **fresh on each memory operation** so changes apply immediately — no restart. `add_memory` / `search_memories` / `get_memories` honor the default (an explicit `scope`, `filters`, or `agent_id` still wins; a `project` default preserves prior behavior, including `global_search`).
+
+### Changed
+
+- **`/mem0-status` now reports the active default scope and auto-dream readiness.** It reads `default_scope` from `~/.mem0/settings.json` (falling back to `project`) and shows the auto-dream gate progress (sessions / memories / time vs. thresholds) so it's clear *why* a consolidation hasn't run yet.
+
+### Fixed
+
+- **Skills load in place via `skills.paths` — no copying.** The `config` hook adds the plugin's own `opencode-skills/` directory to OpenCode's `skills.paths`, so OpenCode discovers the skills directly from the linked/installed plugin package (recursive `**/SKILL.md` scan). The `installSkills()` step that copied skills into `~/.config/opencode/skills/` (and the legacy `~/.opencode/skills/`) and its version-marker gating are removed — the plugin no longer writes into those directories or creates `~/.opencode`. The `config` hook still registers the `/mem0-*` slash commands via `config.command`: OpenCode's TUI slash menu is built from `config.command`, and skills on `skills.paths` are available to the agent's skill tool but do not appear as slash commands on their own. Skill dir names are `mem0-<skill>` (matching `^[a-z0-9]+(-[a-z0-9]+)*$`); commands are `/mem0-<skill>`.
+- **Robust project-id (`app_id`) detection.** Parsed from the git remote's `owner/repo` — handling https, scp-style ssh, and **custom ssh host aliases** like `git@github.com-work:owner/repo.git` — falling back to the git repo's **root directory name** (not the cwd, which may be a sub-directory or your home dir), then the cwd. Fixes the project showing as your username/home when OpenCode was launched outside the repo root.
+- **Auto-dream visibility + robustness.** When auto-dream doesn't fire, the plugin logs the blocking gate (e.g. `auto-dream waiting — memories: 3 < 20`), and `/mem0-status` surfaces the same gate progress. The session-start memory count is parsed defensively (handles both paginated `{count}` and bare-array SDK responses) so the memory gate evaluates correctly.
+- **Error-pattern lookup** in `tool.execute.after` no longer issues two identical `mem0.search()` calls; it now performs a single `topK: 6` search.
+- Corrected the documented system-prompt hook name from `experimental.chat.system.transform` to the actual `experimental.chat.messages.transform`.
+
+### Safety
+
+- **`delete_all_memories` deliberately ignores the default scope.** Deleting user-wide always requires an explicit `scope="global"`, so raising the default to `global` can never turn a routine cleanup into a cross-project wipe.
+
 ## 0.1.3 — File-context injection, session summaries & activity timeline, anonymous telemetry
 
 ### Added

integrations/mem0-plugin/.opencode-plugin/README.md

@@ -4,24 +4,18 @@ Persistent memory for [OpenCode](https://opencode.ai). Your agent remembers deci
 
 ## Install
 
-```bash
-bunx @mem0/opencode-plugin@latest install
-```
-
-Or using OpenCode's built-in CLI:
-
 ```bash
 opencode plugin @mem0/opencode-plugin
 ```
 
+This adds the plugin to your `~/.config/opencode/opencode.json`. The plugin registers its memory tools and skills itself — there is no MCP server to configure.
+
 **Or let your agent do it** — paste this into OpenCode:
 
 ```
 Install @mem0/opencode-plugin by following https://raw.githubusercontent.com/mem0ai/mem0/main/integrations/mem0-plugin/.opencode-plugin/README.md
 ```
 
-All commands auto-add the plugin and MCP server to your `~/.config/opencode/opencode.json`. No manual config needed.
-
 Get your API key (free): [app.mem0.ai/dashboard/api-keys](https://app.mem0.ai/dashboard/api-keys)
 
 ```bash
@@ -34,24 +28,25 @@ Restart OpenCode.
 
 | Component | Description |
 |-----------|-------------|
-| **MCP Server** | 9 memory tools — add, search, get, update, delete memories |
-| **Lifecycle Hooks** | Auto-search on session start and every prompt, metadata enforcement, error memory lookup, compaction context |
-| **16 Slash Commands** | `/mem0:remember`, `/mem0:tour`, `/mem0:stats`, `/mem0:health`, `/mem0:dream`, and more |
+| **9 Native Memory Tools** | `add_memory`, `search_memories`, `get_memories`, `update_memory`, `delete_memory`, and more — registered as OpenCode tools, backed by the `mem0ai` SDK (no MCP server required) |
+| **Lifecycle Hooks** | Auto-search on session start and every prompt, error memory lookup, compaction context, secret redaction |
+| **9 Skills** | `/mem0-remember`, `/mem0-tour`, `/mem0-search`, `/mem0-status`, `/mem0-scope`, `/mem0-dream`, `/mem0-forget`, `/mem0-pin`, `/mem0-context-loader` — discovered in place from the plugin via OpenCode's `skills.paths` |
 
 ## Hooks
 
-Pure TypeScript — no Python, no shell scripts. Uses the [mem0ai](https://www.npmjs.com/package/mem0ai) SDK directly.
+Pure TypeScript — no Python, no shell scripts. Memory operations are native OpenCode tools backed by the [mem0ai](https://www.npmjs.com/package/mem0ai) SDK directly.
 
 | Hook | Event | What it does |
 |------|-------|-------------|
+| **Config** | `config` | Registers the `/mem0-*` slash commands (via `config.command`) and adds the plugin's own `opencode-skills/` dir to OpenCode's `skills.paths` for in-place skill discovery — no copying into `~/.config/opencode/skills` |
 | **Chat message** | `chat.message` | Loads prior memories on session start, searches relevant memories before each prompt, auto-captures learnings periodically |
-| **Pre-tool** | `tool.execute.before` | Blocks MEMORY.md writes, enforces `user_id`/`app_id` on mem0 tools |
-| **Post-tool** | `tool.execute.after` | Tracks stats, scans bash errors for related memories |
-| **System transform** | `experimental.chat.system.transform` | Injects memory context (session memories, search results, error lookups) into system prompt |
+| **Pre-tool** | `tool.execute.before` | Blocks MEMORY.md writes, steering them to the `add_memory` tool |
+| **Post-tool** | `tool.execute.after` | Scans bash errors and pre-fetches related memories |
+| **Messages transform** | `experimental.chat.messages.transform` | Injects memory context (session memories, search results, error lookups) into the prompt |
 | **Compaction** | `experimental.session.compacting` | Stores session state memory, then injects prior memories into compaction context so nothing is lost |
 | **Shell env** | `shell.env` | Exports `MEM0_USER_ID`, `MEM0_APP_ID`, `MEM0_SESSION_ID`, and `MEM0_BRANCH` to shell |
 
-## MCP Tools
+## Memory Tools
 
 | Tool | Description |
 |------|-------------|
@@ -65,6 +60,28 @@ Pure TypeScript — no Python, no shell scripts. Uses the [mem0ai](https://www.n
 | `delete_entities` | Delete an entity and its memories |
 | `list_entities` | List users/agents/apps stored in Mem0 |
 
+## Memory scope
+
+Every memory tool accepts an optional `scope`, and you can set the **default**
+scope (used when none is passed) with the `/mem0-scope` skill:
+
+| Scope | Reads | Writes |
+|-------|-------|--------|
+| `project` (default) | this repo (`user_id` + `app_id`) | this repo |
+| `session` | this run (adds `run_id`) | this run |
+| `global` | all your projects (`app_id="*"`) | user-wide (drops `app_id`) |
+
+```
+/mem0-scope            # show the current default scope
+/mem0-scope global     # save & search across all your projects by default
+/mem0-scope project    # back to repo-only (default)
+```
+
+The default persists in `~/.mem0/settings.json` (`default_scope`) and is read
+fresh on each memory operation, so a change applies immediately — no restart.
+`delete_all_memories` always requires an explicit `scope="global"` to delete
+user-wide, so changing the default can't trigger a cross-project wipe.
+
 ## Verify
 
 Start OpenCode and ask: *"Search my memories for recent decisions"*

integrations/mem0-plugin/.opencode-plugin/bun.lock

@@ -6,7 +6,7 @@
       "name": "@mem0/opencode-plugin",
       "dependencies": {
         "@opencode-ai/plugin": "^1.0.162",
-        "mem0ai": "^3.0.7",
+        "mem0ai": "^3.0.8",
       },
       "devDependencies": {
         "bun-types": ">=1.3.14",
@@ -462,7 +462,7 @@
 
     "md5": ["md5@2.3.0", "", { "dependencies": { "charenc": "0.0.2", "crypt": "0.0.2", "is-buffer": "~1.1.6" } }, "sha512-T1GITYmFaKuO91vxyoQMFETst+O71VUPEU3ze5GNzDm0OWdP8v1ziTaAEPUr/3kLsY3Sftgz242A1SetQiDL7g=="],
 
-    "mem0ai": ["mem0ai@3.0.7", "", { "dependencies": { "axios": "^1.16.0", "openai": "^4.93.0", "uuid": "9.0.1", "zod": "^3.24.1" }, "peerDependencies": { "@anthropic-ai/sdk": "^0.40.1", "@azure/identity": "^4.0.0", "@azure/search-documents": "^12.0.0", "@cloudflare/workers-types": "^4.20250504.0", "@google/genai": "^1.40.0", "@langchain/core": "^1.1.47", "@mistralai/mistralai": "^1.5.2", "@qdrant/js-client-rest": "^1.18.0", "@supabase/supabase-js": "^2.49.1", "@types/jest": "29.5.14", "@types/pg": "8.11.0", "better-sqlite3": "^12.6.2", "cloudflare": "^4.2.0", "compromise": "^14.0.0", "groq-sdk": "0.3.0", "natural": "^8.0.1", "ollama": "^0.5.14", "pg": "8.11.3", "redis": "^4.6.13" } }, "sha512-CUHzX7DyeKTHcI3aDsSqY9LXTD7GcFxf988796TuOa4yJgGuF2Xd2NROcBhVFRo3r9y8fVmbo3c5TF9jv1KlKw=="],
+    "mem0ai": ["mem0ai@3.0.8", "", { "dependencies": { "axios": "^1.16.0", "openai": "^4.93.0", "uuid": "^11.1.1", "zod": "^3.24.1" }, "peerDependencies": { "@anthropic-ai/sdk": "^0.40.1", "@azure/identity": "^4.0.0", "@azure/search-documents": "^12.0.0", "@cloudflare/workers-types": "^4.20250504.0", "@google/genai": "^1.40.0", "@langchain/core": "^1.1.47", "@mistralai/mistralai": "^1.5.2", "@qdrant/js-client-rest": "^1.18.0", "@supabase/supabase-js": "^2.49.1", "@types/jest": "29.5.14", "@types/pg": "8.11.0", "better-sqlite3": "^12.6.2", "cloudflare": "^4.2.0", "compromise": "^14.0.0", "groq-sdk": "0.3.0", "natural": "^8.0.1", "ollama": "^0.5.14", "pg": "8.11.3", "redis": "^4.6.13" } }, "sha512-6lvHGOYc/Z2r0JEulS559MVPOOiOtfAqG02VESDY7b0WAZwsmgLWAjQkbmWnD9fbXQQ3QvSpSaVx1q6Ex01eLQ=="],
 
     "memjs": ["memjs@1.3.2", "", {}, "sha512-qUEg2g8vxPe+zPn09KidjIStHPtoBO8Cttm8bgJFWWabbsjQ9Av9Ky+6UcvKx6ue0LLb/LEhtcyQpRyKfzeXcg=="],
 
@@ -652,7 +652,7 @@
 
     "util-deprecate": ["util-deprecate@1.0.2", "", {}, "sha512-EPD5q1uXyFxJpCrLnCc1nHnq3gOa6DZBocAIiI2TaSCA7VCJ1UJDMagCzIkXNsUYfD1daK//LTEQ8xiIbrHtcw=="],
 
-    "uuid": ["uuid@9.0.1", "", { "bin": { "uuid": "dist/bin/uuid" } }, "sha512-b+1eJOlsR9K8HJpow9Ok3fiWOWSIcIzXodvv0rQjVoOVNpWMpxf1wZNpt4y9h10odCNrqnYp1OBzRktckBe3sA=="],
+    "uuid": ["uuid@11.1.1", "", { "bin": { "uuid": "dist/esm/bin/uuid" } }, "sha512-vIYxrBCC/N/K+Js3qSN88go7kIfNPssr/hHCesKCQNAjmgvYS2oqr69kIufEG+O4+PfezOH4EbIeHCfFov8ZgQ=="],
 
     "web-streams-polyfill": ["web-streams-polyfill@3.3.3", "", {}, "sha512-d2JWLCivmZYTSIoge9MsgFCZrt571BikcWGYkjC1khllbTeDlGqZ2D8vD8E/lJa8WGWbb7Plm8/XJYV7IJHZZw=="],
 

integrations/mem0-plugin/.opencode-plugin/cli.ts

@@ -1,254 +0,0 @@
-#!/usr/bin/env bun
-import {
-  readFileSync,
-  writeFileSync,
-  existsSync,
-  mkdirSync,
-  copyFileSync,
-  readdirSync,
-  rmSync,
-  statSync,
-} from "fs";
-import { join, dirname } from "path";
-import { homedir } from "os";
-
-const PLUGIN_NAME = "@mem0/opencode-plugin";
-const MCP_CONFIG = {
-  mem0: {
-    type: "remote",
-    url: "https://mcp.mem0.ai/mcp/",
-    headers: {
-      Authorization: "Token {env:MEM0_API_KEY}",
-    },
-    oauth: false,
-  },
-};
-
-const SKILLS_NAMESPACE = "mem0";
-
-function getConfigDir(): string {
-  const dir = join(homedir(), ".config", "opencode");
-  if (!existsSync(dir)) mkdirSync(dir, { recursive: true });
-  return dir;
-}
-
-function getConfigPath(): string {
-  const configDir = getConfigDir();
-  const jsonc = join(configDir, "opencode.jsonc");
-  if (existsSync(jsonc)) return jsonc;
-  return join(configDir, "opencode.json");
-}
-
-function stripJsonComments(text: string): string {
-  let result = "";
-  let i = 0;
-  let inString = false;
-  let escape = false;
-  while (i < text.length) {
-    const ch = text[i];
-    if (escape) {
-      result += ch;
-      escape = false;
-      i++;
-      continue;
-    }
-    if (inString) {
-      if (ch === "\\") escape = true;
-      else if (ch === '"') inString = false;
-      result += ch;
-      i++;
-      continue;
-    }
-    if (ch === '"') {
-      inString = true;
-      result += ch;
-      i++;
-      continue;
-    }
-    if (ch === "/" && text[i + 1] === "/") {
-      while (i < text.length && text[i] !== "\n") i++;
-      continue;
-    }
-    if (ch === "/" && text[i + 1] === "*") {
-      i += 2;
-      while (i < text.length && !(text[i] === "*" && text[i + 1] === "/")) i++;
-      i += 2;
-      continue;
-    }
-    result += ch;
-    i++;
-  }
-  return result;
-}
-
-function resolvePluginDir(): string {
-  try {
-    return dirname(new URL(import.meta.url).pathname);
-  } catch {}
-  return __dirname ?? process.cwd();
-}
-
-function findSkillsDir(): string {
-  const base = resolvePluginDir();
-  const candidates = [
-    join(base, "opencode-skills"),
-    join(dirname(base), "opencode-skills"),
-    join(base, "..", "opencode-skills"),
-  ];
-  for (const c of candidates) {
-    try {
-      if (existsSync(c) && statSync(c).isDirectory()) return c;
-    } catch {}
-  }
-  return "";
-}
-
-function installSkills(): number {
-  const skillsSource = findSkillsDir();
-  if (!skillsSource) {
-    console.log("  ! Skills directory not found — skipping slash command install");
-    return 0;
-  }
-
-  const skillsTarget = join(getConfigDir(), "skills");
-  if (!existsSync(skillsTarget)) mkdirSync(skillsTarget, { recursive: true });
-
-  let count = 0;
-  const entries = readdirSync(skillsSource);
-
-  for (const name of entries) {
-    const skillDir = join(skillsSource, name);
-    try {
-      if (!statSync(skillDir).isDirectory()) continue;
-    } catch {
-      continue;
-    }
-
-    const skillFile = join(skillDir, "SKILL.md");
-    if (!existsSync(skillFile)) continue;
-
-    const targetDir = join(skillsTarget, `${SKILLS_NAMESPACE}-${name}`);
-    if (!existsSync(targetDir)) mkdirSync(targetDir, { recursive: true });
-
-    copyFileSync(skillFile, join(targetDir, "SKILL.md"));
-    count++;
-  }
-
-  return count;
-}
-
-function uninstallSkills(): number {
-  const skillsTarget = join(getConfigDir(), "skills");
-  if (!existsSync(skillsTarget)) return 0;
-
-  let count = 0;
-  const entries = readdirSync(skillsTarget);
-
-  for (const name of entries) {
-    if (!name.startsWith(`${SKILLS_NAMESPACE}-`)) continue;
-    const fullPath = join(skillsTarget, name);
-    try {
-      if (!statSync(fullPath).isDirectory()) continue;
-      rmSync(fullPath, { recursive: true });
-      count++;
-    } catch {}
-  }
-
-  return count;
-}
-
-function install() {
-  console.log("Installing Mem0 plugin for OpenCode...\n");
-
-  const configPath = getConfigPath();
-  let config: any = {};
-
-  if (existsSync(configPath)) {
-    try {
-      const raw = readFileSync(configPath, "utf-8");
-      config = JSON.parse(stripJsonComments(raw));
-    } catch {
-      console.log(`  ! Could not parse ${configPath}, creating fresh config`);
-      config = {};
-    }
-  }
-
-  if (!Array.isArray(config.plugin)) config.plugin = [];
-  if (!config.plugin.includes(PLUGIN_NAME)) {
-    config.plugin.push(PLUGIN_NAME);
-    console.log(`  + Added "${PLUGIN_NAME}" to plugin array`);
-  } else {
-    console.log(`  ~ "${PLUGIN_NAME}" already in plugin array`);
-  }
-
-  if (!config.mcp) config.mcp = {};
-  if (!config.mcp.mem0) {
-    config.mcp.mem0 = MCP_CONFIG.mem0;
-    console.log("  + Added mem0 MCP server config");
-  } else {
-    console.log("  ~ mem0 MCP server already configured");
-  }
-
-  writeFileSync(configPath, JSON.stringify(config, null, 2) + "\n");
-  console.log(`\n  Wrote ${configPath}`);
-
-  const skillCount = installSkills();
-  if (skillCount > 0) {
-    console.log(`  + Installed ${skillCount} slash commands to ~/.config/opencode/skills/`);
-  }
-
-  console.log("");
-
-  if (!process.env.MEM0_API_KEY) {
-    console.log("  ! MEM0_API_KEY is not set in your environment.");
-    console.log(
-      '  Run: echo \'export MEM0_API_KEY="m0-your-key"\' >> ~/.zshrc && source ~/.zshrc',
-    );
-    console.log(
-      "  Get a free key at: https://app.mem0.ai/dashboard/api-keys\n",
-    );
-  } else {
-    console.log("  MEM0_API_KEY detected\n");
-  }
-
-  console.log("Done! Restart OpenCode to activate Mem0.");
-  console.log("  Then run /mem0-onboard in the TUI to complete setup.\n");
-}
-
-function uninstall() {
-  const configPath = getConfigPath();
-  if (!existsSync(configPath)) {
-    console.log("No OpenCode config found. Nothing to remove.");
-    return;
-  }
-
-  const raw = readFileSync(configPath, "utf-8");
-  const config = JSON.parse(stripJsonComments(raw));
-
-  if (Array.isArray(config.plugin)) {
-    config.plugin = config.plugin.filter((p: string) => p !== PLUGIN_NAME);
-    if (config.plugin.length === 0) delete config.plugin;
-  }
-
-  if (config.mcp?.mem0) {
-    delete config.mcp.mem0;
-    if (Object.keys(config.mcp).length === 0) delete config.mcp;
-  }
-
-  writeFileSync(configPath, JSON.stringify(config, null, 2) + "\n");
-  console.log(`  Removed plugin + MCP from ${configPath}`);
-
-  const skillCount = uninstallSkills();
-  if (skillCount > 0) {
-    console.log(`  Removed ${skillCount} slash commands from ~/.config/opencode/skills/`);
-  }
-
-  console.log("Restart OpenCode to complete removal.");
-}
-
-const cmd = process.argv[2];
-if (cmd === "uninstall" || cmd === "remove") {
-  uninstall();
-} else {
-  install();
-}

integrations/mem0-plugin/.opencode-plugin/dream.test.ts

@@ -0,0 +1,100 @@
+import { afterEach, beforeEach, describe, expect, test } from "bun:test";
+import { mkdtempSync, rmSync, writeFileSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+import {
+  loadDreamConfig,
+  incrementSessionCount,
+  checkCheapGates,
+  checkMemoryGate,
+  acquireDreamLock,
+  releaseDreamLock,
+  recordDreamCompletion,
+  DREAM_DEFAULTS,
+  DREAM_PROTOCOL,
+} from "./dream";
+
+let dir: string;
+
+beforeEach(() => {
+  dir = mkdtempSync(join(tmpdir(), "mem0-dream-"));
+});
+
+afterEach(() => {
+  try {
+    rmSync(dir, { recursive: true, force: true });
+  } catch {
+    /* ignore */
+  }
+  delete process.env.MEM0_DREAM;
+});
+
+describe("auto-dream gates", () => {
+  test("memory gate passes at >= minMemories, fails below", () => {
+    expect(checkMemoryGate(DREAM_DEFAULTS.minMemories, {}).pass).toBe(true);
+    expect(checkMemoryGate(DREAM_DEFAULTS.minMemories - 1, {}).pass).toBe(false);
+  });
+
+  test("cheap gates: fresh state blocks on session count, passes after enough sessions", () => {
+    // Fresh state: time gate passes (lastConsolidatedAt=0), but 0 sessions blocks.
+    expect(checkCheapGates(dir, {}).proceed).toBe(false);
+    for (let i = 0; i < DREAM_DEFAULTS.minSessions; i++) {
+      incrementSessionCount(dir, `ses_${i}`);
+    }
+    expect(checkCheapGates(dir, {}).proceed).toBe(true);
+  });
+
+  test("incrementSessionCount only counts distinct session ids", () => {
+    incrementSessionCount(dir, "ses_a");
+    incrementSessionCount(dir, "ses_a");
+    incrementSessionCount(dir, "ses_a");
+    expect(checkCheapGates(dir, { minHours: 0 }).reason).toContain("sessions: 1");
+  });
+
+  test("recordDreamCompletion resets gates (recent time blocks again)", () => {
+    for (let i = 0; i < 6; i++) incrementSessionCount(dir, `ses_${i}`);
+    expect(checkCheapGates(dir, {}).proceed).toBe(true);
+    recordDreamCompletion(dir);
+    const r = checkCheapGates(dir, {});
+    expect(r.proceed).toBe(false);
+    expect(r.reason).toContain("time");
+  });
+
+  test("dream lock is exclusive and reclaimable after release", () => {
+    expect(acquireDreamLock(dir)).toBe(true);
+    expect(acquireDreamLock(dir)).toBe(false);
+    releaseDreamLock(dir);
+    expect(acquireDreamLock(dir)).toBe(true);
+  });
+});
+
+describe("dream config", () => {
+  test("defaults when no settings file", () => {
+    const cfg = loadDreamConfig(dir);
+    expect(cfg.enabled).toBe(true);
+    expect(cfg.auto).toBe(true);
+    expect(cfg.minMemories).toBe(DREAM_DEFAULTS.minMemories);
+  });
+
+  test("MEM0_DREAM=false force-disables", () => {
+    process.env.MEM0_DREAM = "false";
+    expect(loadDreamConfig(dir).enabled).toBe(false);
+  });
+
+  test("settings.json dream block overrides defaults", () => {
+    writeFileSync(
+      join(dir, "settings.json"),
+      JSON.stringify({ dream: { minMemories: 99, auto: false } }),
+    );
+    const cfg = loadDreamConfig(dir);
+    expect(cfg.minMemories).toBe(99);
+    expect(cfg.auto).toBe(false);
+    expect(cfg.enabled).toBe(true);
+  });
+
+  test("protocol uses native tools, not the MCP tool", () => {
+    expect(DREAM_PROTOCOL).toContain("get_memories");
+    expect(DREAM_PROTOCOL).toContain("add_memory");
+    expect(DREAM_PROTOCOL).not.toContain("mem0_memory");
+  });
+});

integrations/mem0-plugin/.opencode-plugin/dream.ts

@@ -0,0 +1,225 @@
+/**
+ * Auto-dream: gated automatic memory consolidation for the Mem0 OpenCode plugin.
+ *
+ * Ported from the (stable) pi-agent plugin's dream module and adapted to
+ * OpenCode's hook model. When the cheap gates (time since last consolidation +
+ * sessions since) and the memory-count gate all pass, the plugin injects the
+ * DREAM_PROTOCOL into the agent's context so it consolidates memories (merge
+ * duplicates, drop stale/sensitive entries, rewrite vague ones) before
+ * answering. A filesystem lock prevents concurrent sessions from dreaming at
+ * once, and completion is recorded so it won't re-trigger until the next cycle.
+ *
+ * State + lock live in ~/.mem0/ alongside settings.json. Opt out with
+ * MEM0_DREAM=false, or tune via the `dream` block in ~/.mem0/settings.json.
+ */
+
+import { existsSync, mkdirSync, readFileSync, writeFileSync, unlinkSync } from "node:fs";
+import { join } from "node:path";
+
+export interface DreamConfig {
+  enabled: boolean;
+  auto: boolean;
+  minHours: number;
+  minSessions: number;
+  minMemories: number;
+}
+
+interface DreamState {
+  lastConsolidatedAt: number;
+  sessionsSince: number;
+  lastSessionId: string | null;
+}
+
+interface DreamLock {
+  pid: number;
+  startedAt: number;
+}
+
+const LOCK_STALE_MS = 60 * 60 * 1000;
+
+export const DREAM_DEFAULTS: DreamConfig = {
+  enabled: true,
+  auto: true,
+  minHours: 24,
+  minSessions: 5,
+  minMemories: 20,
+};
+
+function statePath(stateDir: string): string {
+  return join(stateDir, "mem0-dream-state.json");
+}
+
+function lockPath(stateDir: string): string {
+  return join(stateDir, "mem0-dream.lock");
+}
+
+function ensureDir(dir: string): void {
+  try {
+    mkdirSync(dir, { recursive: true });
+  } catch {
+    /* exists */
+  }
+}
+
+function readState(stateDir: string): DreamState {
+  try {
+    return JSON.parse(readFileSync(statePath(stateDir), "utf-8")) as DreamState;
+  } catch {
+    return { lastConsolidatedAt: 0, sessionsSince: 0, lastSessionId: null };
+  }
+}
+
+function writeState(stateDir: string, state: DreamState): void {
+  ensureDir(stateDir);
+  writeFileSync(statePath(stateDir), JSON.stringify(state, null, 2));
+}
+
+/**
+ * Load dream config from ~/.mem0/settings.json (`dream` block), applying
+ * defaults. MEM0_DREAM=false (or 0/no/off) force-disables regardless.
+ */
+export function loadDreamConfig(settingsDir: string): DreamConfig {
+  let envEnabled: boolean | undefined;
+  const env = process.env.MEM0_DREAM;
+  if (env !== undefined) {
+    const s = env.toLowerCase();
+    envEnabled = s !== "false" && s !== "0" && s !== "no" && s !== "off";
+  }
+
+  let cfg: DreamConfig = { ...DREAM_DEFAULTS };
+  try {
+    const sp = join(settingsDir, "settings.json");
+    if (existsSync(sp)) {
+      const settings = JSON.parse(readFileSync(sp, "utf-8"));
+      const d = settings?.dream;
+      if (d && typeof d === "object") {
+        cfg = {
+          enabled: typeof d.enabled === "boolean" ? d.enabled : cfg.enabled,
+          auto: typeof d.auto === "boolean" ? d.auto : cfg.auto,
+          minHours: typeof d.minHours === "number" ? d.minHours : cfg.minHours,
+          minSessions: typeof d.minSessions === "number" ? d.minSessions : cfg.minSessions,
+          minMemories: typeof d.minMemories === "number" ? d.minMemories : cfg.minMemories,
+        };
+      }
+    }
+  } catch {
+    /* defaults */
+  }
+
+  if (envEnabled !== undefined) cfg.enabled = envEnabled;
+  return cfg;
+}
+
+/** Count a new session toward the dream gate (once per distinct sessionId). */
+export function incrementSessionCount(stateDir: string, sessionId: string): void {
+  const state = readState(stateDir);
+  if (state.lastSessionId !== sessionId) {
+    state.sessionsSince++;
+    state.lastSessionId = sessionId;
+    writeState(stateDir, state);
+  }
+}
+
+/** Cheap gates that don't need an API call: time since last + sessions since. */
+export function checkCheapGates(
+  stateDir: string,
+  config: Partial<DreamConfig>,
+): { proceed: boolean; reason?: string } {
+  const minHours = config.minHours ?? DREAM_DEFAULTS.minHours;
+  const minSessions = config.minSessions ?? DREAM_DEFAULTS.minSessions;
+  const state = readState(stateDir);
+
+  const hoursSince = (Date.now() - state.lastConsolidatedAt) / 3_600_000;
+  if (hoursSince < minHours) {
+    return { proceed: false, reason: `time: ${hoursSince.toFixed(1)}h < ${minHours}h` };
+  }
+  if (state.sessionsSince < minSessions) {
+    return { proceed: false, reason: `sessions: ${state.sessionsSince} < ${minSessions}` };
+  }
+  return { proceed: true };
+}
+
+/** Memory-count gate (uses the count already fetched at session init). */
+export function checkMemoryGate(
+  memoryCount: number,
+  config: Partial<DreamConfig>,
+): { pass: boolean; reason?: string } {
+  const minMemories = config.minMemories ?? DREAM_DEFAULTS.minMemories;
+  if (memoryCount < minMemories) {
+    return { pass: false, reason: `memories: ${memoryCount} < ${minMemories}` };
+  }
+  return { pass: true };
+}
+
+/** Acquire an exclusive dream lock (stale locks > 1h are reclaimed). */
+export function acquireDreamLock(stateDir: string): boolean {
+  ensureDir(stateDir);
+  const lp = lockPath(stateDir);
+
+  try {
+    const lock = JSON.parse(readFileSync(lp, "utf-8")) as DreamLock;
+    if (Date.now() - lock.startedAt < LOCK_STALE_MS) {
+      return false;
+    }
+    try {
+      unlinkSync(lp);
+    } catch {
+      /* race ok */
+    }
+  } catch {
+    /* no lock file */
+  }
+
+  const lock: DreamLock = { pid: process.pid, startedAt: Date.now() };
+  try {
+    writeFileSync(lp, JSON.stringify(lock), { flag: "wx" });
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+export function releaseDreamLock(stateDir: string): void {
+  try {
+    unlinkSync(lockPath(stateDir));
+  } catch {
+    /* already gone */
+  }
+}
+
+/** Reset the gates after a successful consolidation. */
+export function recordDreamCompletion(stateDir: string): void {
+  const state = readState(stateDir);
+  state.lastConsolidatedAt = Date.now();
+  state.sessionsSince = 0;
+  state.lastSessionId = null;
+  writeState(stateDir, state);
+}
+
+/**
+ * Consolidation protocol injected into the agent context when a dream is
+ * triggered. Uses the plugin's native OpenCode memory tools (get_memories /
+ * add_memory / delete_memory) rather than an MCP tool.
+ */
+export const DREAM_PROTOCOL = `<mem0-dream>
+You are running memory consolidation. Complete these steps using the mem0 memory tools (get_memories, add_memory, delete_memory):
+
+1. ORIENT — Call get_memories to list all memories. Count by category. Note oldest/newest.
+
+2. GATHER TARGETS — Review each memory. Classify as:
+   - DELETE: sensitive information (API keys, passwords, tokens), expired/stale entries, noise, redundant operational details
+   - MERGE: near-duplicates (same fact stated differently). Keep the better-worded one, delete the other.
+   - REWRITE: vague, first-person, or poorly-categorized entries. add_memory with improved text, then delete_memory the old one.
+   - KEEP: everything else.
+   Skip any memory starting with "[PINNED]".
+
+3. CONSOLIDATE — Execute the changes:
+   - Delete stale/duplicate entries with delete_memory
+   - For merges: add_memory the merged text, delete_memory both originals
+   - For rewrites: add_memory the improved version, delete_memory the original
+
+4. REPORT — Summarize: how many reviewed, deleted, merged, rewritten, final count.
+
+Quality targets: zero sensitive data stored, zero duplicates, all entries are atomic (one fact each), 15-50 words each.
+After consolidation, respond to the user's message normally.
+</mem0-dream>`;

integrations/mem0-plugin/.opencode-plugin/opencode-skills/export/SKILL.md

@@ -1,80 +0,0 @@
----
-name: export
-description: Exports all project memories to a portable Markdown file for backup or migration. Use when backing up memories, migrating to another project, sharing memory state with teammates, or archiving before cleanup.
----
-
-# Mem0 Export
-
-Export all memories for the current project to a portable Markdown file.
-
-## Execution
-
-### Step 1: Resolve identity
-
-Determine the active identity:
-- `user_id` from `MEM0_USER_ID` env var, else `$USER`, else `"default"`
-- `project_id` (used as `app_id`) from `MEM0_PROJECT_ID` env var, or via the project resolver
-
-### Step 2: Fetch all memories
-
-Call `get_memories` with:
-- `filters={"AND": [{"user_id": "<active_user_id>"}, {"app_id": "<active_project_id>"}]}`
-- `page_size=200`
-
-If the response is paginated (i.e. the result contains a `next` cursor or the count equals `page_size`), continue fetching pages until all memories are retrieved.
-
-### Step 3: Format each memory as a YAML-frontmatter block
-
-For each memory record, produce a block in this exact format:
-
-```
----
-id: <memory.id>
-created_at: <memory.created_at>
-type: <memory.metadata.type or "">
-confidence: <memory.metadata.confidence or "">
-branch: <memory.metadata.branch or "">
-files: <memory.metadata.files joined with ", " or "">
-categories: <memory.categories joined with ", " or "">
----
-<memory.memory or memory content string>
-
-```
-
-Notes:
-- The `---` delimiters must be on their own lines with no extra whitespace.
-- `files` and `categories` are written as comma-separated values on a single line.
-- Leave a blank line after the content before the next `---` (for readability).
-- If a field is missing or null, write an empty string (not "null").
-
-### Step 4: Write the export file
-
-Determine the output filename:
-
-```
-mem0-export-<project_id>-<YYYY-MM-DD>.md
-```
-
-Where `<YYYY-MM-DD>` is today's date in UTC.
-
-Write all formatted blocks to this file using the Write tool (or equivalent). The file is written to the current working directory.
-
-### Step 5: Print summary
-
-```
-Exported <N> memories to <filename>
-```
-
-Where `<N>` is the total number of memory blocks written.
-
-## Error Handling
-
-- If `get_memories` returns an error or zero memories, print:
-  ```
-  No memories found for project <project_id>. Nothing exported.
-  ```
-- If the write fails, report the error to the user.
-
-## Output formatting
-
-IMPORTANT: Do NOT use markdown in your output. OpenCode TUI renders text verbatim — markdown like **bold**, ## headers, and | table | syntax appears as raw characters. Use plain text with indentation for structure. Use dashes for lists. Use spaces to align columns instead of markdown tables.

integrations/mem0-plugin/.opencode-plugin/opencode-skills/import/SKILL.md

@@ -1,185 +0,0 @@
----
-name: import
-description: Imports memories from an exported Markdown file or MEMORY.md into the current project. Use when migrating from another project, restoring from backup, importing Claude Code native MEMORY.md content, or setting up a new project with existing knowledge.
----
-
-# Mem0 Import
-
-Import memories from a mem0 export file into the current project.
-
-## Execution
-
-### Step 1: Determine the export file to import
-
-If the user provided a filename as an argument to `/mem0:import <filename>`, use that file.
-
-Otherwise, list `.md` files in the current directory whose names contain `mem0-export`:
-
-```bash
-ls -1 *.md 2>/dev/null | grep mem0-export || echo "No export files found"
-```
-
-If multiple files are found, ask the user which one to import. If none are found, print:
-```
-No mem0-export files found in the current directory.
-Run /mem0:export first, or provide the filename: /mem0:import <path-to-file>
-```
-
-### Step 2: Parse the export file
-
-Read the export file directly. It is a JSON file containing a top-level `memories` array. Each element has:
-- `id` — original memory ID (for reference only; a new ID will be assigned on import)
-- `type` — metadata type
-- `confidence` — metadata confidence value
-- `branch` — metadata branch
-- `files` — list of associated files
-- `categories` — list of categories
-- `content` — the memory text
-
-Parse the JSON in-memory (do not run any external script). If the file cannot be read or parsed, or if the `memories` array is missing or empty, print:
-```
-Failed to parse <filename> or file contains no valid memory blocks.
-```
-and stop.
-
-### Step 3: Resolve identity
-
-Determine the active identity:
-- `user_id` from `MEM0_USER_ID` env var, else `$USER`, else `"default"`
-- `project_id` (used as `app_id`) from `MEM0_PROJECT_ID` env var, or via the project resolver
-
-### Step 4: Import each memory
-
-For each record in the parsed JSON array, call `add_memory` (MCP tool) with:
-
-- `text="<record.content>"`
-- `user_id=<active_user_id>`
-- `app_id=<active_project_id>`
-- `metadata={`
-  - `"type": "<record.type>"` (if non-empty)
-  - `"confidence": "<record.confidence>"` (if non-empty)
-  - `"branch": "<record.branch>"` (if non-empty)
-  - `"files": <record.files>` (the list, if non-empty)
-  - `"source": "import"`
-  - `}`
-- `infer=False`
-
-Notes:
-- Do NOT pass the original `id` — the platform assigns a new ID.
-- Skip records where `content` is empty.
-- Continue importing even if individual records fail; track the count of successes.
-
-### Step 5: Print results
-
-```
-Imported <N> memories into project <project_id>
-```
-
-Where `<N>` is the number of successfully imported memories.
-
-If any failed:
-```
-Imported <N>/<total> memories into project <project_id> (<failed> failed)
-```
-
-## Importing from competing AI tools (`--tools`)
-
-When invoked with `--tools` (e.g., `/mem0:import --tools`), detect and import
-from competing AI tool configuration files:
-
-### Supported tools
-
-| Tool | File/directory |
-|------|---------------|
-| Cursor | `.cursorrules` |
-| GitHub Copilot | `.github/copilot-instructions.md` |
-| Cline | `memory-bank/` (directory of `.md` files) |
-| Continue | `.continue/rules.md` |
-
-### T1: Detect
-
-```bash
-test -f .cursorrules && echo "cursor: .cursorrules"
-test -f .github/copilot-instructions.md && echo "copilot: .github/copilot-instructions.md"
-test -d memory-bank/ && echo "cline: memory-bank/"
-test -f .continue/rules.md && echo "continue: .continue/rules.md"
-```
-
-### T2: Ask user
-
-List found files, ask which to import (numbers, comma-separated, or "all").
-If none found:
-```
-No competing tool configuration files found.
-Checked: .cursorrules, .github/copilot-instructions.md, memory-bank/, .continue/rules.md
-```
-
-### T3: Import
-
-For each selected tool, read the file(s) directly and split the content into logical
-chunks to import as individual memories. No external scripts are used — all parsing
-and importing is done via MCP tools.
-
-Chunking rules per tool:
-
-- **cursorrules / copilot / continue**: Read the file as plain text. Split on blank
-  lines or section headers (`#`, `##`). Each non-empty chunk becomes one memory.
-  Skip chunks shorter than 50 characters.
-
-- **cline (memory-bank/)**: List all `.md` files in the directory. Read each file.
-  Split each file on blank lines or headers. Each non-empty chunk becomes one memory.
-  Skip chunks shorter than 50 characters.
-
-For each chunk, call `add_memory` (MCP tool) with:
-- `text="<chunk text>"`
-- `user_id=<active_user_id>`
-- `app_id=<active_project_id>`
-- `metadata={"type": "task_learning", "source": "<tool>-import", "confidence": 0.8}`
-- `infer=False`
-
-Where `<tool>` is `cursorrules`, `copilot`, `cline`, or `continue`.
-
-Notes: chunks longer than 10,000 characters are truncated before import. Safe to
-re-run — deduplication handles repeated entries.
-
-### T4: Report
-
-```
-Imported <N> memories into <project_id> (cursor: <N>, copilot: <N>)
-```
-
----
-
-## Importing Claude Code's native MEMORY.md
-
-When invoked with a path to Claude Code's native `MEMORY.md` file (typically
-`~/.claude/projects/<proj-key>/memory/MEMORY.md`), or when `on_session_start.sh`
-detects native auto-memory and the user chooses to import:
-
-1. Read the file directly. It contains newline-separated memory entries (one fact per
-   line, sometimes with `- ` bullet prefix).
-2. Split by non-empty lines. Each line becomes one memory.
-3. Skip lines shorter than 20 characters or lines that are just headers (`#`).
-4. For each line, call `add_memory` (MCP tool) with:
-   - `text="<line>"`
-   - `user_id=<active_user_id>`
-   - `app_id=<active_project_id>`
-   - `metadata={"type": "task_learning", "source": "memory-md-import", "confidence": 0.8}`
-   - `infer=False`
-5. Report: `Imported <N> memories from MEMORY.md into project <project_id>`
-6. Suggest disabling native auto-memory:
-   ```
-   To avoid duplicate memory systems, add to ~/.claude/settings.json:
-     "autoMemoryEnabled": false
-   ```
-
-This handles the cold-start gap when a user has been using Claude Code's native
-memory and switches to mem0.
-
-## Error Handling
-
-- If `add_memory` calls fail consistently (e.g. auth error), report the issue and stop early.
-
-## Output formatting
-
-IMPORTANT: Do NOT use markdown in your output. OpenCode TUI renders text verbatim — markdown like **bold**, ## headers, and | table | syntax appears as raw characters. Use plain text with indentation for structure. Use dashes for lists. Use spaces to align columns instead of markdown tables.