chore: touch pyproject.toml to fire Python SDK CI for plugin-only PR

Plugin paths are filtered out of every CI workflow. Same path-filter
trap and same workaround as #5094.

.claude-plugin/marketplace.json

@@ -12,7 +12,7 @@
       "name": "mem0",
       "source": "./mem0-plugin",
       "description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search to Claude workflows.",
-      "version": "0.1.2"
+      "version": "0.1.3"
     }
   ]
 }

docs/changelog/sdk.mdx

@@ -1326,7 +1326,7 @@ See the [TypeScript SDK migration guide](https://docs.mem0.ai/migration/ts-v2-to
 <Update label="2026-05-14" description="Python v0.2.5 / Node v0.2.5">
 
 **New Features:**
-- **Agent Mode (`mem0 init --agent`):** Zero-friction signup for AI agents — mints a working Mem0 API key in under 5 seconds with no email, no dashboard, no OTP. Returns an unclaimed shadow account the human can later claim with `mem0 init --email <their-email>` (memories preserved, same key keeps working) ([#5123](https://github.com/mem0ai/mem0/pull/5123))
+- **Agent Mode (`mem0 init --agent`):** Zero-friction signup for AI agents — mints a working Mem0 API key in <5s with no email, no dashboard, no OTP. Returns an unclaimed shadow account the human can later claim with `mem0 init --email <their-email>` (memories preserved, same key keeps working) ([#5123](https://github.com/mem0ai/mem0/pull/5123))
 - **Self-declared agent identity:** Agents pass `--agent-caller <name>` (e.g. `claude-code`, `cursor`, `codex`) on `mem0 init --agent` so signups attribute to the right tool in analytics. Proof Editor-style — the agent declares itself rather than the CLI sniffing it from env vars ([#5123](https://github.com/mem0ai/mem0/pull/5123))
 - **`mem0 identify <name>`:** New subcommand to self-tag an Agent Mode key after the fact when the agent forgot to pass `--agent-caller` on init. Idempotent — re-running just overwrites ([#5123](https://github.com/mem0ai/mem0/pull/5123))
 - **Plugin sync:** `~/.claude/settings.json::env::MEM0_API_KEY` and `~/.zshrc`/`.bashrc` `export MEM0_API_KEY=` lines stay in sync with `~/.mem0/config.json` automatically. Idempotent — only updates EXISTING entries, never creates new ones ([#5123](https://github.com/mem0ai/mem0/pull/5123))

docs/platform/cli.mdx

@@ -25,44 +25,7 @@ pip install mem0-cli
 ```
 </CodeGroup>
 
-## Agent Mode — zero-friction signup for AI agents
-
-<Tip>
-**If you're an AI agent reading this**, skip the rest of this page until you've run the command below. Everything else assumes you already have an API key.
-</Tip>
-
-AI agents (Claude Code, Cursor, Codex, Cline, Aider, …) can mint a working Mem0 API key in under five seconds with no email, no dashboard, and no OTP:
-
-```bash
-mem0 init --agent --agent-caller claude-code
-```
-
-Replace `claude-code` with your agent's name (e.g. `cursor`, `codex`, `cline`, `aider`, or any custom string). The CLI saves the key to `~/.mem0/config.json` and prints a notice you should surface to your human user. The human can claim the account later — same API key keeps working, memories transfer.
-
-<Tip>
-**Forgot `--agent-caller`?** Run `mem0 identify <your-name>` after init — same key, just back-fills the attribution. Idempotent.
-</Tip>
-
-### Claiming an Agent Mode key (humans)
-
-When the human is ready, they claim ownership of the agent's key by running:
-
-```bash
-mem0 init --email you@yourcompany.com
-```
-
-The CLI detects the existing unclaimed Agent Mode config, sends a verification code, and upgrades the shadow account in-place: **the API key never changes, all memories transfer to the human's account, and the agent isn't disrupted**. Pass `--code 123456` for fully non-interactive flows.
-
-### Plugin sync
-
-When you save a Mem0 API key (any flow — Agent Mode, email, or `--api-key`), the CLI also propagates it to ecosystem touchpoints **that already exist**:
-
-- `~/.claude/settings.json` → `env.MEM0_API_KEY` (Claude Code plugin env injection)
-- `~/.zshrc` / `~/.bashrc` → existing `export MEM0_API_KEY=` lines
-
-Sync is idempotent and **never creates new entries** — it only updates entries you've already set up. Failures are best-effort and never block the canonical write to `~/.mem0/config.json`.
-
-## Authentication (humans)
+## Authentication
 
 Run the interactive setup wizard to configure your API key:
 
@@ -116,7 +79,6 @@ Interactive setup wizard. Prompts for your API key and default user ID.
 mem0 init
 mem0 init --api-key m0-xxx --user-id alice
 mem0 init --email alice@company.com
-mem0 init --agent --agent-caller claude-code   # zero-friction signup for AI agents
 ```
 
 If an existing configuration is detected, the CLI will ask for confirmation before overwriting. Use `--force` to skip the prompt (useful in CI/CD pipelines).
@@ -129,25 +91,10 @@ mem0 init --api-key m0-xxx --user-id alice --force
 |------|-------------|
 | `--api-key` | API key (skip prompt) |
 | `-u, --user-id` | Default user ID (skip prompt) |
-| `--email` | Login via email verification code (also used to claim an Agent Mode key) |
+| `--email` | Login via email verification code |
 | `--code` | Verification code (use with `--email` for non-interactive login) |
-| `--agent` | Bootstrap an Agent Mode account — no email, no dashboard |
-| `--agent-caller` | Self-declared agent identity for Agent Mode signups (e.g. `claude-code`, `cursor`) |
-| `--source` | Channel attribution for analytics (e.g. `github`, `hn`, `ph`) |
 | `--force` | Overwrite existing config without confirmation |
 
-### `mem0 identify`
-
-Tag your active Agent Mode key with the AI agent that's using it. Run this once after `mem0 init --agent` if you didn't pass `--agent-caller` on init. Idempotent — re-running just overwrites the value.
-
-```bash
-mem0 identify claude-code
-mem0 identify cursor
-mem0 identify my-custom-bot
-```
-
-The CLI calls `PATCH /api/v1/auth/agent_mode/caller/` against the active key. Only works on unclaimed Agent Mode keys; the backend rejects with 400 otherwise. Agent names are sanitized server-side (lowercased, restricted to `[a-z0-9._/-]`, truncated to 32 chars).
-
 ### `mem0 add`
 
 Add a memory from text, a JSON messages array, a file, or stdin.

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

@@ -1,6 +1,6 @@
 {
   "name": "mem0",
-  "version": "0.1.2",
+  "version": "0.1.3",
   "description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search to Claude workflows using the Mem0 Platform MCP server.",
   "author": {
     "name": "Mem0",

mem0-plugin/CHANGELOG.md

@@ -0,0 +1,45 @@
+# Changelog
+
+All notable changes to the Mem0 plugin will be documented in this file.
+
+## 0.1.3
+
+### Fixed
+
+- **user_id resolution no longer derives from `MEM0_API_KEY`.** v0.1.2 changed the resolver to fall back to `"mem0-" + sha256(MEM0_API_KEY)[:12]` ahead of `$USER`, which silently moved every existing user to a new bucket on update. Memories written under the previous `$USER` value became unreachable from the plugin. Resolution is now back to `MEM0_USER_ID` → `$USER` → `"default"`.
+- Dropped the "regardless of which machine you're on" line from the SessionStart bootstrap, since cross-machine consolidation now requires setting `MEM0_USER_ID` explicitly.
+
+### Notes for users upgrading from 0.1.2
+
+- The `~/.mem0/identity.json` cache file is no longer read or written. Safe to delete.
+- If you wrote memories during the v0.1.2 window, they live under `mem0-<sha256(api_key)[:12]>`. To recover: temporarily `export MEM0_USER_ID=mem0-<hash>`, search/export, then unset.
+- Want a single bucket across machines (the original goal of #5076)? Set `MEM0_USER_ID` explicitly in your shell profile. The plugin will not auto-derive one.
+
+## 0.1.2
+
+### Added
+
+- Deterministic `user_id` resolver (`_identity.sh` / `_identity.py`) — **reverted in 0.1.3, see above.**
+- SessionStart-compact handler (`capture_compact_summary.py`) that stores the post-compaction summary as a memory with `metadata.type=compact_summary`.
+- Coding-taxonomy setup script (`setup_coding_categories.py`) — one-shot `project.update(custom_categories=[...])` for `architecture_decisions`, `anti_patterns`, `task_learnings`, `tooling_setup`, `bug_fixes`, `coding_conventions`, `user_preferences`.
+- Opt-in hook logging via `MEM0_DEBUG=1` → `~/.mem0/hooks.log`.
+- `mem0-mcp` skill replacing the Claude-Code-specific `mem0-codex` skill.
+
+### Fixed
+
+- `session_id` now written to memory metadata (`on_pre_compact.py`).
+- SessionStart bootstrap exits silently when `MEM0_API_KEY` is unset.
+- `block_memory_write.sh` regex tightened to `MEMORY.md` / `.claude/memory/*` — no longer blocks `docs/memory/*.md`.
+- Removed duplicate PreCompact write path (kept agent-driven, dropped the parallel Python REST entry from `hooks.json` / `cursor-hooks.json`).
+- Hook-side captures (`session_state`, `compact_summary`) now set `expiration_date = today + 90 days`.
+
+## 0.1.1
+
+- Cursor plugin fully functional (`#4547`).
+- Codex plugin support and integration docs (`#4665`).
+- Codex lifecycle hooks via opt-in installer (`#4917`).
+- Removed invalid keys from Claude plugin config (`#4821`).
+
+## 0.1.0
+
+- Initial release: Mem0 plugin for Claude Code and Cursor (`#4518`).

mem0-plugin/scripts/_identity.py

@@ -1,59 +1,17 @@
-"""Resolve mem0 user_id with deterministic priority.
+"""Resolve mem0 user_id.
 
 Resolution priority:
   1. MEM0_USER_ID env var (explicit override)
-  2. ~/.mem0/identity.json cache (pinned to current MEM0_API_KEY fingerprint)
-  3. Derived: "mem0-" + sha256(MEM0_API_KEY)[:12]
-  4. Fallback: $USER, else "default"
-
-Same MEM0_API_KEY across machines yields the same user_id, which fixes
-the "47 user buckets per account" symptom from running on multiple
-laptops with different $USER values.
+  2. $USER, else "default"
 """
 
 from __future__ import annotations
 
-import hashlib
-import json
 import os
-from datetime import datetime, timezone
-
-_CACHE_PATH = os.path.expanduser("~/.mem0/identity.json")
 
 
 def resolve_user_id() -> str:
     explicit = os.environ.get("MEM0_USER_ID", "").strip()
     if explicit:
         return explicit
-
-    api_key = os.environ.get("MEM0_API_KEY", "").strip()
-    if api_key:
-        digest = hashlib.sha256(api_key.encode("utf-8")).hexdigest()
-        fingerprint = digest[:8]
-
-        try:
-            with open(_CACHE_PATH, "r") as f:
-                cached = json.load(f)
-            if cached.get("api_key_fingerprint") == fingerprint and cached.get("user_id"):
-                return cached["user_id"]
-        except (OSError, json.JSONDecodeError):
-            pass
-
-        derived = "mem0-" + digest[:12]
-        try:
-            os.makedirs(os.path.dirname(_CACHE_PATH), exist_ok=True)
-            with open(_CACHE_PATH, "w") as f:
-                json.dump(
-                    {
-                        "user_id": derived,
-                        "source": "api_key",
-                        "api_key_fingerprint": fingerprint,
-                        "resolved_at": datetime.now(timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ"),
-                    },
-                    f,
-                )
-        except OSError:
-            pass
-        return derived
-
     return os.environ.get("USER") or "default"

mem0-plugin/scripts/_identity.sh

@@ -2,54 +2,13 @@
 #
 # Resolution priority:
 #   1. MEM0_USER_ID env var (explicit override)
-#   2. ~/.mem0/identity.json cache (pinned to current MEM0_API_KEY fingerprint)
-#   3. Derived: "mem0-" + sha256(MEM0_API_KEY)[:12]
-#   4. Fallback: $USER, else "default"
-#
-# Same MEM0_API_KEY across machines yields the same user_id, which fixes
-# the "47 user buckets per account" symptom from running on multiple
-# laptops with different $USER values.
-
-_mem0_sha256() {
-  if command -v sha256sum >/dev/null 2>&1; then
-    sha256sum | cut -d' ' -f1
-  else
-    shasum -a 256 | cut -d' ' -f1
-  fi
-}
+#   2. $USER, else "default"
 
 _mem0_resolve_identity() {
   if [ -n "${MEM0_USER_ID:-}" ]; then
     printf '%s' "$MEM0_USER_ID"
     return
   fi
-
-  local api_key="${MEM0_API_KEY:-}"
-  local cache="$HOME/.mem0/identity.json"
-
-  if [ -n "$api_key" ]; then
-    local digest
-    digest=$(printf '%s' "$api_key" | _mem0_sha256)
-    local fp="${digest:0:8}"
-
-    if [ -f "$cache" ]; then
-      local cached_fp cached_id
-      cached_fp=$(jq -r '.api_key_fingerprint // ""' "$cache" 2>/dev/null)
-      cached_id=$(jq -r '.user_id // ""' "$cache" 2>/dev/null)
-      if [ "$cached_fp" = "$fp" ] && [ -n "$cached_id" ]; then
-        printf '%s' "$cached_id"
-        return
-      fi
-    fi
-
-    local derived="mem0-${digest:0:12}"
-    mkdir -p "$HOME/.mem0" 2>/dev/null && \
-      printf '{"user_id":"%s","source":"api_key","api_key_fingerprint":"%s","resolved_at":"%s"}\n' \
-        "$derived" "$fp" "$(date -u +%FT%TZ)" > "$cache" 2>/dev/null
-    printf '%s' "$derived"
-    return
-  fi
-
   printf '%s' "${USER:-default}"
 }
 

mem0-plugin/scripts/on_session_start.sh

@@ -36,7 +36,7 @@ echo "## Mem0 Identity"
 echo ""
 echo "Active user_id: \`$MEM0_RESOLVED_USER_ID\`"
 echo ""
-echo "Always include \`{\"user_id\": \"$MEM0_RESOLVED_USER_ID\"}\` (wrapped in an \`AND\` clause) in every \`search_memories\` filter and as \`user_id\` on every \`add_memory\` call. This keeps memories under one bucket regardless of which machine you're on."
+echo "Always include \`{\"user_id\": \"$MEM0_RESOLVED_USER_ID\"}\` (wrapped in an \`AND\` clause) in every \`search_memories\` filter and as \`user_id\` on every \`add_memory\` call. This keeps the agent's MCP calls aligned with the bucket the hooks write to."
 echo ""
 
 if [ "$SOURCE" = "startup" ]; then

mem0/__init__.py

@@ -4,3 +4,5 @@ __version__ = importlib.metadata.version("mem0ai")
 
 from mem0.client.main import AsyncMemoryClient, MemoryClient  # noqa
 from mem0.memory.main import AsyncMemory, Memory  # noqa
+
+

pyproject.toml

@@ -156,3 +156,4 @@ known_first_party = ["mem0", "mem0_cli"]
 # isort scope kept aligned with [tool.ruff.lint.isort] above.
 # black-equivalent profile here matches the formatter behaviour ruff applies.
 # Plugin-version bumps need a touch here to fire required CI checks (path-filter trap).
+# Last touched: plugin v0.1.3