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

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

.agents/plugins/marketplace.json

@@ -8,7 +8,7 @@
       "name": "mem0",
       "source": {
         "source": "local",
-        "path": "./mem0-plugin"
+        "path": "./integrations/mem0-plugin"
       },
       "policy": {
         "installation": "AVAILABLE",

.claude-plugin/marketplace.json

@@ -10,9 +10,9 @@
   "plugins": [
     {
       "name": "mem0",
-      "source": "./mem0-plugin",
+      "source": "./integrations/mem0-plugin",
       "description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search to Claude workflows.",
-      "version": "0.2.8"
+      "version": "0.2.11"
     }
   ]
 }

.codex-plugin/marketplace.json

@@ -8,7 +8,7 @@
       "name": "mem0",
       "source": {
         "source": "local",
-        "path": "./mem0-plugin"
+        "path": "./integrations/mem0-plugin"
       },
       "policy": {
         "installation": "AVAILABLE",

.cursor-plugin/marketplace.json

@@ -10,9 +10,9 @@
   "plugins": [
     {
       "name": "mem0",
-      "source": "./mem0-plugin",
+      "source": "./integrations/mem0-plugin",
       "description": "Mem0 memory layer for AI applications. Add persistent memory, personalization, and semantic search.",
-      "version": "0.2.8"
+      "version": "0.2.11"
     }
   ]
 }

.github/workflows/cd.yml

@@ -1,18 +1,33 @@
 name: Publish Python 🐍 distributions 📦 to PyPI and TestPyPI
 
+# Dispatched by release.yml (Release Router) when a release tagged v* is
+# published. Can also be dispatched manually to re-publish a tag.
 on:
-  release:
-    types: [published]
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build and publish (e.g. v1.2.3)'
+        required: true
+        type: string
+      prerelease:
+        description: 'Unused for PyPI (pre-releases are expressed in the version itself); accepted for router uniformity'
+        required: false
+        type: boolean
+        default: false
 
 jobs:
   build-n-publish:
     name: Build and publish Python 🐍 distributions 📦 to PyPI and TestPyPI
-    if: startsWith(github.event.release.tag_name, 'v')
+    # Pure SDK version tags only (v1.2.3) — excludes package-prefixed tags
+    # like vercel-ai-v* that also start with 'v'
+    if: startsWith(inputs.tag, 'v') && !contains(inputs.tag, '-v')
     runs-on: ubuntu-latest
     permissions:
       id-token: write
     steps:
       - uses: actions/checkout@v2
+        with:
+          ref: ${{ inputs.tag }}
 
       - name: Set up Python
         uses: actions/setup-python@v2
@@ -39,7 +54,6 @@ jobs:
       #     packages_dir: dist/
 
       - name: Publish distribution 📦 to PyPI
-        if: startsWith(github.ref, 'refs/tags/v')
         uses: pypa/gh-action-pypi-publish@release/v1
         with:
           packages_dir: dist/

.github/workflows/ci-gate.yml

@@ -0,0 +1,171 @@
+name: CI Gate
+
+# Single required status check for all PRs.
+#
+# Path-filtered CI workflows can't be marked as required in branch
+# protection: on a PR that doesn't touch their paths they never report, and
+# the required check hangs at "Expected" forever. This gate solves that. It
+# runs on every PR, detects which packages changed, calls only the relevant
+# package CI workflows (as reusable workflows), and the final "CI Gate" job
+# reports the aggregate result — success when every invoked pipeline passed
+# (skipped pipelines are fine), failure when any failed.
+#
+# Branch protection should require exactly one status check: "CI Gate".
+#
+# Package CI workflows keep their own push-to-main and workflow_dispatch
+# triggers; only their pull_request triggers moved here. To wire in a new
+# package: add a filter under the `changes` job, a call job that `uses:` the
+# package workflow, and list the call job in the gate's `needs`.
+
+on:
+  pull_request:
+
+concurrency:
+  group: ci-gate-${{ github.event.pull_request.number }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+  pull-requests: read
+
+jobs:
+  changes:
+    name: Detect changed packages
+    runs-on: ubuntu-latest
+    outputs:
+      python_sdk: ${{ steps.filter.outputs.python_sdk }}
+      ts_sdk: ${{ steps.filter.outputs.ts_sdk }}
+      cli_python: ${{ steps.filter.outputs.cli_python }}
+      cli_node: ${{ steps.filter.outputs.cli_node }}
+      openclaw: ${{ steps.filter.outputs.openclaw }}
+      opencode_plugin: ${{ steps.filter.outputs.opencode_plugin }}
+      pi_agent_plugin: ${{ steps.filter.outputs.pi_agent_plugin }}
+      docs_llms_txt: ${{ steps.filter.outputs.docs_llms_txt }}
+    steps:
+      - uses: dorny/paths-filter@v3
+        id: filter
+        with:
+          # Each filter mirrors the package workflow's old pull_request
+          # paths, plus the package workflow file itself and this gate file
+          # (changing either must re-exercise the pipeline).
+          filters: |
+            python_sdk:
+              - 'mem0/**'
+              - 'tests/**'
+              - 'pyproject.toml'
+              - '.github/workflows/ci.yml'
+              - '.github/workflows/ci-gate.yml'
+            ts_sdk:
+              - 'mem0-ts/**'
+              - '.github/workflows/ts-sdk-ci.yml'
+              - '.github/workflows/ci-gate.yml'
+            cli_python:
+              - 'cli/python/**'
+              - '.github/workflows/cli-python-ci.yml'
+              - '.github/workflows/ci-gate.yml'
+            cli_node:
+              - 'cli/node/**'
+              - '.github/workflows/cli-node-ci.yml'
+              - '.github/workflows/ci-gate.yml'
+            openclaw:
+              - 'integrations/openclaw/**'
+              - '.github/workflows/openclaw-checks.yml'
+              - '.github/workflows/ci-gate.yml'
+            opencode_plugin:
+              - 'integrations/mem0-plugin/.opencode-plugin/**'
+              - '.github/workflows/opencode-plugin-checks.yml'
+              - '.github/workflows/ci-gate.yml'
+            pi_agent_plugin:
+              - 'integrations/pi-agent-plugin/**'
+              - '.github/workflows/pi-agent-plugin-checks.yml'
+              - '.github/workflows/ci-gate.yml'
+            docs_llms_txt:
+              - 'docs/**/*.mdx'
+              - 'docs/llms.txt'
+              - 'scripts/check-llms-txt-coverage.py'
+              - 'scripts/llms-txt-ignore.txt'
+              - '.github/workflows/docs-llms-txt-check.yml'
+              - '.github/workflows/ci-gate.yml'
+
+  python-sdk:
+    name: Python SDK
+    needs: changes
+    if: needs.changes.outputs.python_sdk == 'true'
+    uses: ./.github/workflows/ci.yml
+    secrets: inherit
+
+  ts-sdk:
+    name: TypeScript SDK
+    needs: changes
+    if: needs.changes.outputs.ts_sdk == 'true'
+    uses: ./.github/workflows/ts-sdk-ci.yml
+    secrets: inherit
+
+  cli-python:
+    name: Python CLI
+    needs: changes
+    if: needs.changes.outputs.cli_python == 'true'
+    uses: ./.github/workflows/cli-python-ci.yml
+    secrets: inherit
+
+  cli-node:
+    name: Node CLI
+    needs: changes
+    if: needs.changes.outputs.cli_node == 'true'
+    uses: ./.github/workflows/cli-node-ci.yml
+    secrets: inherit
+
+  openclaw:
+    name: OpenClaw
+    needs: changes
+    if: needs.changes.outputs.openclaw == 'true'
+    uses: ./.github/workflows/openclaw-checks.yml
+    secrets: inherit
+
+  opencode-plugin:
+    name: OpenCode Plugin
+    needs: changes
+    if: needs.changes.outputs.opencode_plugin == 'true'
+    uses: ./.github/workflows/opencode-plugin-checks.yml
+    secrets: inherit
+
+  pi-agent-plugin:
+    name: Pi Agent Plugin
+    needs: changes
+    if: needs.changes.outputs.pi_agent_plugin == 'true'
+    uses: ./.github/workflows/pi-agent-plugin-checks.yml
+    secrets: inherit
+
+  docs-llms-txt:
+    name: docs llms.txt
+    needs: changes
+    if: needs.changes.outputs.docs_llms_txt == 'true'
+    uses: ./.github/workflows/docs-llms-txt-check.yml
+    secrets: inherit
+
+  gate:
+    name: CI Gate
+    needs:
+      - changes
+      - python-sdk
+      - ts-sdk
+      - cli-python
+      - cli-node
+      - openclaw
+      - opencode-plugin
+      - pi-agent-plugin
+      - docs-llms-txt
+    if: always()
+    runs-on: ubuntu-latest
+    steps:
+      - name: Evaluate pipeline results
+        env:
+          NEEDS: ${{ toJSON(needs) }}
+        run: |
+          echo "$NEEDS" | jq -r 'to_entries[] | "\(.key): \(.value.result)"'
+          failed=$(echo "$NEEDS" | jq -r '[to_entries[] | select(.value.result == "failure" or .value.result == "cancelled") | .key] | join(", ")')
+          if [ -n "$failed" ]; then
+            echo "::error::Failing pipelines: $failed"
+            exit 1
+          fi
+          echo "All pipelines relevant to this change passed."

.github/workflows/ci.yml

@@ -1,9 +1,11 @@
 name: ci
 
+# On PRs this is invoked by ci-gate.yml (the single required check);
+# push-to-main runs remain standalone.
 on:
   push:
     branches: [main]
-  pull_request:
+  workflow_call:
 
 jobs:
   changelog_check:

.github/workflows/cli-node-cd.yml

@@ -1,13 +1,25 @@
 name: Publish @mem0/cli 📦 to npm
 
+# Dispatched by release.yml (Release Router) when a release tagged
+# cli-node-v* is published. Can also be dispatched manually to re-publish
+# a tag.
 on:
-  release:
-    types: [published]
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build and publish (e.g. cli-node-v0.2.0)'
+        required: true
+        type: string
+      prerelease:
+        description: 'Publish under the version preid dist-tag instead of latest'
+        required: false
+        type: boolean
+        default: false
 
 jobs:
   build-n-publish:
     name: Build and publish @mem0/cli 📦 to npm
-    if: startsWith(github.event.release.tag_name, 'cli-node-v')
+    if: startsWith(inputs.tag, 'cli-node-v')
     runs-on: ubuntu-latest
     permissions:
       id-token: write
@@ -16,6 +28,8 @@ jobs:
         working-directory: cli/node
     steps:
       - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
 
       - name: Install pnpm
         uses: pnpm/action-setup@v4
@@ -38,7 +52,7 @@ jobs:
 
       - name: Publish to npm
         run: |
-          if [ "${{ github.event.release.prerelease }}" = "true" ]; then
+          if [ "${{ inputs.prerelease }}" = "true" ]; then
             PREID=$(node -p "require('./package.json').version.split('-')[1].split('.')[0]")
             npx npm@latest publish --provenance --access public --tag "$PREID"
           else

.github/workflows/cli-node-ci.yml

@@ -1,5 +1,7 @@
 name: CLI Node CI
 
+# On PRs this is invoked by ci-gate.yml (the single required check);
+# push-to-main and manual runs remain standalone.
 on:
   workflow_dispatch:
   push:
@@ -7,10 +9,7 @@ on:
     paths:
       - 'cli/node/**'
       - '.github/workflows/cli-node-ci.yml'
-  pull_request:
-    paths:
-      - 'cli/node/**'
-      - '.github/workflows/cli-node-ci.yml'
+  workflow_call:
 
 jobs:
   lint:

.github/workflows/cli-python-cd.yml

@@ -1,13 +1,24 @@
 name: Publish mem0-cli 🐍 distributions 📦 to PyPI
 
+# Dispatched by release.yml (Release Router) when a release tagged cli-v* is
+# published. Can also be dispatched manually to re-publish a tag.
 on:
-  release:
-    types: [published]
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build and publish (e.g. cli-v0.2.0)'
+        required: true
+        type: string
+      prerelease:
+        description: 'Unused for PyPI (pre-releases are expressed in the version itself); accepted for router uniformity'
+        required: false
+        type: boolean
+        default: false
 
 jobs:
   build-n-publish:
     name: Build and publish mem0-cli 📦 to PyPI
-    if: startsWith(github.event.release.tag_name, 'cli-v')
+    if: startsWith(inputs.tag, 'cli-v')
     runs-on: ubuntu-latest
     permissions:
       id-token: write
@@ -16,6 +27,8 @@ jobs:
         working-directory: cli/python
     steps:
       - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
 
       - name: Set up Python
         uses: actions/setup-python@v5

.github/workflows/cli-python-ci.yml

@@ -1,5 +1,7 @@
 name: CLI Python CI
 
+# On PRs this is invoked by ci-gate.yml (the single required check);
+# push-to-main and manual runs remain standalone.
 on:
   workflow_dispatch:
   push:
@@ -7,10 +9,7 @@ on:
     paths:
       - 'cli/python/**'
       - '.github/workflows/cli-python-ci.yml'
-  pull_request:
-    paths:
-      - 'cli/python/**'
-      - '.github/workflows/cli-python-ci.yml'
+  workflow_call:
 
 jobs:
   lint:

.github/workflows/docs-llms-txt-check.yml

@@ -6,13 +6,10 @@ name: docs - llms.txt check
 #   python scripts/check-llms-txt-coverage.py           # read-only
 #   python scripts/check-llms-txt-coverage.py --write   # scaffold placeholders
 
+# On PRs this is invoked by ci-gate.yml (the single required check);
+# manual runs remain standalone.
 on:
-  pull_request:
-    paths:
-      - 'docs/**/*.mdx'
-      - 'docs/llms.txt'
-      - 'scripts/check-llms-txt-coverage.py'
-      - 'scripts/llms-txt-ignore.txt'
+  workflow_call:
   workflow_dispatch: {}
 
 permissions:

.github/workflows/openclaw-cd.yml

@@ -1,21 +1,35 @@
 name: Publish @mem0/openclaw-mem0 📦 to npm
 
+# Dispatched by release.yml (Release Router) when a release tagged
+# openclaw-v* is published. Can also be dispatched manually to re-publish
+# a tag.
 on:
-  release:
-    types: [published]
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build and publish (e.g. openclaw-v0.5.0)'
+        required: true
+        type: string
+      prerelease:
+        description: 'Publish under the version preid dist-tag instead of latest'
+        required: false
+        type: boolean
+        default: false
 
 jobs:
   build-n-publish:
     name: Build and publish @mem0/openclaw-mem0 📦 to npm
-    if: startsWith(github.event.release.tag_name, 'openclaw-v')
+    if: startsWith(inputs.tag, 'openclaw-v')
     runs-on: ubuntu-latest
     permissions:
       id-token: write
     defaults:
       run:
-        working-directory: openclaw
+        working-directory: integrations/openclaw
     steps:
       - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
 
       - name: Install pnpm
         uses: pnpm/action-setup@v4
@@ -28,7 +42,7 @@ jobs:
           node-version: '22'
           registry-url: 'https://registry.npmjs.org'
           cache: 'pnpm'
-          cache-dependency-path: openclaw/pnpm-lock.yaml
+          cache-dependency-path: integrations/openclaw/pnpm-lock.yaml
 
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
@@ -38,7 +52,7 @@ jobs:
 
       - name: Publish to npm
         run: |
-          if [ "${{ github.event.release.prerelease }}" = "true" ]; then
+          if [ "${{ inputs.prerelease }}" = "true" ]; then
             PREID=$(node -p "require('./package.json').version.split('-')[1].split('.')[0]")
             npx npm@latest publish --provenance --access public --tag "$PREID"
           else

.github/workflows/openclaw-checks.yml

@@ -1,16 +1,15 @@
 name: openclaw checks
 
+# On PRs this is invoked by ci-gate.yml (the single required check);
+# push-to-main and manual runs remain standalone.
 on:
   workflow_dispatch:
   push:
     branches: [main]
     paths:
-      - 'openclaw/**'
-      - '.github/workflows/openclaw-checks.yml'
-  pull_request:
-    paths:
-      - 'openclaw/**'
+      - 'integrations/openclaw/**'
       - '.github/workflows/openclaw-checks.yml'
+  workflow_call:
 
 jobs:
   lint:
@@ -28,13 +27,13 @@ jobs:
         with:
           node-version: 20
           cache: 'pnpm'
-          cache-dependency-path: openclaw/pnpm-lock.yaml
+          cache-dependency-path: integrations/openclaw/pnpm-lock.yaml
 
       - name: Install dependencies
-        run: cd openclaw && pnpm install --frozen-lockfile
+        run: cd integrations/openclaw && pnpm install --frozen-lockfile
 
       - name: Type check
-        run: cd openclaw && pnpm exec tsc --noEmit
+        run: cd integrations/openclaw && pnpm exec tsc --noEmit
 
   test:
     runs-on: ubuntu-latest
@@ -54,20 +53,20 @@ jobs:
         with:
           node-version: ${{ matrix.node-version }}
           cache: 'pnpm'
-          cache-dependency-path: openclaw/pnpm-lock.yaml
+          cache-dependency-path: integrations/openclaw/pnpm-lock.yaml
 
       - name: Install dependencies
-        run: cd openclaw && pnpm install --frozen-lockfile
+        run: cd integrations/openclaw && pnpm install --frozen-lockfile
 
       - name: Run tests with coverage
-        run: cd openclaw && pnpm exec vitest run --coverage
+        run: cd integrations/openclaw && pnpm exec vitest run --coverage
 
       - name: Upload coverage to Codecov
         if: matrix.node-version == 20
         uses: codecov/codecov-action@v4
         with:
           flags: openclaw
-          directory: openclaw/coverage
+          directory: integrations/openclaw/coverage
         env:
           CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
 
@@ -86,15 +85,15 @@ jobs:
         with:
           node-version: 20
           cache: 'pnpm'
-          cache-dependency-path: openclaw/pnpm-lock.yaml
+          cache-dependency-path: integrations/openclaw/pnpm-lock.yaml
 
       - name: Install dependencies
-        run: cd openclaw && pnpm install --frozen-lockfile
+        run: cd integrations/openclaw && pnpm install --frozen-lockfile
 
       - name: Build
-        run: cd openclaw && pnpm build
+        run: cd integrations/openclaw && pnpm build
 
       - name: Verify dist output exists
         run: |
-          test -f openclaw/dist/index.js || (echo "Build output missing: dist/index.js" && exit 1)
-          test -f openclaw/dist/index.d.ts || (echo "Build output missing: dist/index.d.ts" && exit 1)
+          test -f integrations/openclaw/dist/index.js || (echo "Build output missing: dist/index.js" && exit 1)
+          test -f integrations/openclaw/dist/index.d.ts || (echo "Build output missing: dist/index.d.ts" && exit 1)

.github/workflows/opencode-plugin-cd.yml

@@ -1,21 +1,35 @@
 name: Publish @mem0/opencode-plugin 📦 to npm
 
+# Dispatched by release.yml (Release Router) when a release tagged
+# opencode-v* is published. Can also be dispatched manually to re-publish
+# a tag.
 on:
-  release:
-    types: [published]
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build and publish (e.g. opencode-v0.2.0)'
+        required: true
+        type: string
+      prerelease:
+        description: 'Publish under the version preid dist-tag instead of latest'
+        required: false
+        type: boolean
+        default: false
 
 jobs:
   build-n-publish:
     name: Build and publish @mem0/opencode-plugin 📦 to npm
-    if: startsWith(github.event.release.tag_name, 'opencode-v')
+    if: startsWith(inputs.tag, 'opencode-v')
     runs-on: ubuntu-latest
     permissions:
       id-token: write
     defaults:
       run:
-        working-directory: mem0-plugin/.opencode-plugin
+        working-directory: integrations/mem0-plugin/.opencode-plugin
     steps:
       - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
 
       - name: Install Bun
         uses: oven-sh/setup-bun@v2
@@ -36,7 +50,7 @@ jobs:
 
       - name: Publish to npm
         run: |
-          if [ "${{ github.event.release.prerelease }}" = "true" ]; then
+          if [ "${{ inputs.prerelease }}" = "true" ]; then
             PREID=$(node -p "require('./package.json').version.split('-')[1].split('.')[0]")
             npx npm@latest publish --provenance --access public --tag "$PREID"
           else

.github/workflows/opencode-plugin-checks.yml

@@ -1,23 +1,22 @@
 name: opencode-plugin checks
 
+# On PRs this is invoked by ci-gate.yml (the single required check);
+# push-to-main and manual runs remain standalone.
 on:
   workflow_dispatch:
   push:
     branches: [main]
     paths:
-      - 'mem0-plugin/.opencode-plugin/**'
-      - '.github/workflows/opencode-plugin-checks.yml'
-  pull_request:
-    paths:
-      - 'mem0-plugin/.opencode-plugin/**'
+      - 'integrations/mem0-plugin/.opencode-plugin/**'
       - '.github/workflows/opencode-plugin-checks.yml'
+  workflow_call:
 
 jobs:
   build:
     runs-on: ubuntu-latest
     defaults:
       run:
-        working-directory: mem0-plugin/.opencode-plugin
+        working-directory: integrations/mem0-plugin/.opencode-plugin
     steps:
       - uses: actions/checkout@v4
 

.github/workflows/pi-agent-plugin-cd.yml

@@ -0,0 +1,60 @@
+name: Publish @mem0/pi-agent-plugin 📦 to npm
+
+# Dispatched by release.yml (Release Router) when a release tagged
+# pi-agent-v* is published. Can also be dispatched manually to re-publish
+# a tag.
+on:
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build and publish (e.g. pi-agent-v0.1.1)'
+        required: true
+        type: string
+      prerelease:
+        description: 'Publish under the version preid dist-tag instead of latest'
+        required: false
+        type: boolean
+        default: false
+
+jobs:
+  build-n-publish:
+    name: Build and publish @mem0/pi-agent-plugin 📦 to npm
+    if: startsWith(inputs.tag, 'pi-agent-v')
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+    defaults:
+      run:
+        working-directory: integrations/pi-agent-plugin
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Set up Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: '22'
+          registry-url: 'https://registry.npmjs.org'
+          cache: 'pnpm'
+          cache-dependency-path: integrations/pi-agent-plugin/pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Build
+        run: pnpm build
+
+      - name: Publish to npm
+        run: |
+          if [ "${{ inputs.prerelease }}" = "true" ]; then
+            PREID=$(node -p "require('./package.json').version.split('-')[1].split('.')[0]")
+            npx npm@latest publish --provenance --access public --tag "$PREID"
+          else
+            npx npm@latest publish --provenance --access public
+          fi

.github/workflows/pi-agent-plugin-checks.yml

@@ -0,0 +1,92 @@
+name: pi-agent-plugin checks
+
+# On PRs this is invoked by ci-gate.yml (the single required check);
+# push-to-main and manual runs remain standalone.
+on:
+  workflow_dispatch:
+  push:
+    branches: [main]
+    paths:
+      - 'integrations/pi-agent-plugin/**'
+      - '.github/workflows/pi-agent-plugin-checks.yml'
+  workflow_call:
+
+jobs:
+  lint:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: 'pnpm'
+          cache-dependency-path: integrations/pi-agent-plugin/pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: cd integrations/pi-agent-plugin && pnpm install --frozen-lockfile
+
+      - name: Type check
+        run: cd integrations/pi-agent-plugin && pnpm exec tsc --noEmit
+
+  test:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        node-version: [20, 22]
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Setup Node.js ${{ matrix.node-version }}
+        uses: actions/setup-node@v4
+        with:
+          node-version: ${{ matrix.node-version }}
+          cache: 'pnpm'
+          cache-dependency-path: integrations/pi-agent-plugin/pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: cd integrations/pi-agent-plugin && pnpm install --frozen-lockfile
+
+      - name: Run tests
+        run: cd integrations/pi-agent-plugin && pnpm exec vitest run
+
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install pnpm
+        uses: pnpm/action-setup@v4
+        with:
+          version: 9
+
+      - name: Setup Node.js
+        uses: actions/setup-node@v4
+        with:
+          node-version: 20
+          cache: 'pnpm'
+          cache-dependency-path: integrations/pi-agent-plugin/pnpm-lock.yaml
+
+      - name: Install dependencies
+        run: cd integrations/pi-agent-plugin && pnpm install --frozen-lockfile
+
+      - name: Build
+        run: cd integrations/pi-agent-plugin && pnpm build
+
+      - name: Verify dist output exists
+        run: |
+          test -f integrations/pi-agent-plugin/dist/index.js || (echo "Build output missing: dist/index.js" && exit 1)
+          test -f integrations/pi-agent-plugin/dist/index.d.ts || (echo "Build output missing: dist/index.d.ts" && exit 1)
+          test -f integrations/pi-agent-plugin/dist/entry.js || (echo "Build output missing: dist/entry.js" && exit 1)
+          test -f integrations/pi-agent-plugin/dist/entry.d.ts || (echo "Build output missing: dist/entry.d.ts" && exit 1)

.github/workflows/release.yml

@@ -0,0 +1,68 @@
+name: Release Router 🚦
+
+# Single entry point for all release publishing.
+#
+# Package CD workflows no longer listen to release events themselves — this
+# router inspects the release tag and dispatches only the matching pipeline,
+# so each release produces one routed run instead of one real run plus seven
+# skipped ones.
+#
+# Re-publishing a release (e.g. after fixing registry settings) does NOT
+# require deleting and recreating it anymore — manually dispatch the
+# package's CD workflow from the tag instead:
+#
+#   gh workflow run <package>-cd.yml --ref refs/tags/<tag> -f tag=<tag>
+#
+# Note: dispatching runs the workflow file as it exists at the given ref, so
+# this router can only dispatch tags created after the workflow_dispatch
+# conversion landed on main. For older tags, dispatch manually from main.
+
+on:
+  release:
+    types: [published]
+
+permissions:
+  actions: write
+
+jobs:
+  route:
+    name: Route ${{ github.event.release.tag_name }} to its CD pipeline
+    runs-on: ubuntu-latest
+    steps:
+      - name: Match tag prefix to CD workflow
+        id: match
+        env:
+          TAG: ${{ github.event.release.tag_name }}
+        run: |
+          # Specific package prefixes first; the bare v* (Python SDK) arm
+          # must stay last so prefixed tags that also start with 'v'
+          # (vercel-ai-v*) can never be routed to the Python pipeline.
+          case "$TAG" in
+            ts-v*)        workflow="ts-sdk-cd.yml" ;;
+            cli-node-v*)  workflow="cli-node-cd.yml" ;;
+            cli-v*)       workflow="cli-python-cd.yml" ;;
+            vercel-ai-v*) workflow="vercel-ai-cd.yml" ;;
+            openclaw-v*)  workflow="openclaw-cd.yml" ;;
+            opencode-v*)  workflow="opencode-plugin-cd.yml" ;;
+            pi-agent-v*)  workflow="pi-agent-plugin-cd.yml" ;;
+            v*)           workflow="cd.yml" ;;
+            *)
+              echo "::error::Release tag '$TAG' does not match any known package prefix — nothing will be published. See the tag prefix table in AGENTS.md."
+              exit 1
+              ;;
+          esac
+          echo "workflow=$workflow" >> "$GITHUB_OUTPUT"
+          echo ":outbox_tray: Routed \`$TAG\` → \`$workflow\`" >> "$GITHUB_STEP_SUMMARY"
+
+      - name: Dispatch ${{ steps.match.outputs.workflow }}
+        env:
+          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          TAG: ${{ github.event.release.tag_name }}
+        run: |
+          # --ref points at the tag so the dispatched run builds (and signs
+          # provenance for) the exact tagged commit.
+          gh workflow run "${{ steps.match.outputs.workflow }}" \
+            --repo "$GITHUB_REPOSITORY" \
+            --ref "refs/tags/$TAG" \
+            -f tag="$TAG" \
+            -f prerelease="${{ github.event.release.prerelease }}"

.github/workflows/ts-sdk-cd.yml

@@ -1,13 +1,24 @@
 name: Publish mem0ai 📦 to npm
 
+# Dispatched by release.yml (Release Router) when a release tagged ts-v* is
+# published. Can also be dispatched manually to re-publish a tag.
 on:
-  release:
-    types: [published]
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build and publish (e.g. ts-v2.1.0)'
+        required: true
+        type: string
+      prerelease:
+        description: 'Publish under the version preid dist-tag instead of latest'
+        required: false
+        type: boolean
+        default: false
 
 jobs:
   build-n-publish:
     name: Build and publish mem0ai 📦 to npm
-    if: startsWith(github.event.release.tag_name, 'ts-v')
+    if: startsWith(inputs.tag, 'ts-v')
     runs-on: ubuntu-latest
     permissions:
       id-token: write
@@ -16,6 +27,8 @@ jobs:
         working-directory: mem0-ts
     steps:
       - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
 
       - name: Install pnpm
         uses: pnpm/action-setup@v4
@@ -38,7 +51,7 @@ jobs:
 
       - name: Publish to npm
         run: |
-          if [ "${{ github.event.release.prerelease }}" = "true" ]; then
+          if [ "${{ inputs.prerelease }}" = "true" ]; then
             PREID=$(node -p "require('./package.json').version.split('-')[1].split('.')[0]")
             npx npm@latest publish --provenance --access public --tag "$PREID"
           else

.github/workflows/ts-sdk-ci.yml

@@ -1,14 +1,14 @@
 name: TypeScript SDK CI
 
+# On PRs this is invoked by ci-gate.yml (the single required check);
+# push-to-main runs remain standalone.
 on:
   push:
     branches: [main]
     paths:
       - 'mem0-ts/**'
       - '.github/workflows/ts-sdk-ci.yml'
-  pull_request:
-    paths:
-      - 'mem0-ts/**'
+  workflow_call:
 
 jobs:
   check_changes:

.github/workflows/vercel-ai-cd.yml

@@ -1,21 +1,35 @@
 name: Publish @mem0/vercel-ai-provider 📦 to npm
 
+# Dispatched by release.yml (Release Router) when a release tagged
+# vercel-ai-v* is published. Can also be dispatched manually to re-publish
+# a tag.
 on:
-  release:
-    types: [published]
+  workflow_dispatch:
+    inputs:
+      tag:
+        description: 'Release tag to build and publish (e.g. vercel-ai-v2.0.7)'
+        required: true
+        type: string
+      prerelease:
+        description: 'Publish under the version preid dist-tag instead of latest'
+        required: false
+        type: boolean
+        default: false
 
 jobs:
   build-n-publish:
     name: Build and publish @mem0/vercel-ai-provider 📦 to npm
-    if: startsWith(github.event.release.tag_name, 'vercel-ai-v')
+    if: startsWith(inputs.tag, 'vercel-ai-v')
     runs-on: ubuntu-latest
     permissions:
       id-token: write
     defaults:
       run:
-        working-directory: vercel-ai-sdk
+        working-directory: integrations/vercel-ai-sdk
     steps:
       - uses: actions/checkout@v4
+        with:
+          ref: ${{ inputs.tag }}
 
       - name: Install pnpm
         uses: pnpm/action-setup@v4
@@ -28,7 +42,7 @@ jobs:
           node-version: '22'
           registry-url: 'https://registry.npmjs.org'
           cache: 'pnpm'
-          cache-dependency-path: vercel-ai-sdk/pnpm-lock.yaml
+          cache-dependency-path: integrations/vercel-ai-sdk/pnpm-lock.yaml
 
       - name: Install dependencies
         run: pnpm install --frozen-lockfile
@@ -38,7 +52,7 @@ jobs:
 
       - name: Publish to npm
         run: |
-          if [ "${{ github.event.release.prerelease }}" = "true" ]; then
+          if [ "${{ inputs.prerelease }}" = "true" ]; then
             PREID=$(node -p "require('./package.json').version.split('-')[1].split('.')[0]")
             npx npm@latest publish --provenance --access public --tag "$PREID"
           else

.gitignore

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

.gitmodules

@@ -0,0 +1,4 @@
+[submodule "evaluation"]
+	path = evaluation
+	url = https://github.com/mem0ai/memory-benchmarks
+	branch = main

AGENTS.md

@@ -12,7 +12,7 @@ This file provides context for AI coding assistants (Claude Code, Cursor, GitHub
 
 ## Repository Structure
 
-This is a **polyglot monorepo** containing Python and TypeScript packages, CLIs, servers, plugins, documentation, and evaluation tooling.
+This is a **polyglot monorepo** containing Python and TypeScript packages, CLIs, servers, plugins, and documentation.
 
 ### Key Directories
 
@@ -22,17 +22,18 @@ This is a **polyglot monorepo** containing Python and TypeScript packages, CLIs,
 | `mem0-ts/` | TypeScript SDK (`mem0ai` on npm) — client + OSS memory |
 | `cli/python/` | Python CLI (`mem0-cli` on PyPI) — Typer-based, entry point `mem0` |
 | `cli/node/` | Node CLI (`@mem0/cli` on npm) — Commander-based, entry point `mem0` |
-| `vercel-ai-sdk/` | `@mem0/vercel-ai-provider` — Vercel AI SDK memory provider |
-| `openclaw/` | `@mem0/openclaw-mem0` — OpenClaw plugin for Claude Code / AI editors |
+| `integrations/` | **Agent & editor integrations**, one directory per integration (see "Adding a New Integration") |
+| `integrations/mem0-plugin/` | AI editor plugins (Claude Code, Cursor, Codex) — MCP server connection, lifecycle hooks, skills. Contains nested `.opencode-plugin/` (`@mem0/opencode-plugin`) |
+| `integrations/openclaw/` | `@mem0/openclaw-mem0` — OpenClaw plugin for Claude Code / AI editors |
+| `integrations/pi-agent-plugin/` | `@mem0/pi-agent-plugin` — Pi Agent plugin |
+| `integrations/vercel-ai-sdk/` | `@mem0/vercel-ai-provider` — Vercel AI SDK memory provider |
 | `server/` | FastAPI REST server for self-hosted Mem0 (Docker: FastAPI + PostgreSQL/pgvector + Neo4j) |
 | `openmemory/` | Self-hosted memory platform — `api/` (FastAPI + Alembic + MCP server) and `ui/` (Next.js 15 + React 19) |
-| `mem0-plugin/` | AI editor plugins (Claude Code, Cursor, Codex) — MCP server connection, lifecycle hooks, skills |
-| `skills/` | Claude Code skill definitions. Reference skills (SDK knowledge, always-on): `mem0/`, `mem0-cli/`, `mem0-vercel-ai-sdk/`. Pipeline skills (run on demand): `mem0-integrate/`, `mem0-test-integration/` |
+| `skills/` | Claude Code skill definitions. Reference skills (SDK knowledge, always-on): `mem0/`, `mem0-cli/`, `mem0-vercel-ai-sdk/`. Pipeline skills (run on demand): `mem0-integrate/`, `mem0-test-integration/`, `mem0-oss-to-platform/` |
 | `docs/` | Documentation site (Mintlify) |
 | `tests/` | Python SDK tests (pytest) |
-| `evaluation/` | Benchmarking framework — LOCOMO evals, experiment runner, score generation |
-| `examples/` | Sample projects — demo apps, Chrome extension, multi-agent patterns |
-| `cookbooks/` | Jupyter notebooks — customer support chatbot, AutoGen integration |
+| `evaluation/` | Submodule → [`mem0ai/memory-benchmarks`](https://github.com/mem0ai/memory-benchmarks) — benchmarking (LOCOMO, LongMemEval, BEAM) lives in that repo |
+| `examples/` | Sample projects & runnable demos — apps, Chrome extension, multi-agent patterns, and Jupyter notebooks (`notebooks/`) |
 | `pr-reviews/` | Pull request review materials |
 | `scripts/` | Repo-wide utility scripts (e.g., `check-llms-txt-coverage.py` for docs/llms.txt sync) |
 
@@ -49,8 +50,8 @@ mem0 (Python SDK)          mem0-ts (TypeScript SDK)
 
 cli/python/ ──▶ mem0ai (optional, for OSS mode)
 cli/node/   ──▶ mem0ai (npm, for API calls)
-vercel-ai-sdk/ ──▶ ai, @ai-sdk/* providers
-openclaw/   ──▶ mem0ai (npm)
+integrations/vercel-ai-sdk/ ──▶ ai, @ai-sdk/* providers
+integrations/openclaw/ ──▶ mem0ai (npm)
 ```
 
 ## Development Setup
@@ -73,8 +74,8 @@ pre-commit install                # install git hooks
 # TypeScript packages
 cd mem0-ts && pnpm install        # TS SDK
 cd cli/node && pnpm install       # Node CLI
-cd vercel-ai-sdk && pnpm install  # Vercel AI provider
-cd openclaw && pnpm install       # OpenClaw plugin
+cd integrations/vercel-ai-sdk && pnpm install  # Vercel AI provider
+cd integrations/openclaw && pnpm install       # OpenClaw plugin
 ```
 
 ## Build, Lint, and Test Commands
@@ -162,10 +163,10 @@ pnpm run dev                       # tsx src/index.ts (development)
 - **Test:** vitest (not jest)
 - **Framework:** Commander + Chalk + ora + cli-table3
 
-### Vercel AI SDK Provider (`vercel-ai-sdk/`)
+### Vercel AI SDK Provider (`integrations/vercel-ai-sdk/`)
 
 ```bash
-cd vercel-ai-sdk
+cd integrations/vercel-ai-sdk
 pnpm install
 pnpm run build                     # tsup
 pnpm run lint                      # eslint
@@ -180,10 +181,10 @@ pnpm run test:node                 # vitest (node runtime)
 - **Lint:** ESLint + Prettier
 - **Test:** jest + vitest (edge/node configs)
 
-### OpenClaw Plugin (`openclaw/`)
+### OpenClaw Plugin (`integrations/openclaw/`)
 
 ```bash
-cd openclaw
+cd integrations/openclaw
 pnpm install
 pnpm run build                     # tsup
 pnpm run test                      # vitest run
@@ -245,18 +246,19 @@ make docs                          # or: cd docs && mintlify dev
 - **API spec:** `docs/openapi.json`
 - **Structure:** `api-reference/`, `open-source/`, `platform/`, `integrations/`, `cookbooks/`, `core-concepts/`
 
-### Evaluation (`evaluation/`)
+### Evaluation / Benchmarking
+
+Benchmarking lives in the external [`mem0ai/memory-benchmarks`](https://github.com/mem0ai/memory-benchmarks) repo (LOCOMO + LongMemEval + BEAM). The in-repo `evaluation/` path is a **git submodule** pinned to that repo's `main` — populate it with `git submodule update --init evaluation` (or clone mem0 with `--recurse-submodules`), or clone the benchmarks repo standalone:
 
 ```bash
-cd evaluation
-make run-mem0-add                  # Run mem0 add experiments
-make run-mem0-search               # Run mem0 search experiments
-make run-mem0-plus-add             # With graph memory
-make run-mem0-plus-search          # With graph memory
-make run-rag                       # RAG baseline
-make run-full-context              # Full context baseline
-make run-langmem                   # LangMem comparison
-make run-openai                    # OpenAI comparison
+git clone https://github.com/mem0ai/memory-benchmarks.git
+cd memory-benchmarks
+pip install -r requirements.txt
+
+# Run a benchmark (Mem0 Cloud; use docker compose for OSS)
+python -m benchmarks.locomo.run --project-name my-test --backend cloud --mem0-api-key $MEM0_API_KEY
+python -m benchmarks.longmemeval.run --project-name my-test --backend cloud --mem0-api-key $MEM0_API_KEY --all-questions
+python -m benchmarks.beam.run --project-name my-test --backend cloud --mem0-api-key $MEM0_API_KEY --chat-sizes 100K --conversations 0-9
 ```
 
 ## Core APIs
@@ -342,8 +344,8 @@ make run-openai                    # OpenAI comparison
 |---------|--------|-----------|---------------|
 | `mem0-ts/` | — | Prettier | jest |
 | `cli/node/` | Biome | Biome | vitest |
-| `vercel-ai-sdk/` | ESLint | Prettier | jest + vitest |
-| `openclaw/` | — | — | vitest |
+| `integrations/vercel-ai-sdk/` | ESLint | Prettier | jest + vitest |
+| `integrations/openclaw/` | — | — | vitest |
 
 ### Type Checking
 
@@ -381,14 +383,14 @@ Model Context Protocol support in multiple places:
 
 - **Remote:** MCP server at `mcp.mem0.ai`
 - **Local:** MCP server in `openmemory/api/` (FastAPI-based)
-- **Plugin:** MCP tools in `mem0-plugin/` — 9 tools: `add_memory`, `search_memories`, `get_memories`, `get_memory`, `update_memory`, `delete_memory`, `delete_all_memories`, `delete_entities`, `list_entities`
+- **Plugin:** MCP tools in `integrations/mem0-plugin/` — 9 tools: `add_memory`, `search_memories`, `get_memories`, `get_memory`, `update_memory`, `delete_memory`, `delete_all_memories`, `delete_entities`, `list_entities`
 
 ### Plugin & Skills System
 
-- `mem0-plugin/` provides integrations for Claude Code, Cursor, and Codex via MCP server connections and lifecycle hooks for automatic memory capture.
+- `integrations/mem0-plugin/` provides integrations for Claude Code, Cursor, and Codex via MCP server connections and lifecycle hooks for automatic memory capture.
 - `skills/` contains structured skill definitions for AI agents, split into two categories:
   - **Reference skills** (always-on SDK knowledge): `mem0` (Python + TS SDKs, framework integrations), `mem0-cli` (terminal workflows), `mem0-vercel-ai-sdk` (Vercel AI provider).
-  - **Pipeline skills** (run on demand): `mem0-integrate` wires Mem0 into an existing repo via a TDD pipeline; `mem0-test-integration` verifies what the integrator produced on the same branch. The two are loosely coupled via `.mem0-integration/` artifacts.
+  - **Pipeline skills** (run on demand): `mem0-integrate` wires Mem0 into an existing repo via a TDD pipeline; `mem0-test-integration` verifies what the integrator produced on the same branch (the two are loosely coupled via `.mem0-integration/` artifacts); `mem0-oss-to-platform` migrates an existing project from Mem0 OSS to the hosted Platform SDK (plan, then execute on approval).
 
 ### Adding a New Provider
 
@@ -402,23 +404,44 @@ To add a new LLM, embedding, vector store, or reranker provider:
 6. Add any new dependencies to the appropriate optional group in `pyproject.toml` (never to core `dependencies`)
 7. Follow the exact pattern of existing providers in the same category — match method signatures, error handling, and config structure
 
+### Adding a New Integration
+
+Agent/editor integrations live under `integrations/`. Each is a self-contained directory (its own `package.json`/lockfile, build, and tests). To add one:
+
+1. Create `integrations/<name>/` and build the integration there.
+2. If it publishes to a registry, set `repository.directory: "integrations/<name>"` in its `package.json` so npm provenance links to the correct subdirectory.
+3. Add CI/CD under `.github/workflows/` (`<name>-checks.yml`, `<name>-cd.yml`). Use `integrations/<name>` in `paths:` triggers, `working-directory`, and `cache-dependency-path`. Register the release tag prefix in the `case` block in `release.yml` (keep the bare `v*` arm last). Keep workflow **filenames** stable — npm OIDC trusted publishing is pinned to repo + workflow filename.
+4. If it is a Claude Code / editor marketplace plugin, register its path in the five `marketplace.json` files (root + `.claude-plugin/`, `.cursor-plugin/`, `.codex-plugin/`, `.agents/plugins/`).
+5. Document it under `docs/integrations/` and add the page to `docs/docs.json` and `docs/llms.txt`.
+6. Add rows to the "Key Directories" table and the CI/CD tables in this file.
+
 ## CI/CD
 
 ### CI Workflows (automated testing)
 
-| Workflow | File | Triggers | Tests |
-|----------|------|----------|-------|
-| Python SDK | `ci.yml` | Push to main, PRs on `mem0/`, `tests/`, `pyproject.toml` | Ruff lint + pytest on Python 3.10, 3.11, 3.12 |
-| TypeScript SDK | `ts-sdk-ci.yml` | Push to main, PRs on `mem0-ts/` | Prettier + build + jest on Node 20, 22 |
-| Python CLI | `cli-python-ci.yml` | Push to `cli/python/`, PRs, manual | Ruff lint + pytest + hatch build on Python 3.10, 3.11, 3.12 |
-| Node CLI | `cli-node-ci.yml` | Push to `cli/node/`, PRs, manual | Biome lint + tsc + vitest + tsup build on Node 20, 22 |
-| OpenClaw | `openclaw-checks.yml` | Push to `openclaw/`, PRs, manual | tsc + vitest (with Codecov) + tsup build on Node 20, 22 |
-| OpenCode Plugin | `opencode-plugin-checks.yml` | Push to `mem0-plugin/.opencode-plugin/`, PRs, manual | Bun: tsc type-check + build + dist artifact check |
+PR testing is orchestrated by a single entry point: **`ci-gate.yml` (CI Gate)** runs on every PR, detects which packages changed, and invokes only the relevant package workflows below as reusable workflows (`workflow_call`). Its final **`CI Gate`** job aggregates the results (skipped pipelines pass; failed or cancelled ones fail) and is the **only status check that needs to be required** in branch protection. Package workflows keep their own push-to-main and manual triggers; their `pull_request` triggers moved into the gate's path filters.
+
+| Workflow | File | Standalone Triggers | Tests |
+|----------|------|---------------------|-------|
+| CI Gate | `ci-gate.yml` | All PRs | Routes to and aggregates the workflows below |
+| Python SDK | `ci.yml` | Push to main | Ruff lint + pytest on Python 3.10, 3.11, 3.12 |
+| TypeScript SDK | `ts-sdk-ci.yml` | Push to main (on `mem0-ts/`) | Prettier + build + jest on Node 20, 22 |
+| Python CLI | `cli-python-ci.yml` | Push to main (on `cli/python/`), manual | Ruff lint + pytest + hatch build on Python 3.10, 3.11, 3.12 |
+| Node CLI | `cli-node-ci.yml` | Push to main (on `cli/node/`), manual | Biome lint + tsc + vitest + tsup build on Node 20, 22 |
+| OpenClaw | `openclaw-checks.yml` | Push to main (on `integrations/openclaw/`), manual | tsc + vitest (with Codecov) + tsup build on Node 20, 22 |
+| OpenCode Plugin | `opencode-plugin-checks.yml` | Push to main (on `integrations/mem0-plugin/.opencode-plugin/`), manual | Bun: tsc type-check + build + dist artifact check |
+| Pi Agent Plugin | `pi-agent-plugin-checks.yml` | Push to main (on `integrations/pi-agent-plugin/`), manual | tsc + vitest + tsup build (dist artifact check) on Node 20, 22 |
+| docs llms.txt | `docs-llms-txt-check.yml` | Manual | `docs/llms.txt` coverage check |
+
+When adding a new package CI workflow: give it `workflow_call` (plus `push`/`workflow_dispatch` as needed, but no `pull_request` trigger), then register it in `ci-gate.yml` — a path filter under the `changes` job, a call job, and an entry in the gate job's `needs` list.
 
 ### CD Workflows (automated publishing)
 
+Publishing is routed through a single entry point: **`release.yml` (Release Router)** is the only workflow that listens to `release: published` events. It matches the release tag prefix and dispatches the corresponding package workflow via `workflow_dispatch`, so each release produces exactly one routed run (no skipped runs from the other pipelines).
+
 | Workflow | File | Tag Prefix | Target |
 |----------|------|------------|--------|
+| Release Router | `release.yml` | (all releases) | dispatches the matching workflow below |
 | Python SDK | `cd.yml` | `v*` | PyPI (`mem0ai`) |
 | TypeScript SDK | `ts-sdk-cd.yml` | `ts-v*` | npm (`mem0ai`) |
 | Python CLI | `cli-python-cd.yml` | `cli-v*` | PyPI (`mem0-cli`) |
@@ -426,9 +449,13 @@ To add a new LLM, embedding, vector store, or reranker provider:
 | Vercel AI SDK | `vercel-ai-cd.yml` | `vercel-ai-v*` | npm (`@mem0/vercel-ai-provider`) |
 | OpenClaw | `openclaw-cd.yml` | `openclaw-v*` | npm (`@mem0/openclaw-mem0`) |
 | OpenCode Plugin | `opencode-plugin-cd.yml` | `opencode-v*` | npm (`@mem0/opencode-plugin`) |
+| Pi Agent Plugin | `pi-agent-plugin-cd.yml` | `pi-agent-v*` | npm (`@mem0/pi-agent-plugin`) |
 
+- Package CD workflows are `workflow_dispatch`-only (inputs: `tag`, `prerelease`); they check out and build the given tag. Registry trusted-publisher settings stay pinned to each package's own workflow filename.
 - All publishing uses **OIDC trusted publishing** — no tokens or secrets required.
 - First publish of a new npm package must be done manually; OIDC works for subsequent versions.
+- To re-publish a release (e.g. after a registry settings fix), do **not** delete/recreate the GitHub release — manually dispatch the package workflow instead: `gh workflow run <package>-cd.yml --ref refs/tags/<tag> -f tag=<tag>`.
+- When adding a new package: add its CD workflow (`workflow_dispatch` with `tag`/`prerelease` inputs), then register its tag prefix in the `case` block in `release.yml`. Keep the bare `v*` arm last.
 
 ### Utility Workflows
 

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!

LLM.md

@@ -1026,7 +1026,8 @@ def get_user_preferences(user_id: str):
 ### AutoGen Integration
 
 ```python
-from cookbooks.helper.mem0_teachability import Mem0Teachability
+# Mem0Teachability lives in examples/notebooks/helper/ — see examples/notebooks/mem0-autogen.ipynb
+from helper.mem0_teachability import Mem0Teachability
 from mem0 import Memory
 
 # Add memory capability to AutoGen agents

README.md

@@ -186,9 +186,10 @@ npx skills add https://github.com/mem0ai/mem0 --skill mem0-vercel-ai-sdk
 ```bash
 npx skills add https://github.com/mem0ai/mem0 --skill mem0-integrate
 npx skills add https://github.com/mem0ai/mem0 --skill mem0-test-integration
+npx skills add https://github.com/mem0ai/mem0 --skill mem0-oss-to-platform
 ```
 
-Use `/mem0-integrate` to wire Mem0 into an existing repo via a test-first pipeline, then `/mem0-test-integration` to verify. See the [skills catalog](./skills/) or [Vibecoding with Mem0](https://docs.mem0.ai/vibecoding) for the full picture.
+Use `/mem0-integrate` to wire Mem0 into an existing repo via a test-first pipeline, then `/mem0-test-integration` to verify. Use `/mem0-oss-to-platform` to migrate an existing project from Mem0 OSS to the hosted Platform SDK. See the [skills catalog](./skills/) or [Vibecoding with Mem0](https://docs.mem0.ai/vibecoding) for the full picture.
 
 ### Basic Usage
 

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 +5,30 @@ 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
+
+- Pinned transitive dependencies via pnpm overrides to remediate high-severity CVEs:
+  - `jws` → 4.0.1 (CVE-2025-65945)
+  - `langsmith` → ^0.6.0 (CVE-2026-45134)
+  - `tar-fs` → ^2.1.4 (CVE-2025-48387, CVE-2025-59343)
+  - `picomatch` → ^2.3.2 (CVE-2026-33671)
+  - `minimatch` → ^3.1.3 / ^5.1.8 / ^9.0.7 (CVE-2026-27903, CVE-2026-27904, CVE-2026-26996)
+  - `path-to-regexp` → ^8.4.0 (CVE-2026-4926)
+  - `rollup` → ^4.59.0 (CVE-2026-27606)
+  - `glob` → ^10.5.0 (CVE-2025-64756)
+  - `@modelcontextprotocol/sdk` → ^1.25.4 (CVE-2025-66414, CVE-2026-0621)
+
 ## [0.2.7] — 2026-05-20
 
 ### Added

cli/node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mem0/cli",
-  "version": "0.2.7",
+  "version": "0.2.9",
   "description": "The official CLI for mem0 — the memory layer for AI agents",
   "type": "module",
   "bin": {
@@ -40,8 +40,19 @@
     "typescript": "^5.4.0",
     "tsup": "^8.0.0",
     "tsx": "^4.7.0",
-    "vitest": "^1.5.0",
+    "vite": "^6.0.0",
+    "vitest": "^4.1.0",
     "@biomejs/biome": "^1.7.0",
     "@types/node": "^20.0.0"
+  },
+  "pnpm": {
+    "overrides": {
+      "jws@4.0.0": "4.0.1",
+      "langsmith@<0.6.0": "^0.6.0",
+      "tar-fs@>=2.0.0 <2.1.4": "^2.1.4",
+      "picomatch@<2.3.2": "^2.3.2",
+      "postcss@<8.5.10": ">=8.5.10",
+      "esbuild": ">=0.28.1"
+    }
   }
 }

cli/node/pnpm-workspace.yaml

@@ -0,0 +1,14 @@
+packages:
+  - '.'
+
+onlyBuiltDependencies:
+  - "@biomejs/biome"
+  - esbuild
+
+overrides:
+  jws@4.0.0: 4.0.1
+  langsmith@<0.6.0: ^0.6.0
+  tar-fs@>=2.0.0 <2.1.4: ^2.1.4
+  picomatch@<2.3.2: ^2.3.2
+  "postcss@<8.5.10": ">=8.5.10"
+  "esbuild": ">=0.28.1"

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/node/vitest.config.ts

@@ -8,4 +8,10 @@ export default defineConfig({
 	define: {
 		__CLI_VERSION__: JSON.stringify(pkg.version),
 	},
+	test: {
+		// Integration tests spawn the CLI via `npx tsx` (15s subprocess
+		// timeout); the first spawn in a file pays a cold-start cost that can
+		// exceed vitest's 5s default on CI runners.
+		testTimeout: 30_000,
+	},
 });

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_agent_mode.py

@@ -32,12 +32,13 @@ def _run(args: list[str], home_dir: str | None = None) -> subprocess.CompletedPr
         if key.startswith("MEM0_"):
             del env[key]
     env.pop("FORCE_COLOR", None)
+    env["PYTHONIOENCODING"] = "utf-8"
     if home_dir:
         env["HOME"] = home_dir
     result = subprocess.run(
         [sys.executable, "-m", "mem0_cli", *args],
         capture_output=True,
-        text=True,
+        encoding="utf-8",
         env=env,
         timeout=15,
     )
@@ -99,12 +100,13 @@ class TestArgvPreprocessing:
         result = subprocess.run(
             [sys.executable, "-m", "mem0_cli", "init", "--agent"],
             capture_output=True,
-            text=True,
+            encoding="utf-8",
             env={
                 **{k: v for k, v in os.environ.items() if not k.startswith("MEM0_")},
                 "HOME": clean_home,
                 "MEM0_BASE_URL": "http://127.0.0.1:1",  # blackhole
                 "FORCE_COLOR": "0",
+                "PYTHONIOENCODING": "utf-8",
             },
             timeout=15,
         )
@@ -133,12 +135,13 @@ class TestJsonEnvelopeParity:
         result = subprocess.run(
             [sys.executable, "-m", "mem0_cli", "init", "--agent", "--json"],
             capture_output=True,
-            text=True,
+            encoding="utf-8",
             env={
                 **{k: v for k, v in os.environ.items() if not k.startswith("MEM0_")},
                 "HOME": clean_home,
                 "MEM0_BASE_URL": "http://127.0.0.1:1",
                 "FORCE_COLOR": "0",
+                "PYTHONIOENCODING": "utf-8",
             },
             timeout=15,
         )

cli/python/tests/test_cli_integration.py

@@ -49,6 +49,7 @@ def _run(
         if key.startswith("MEM0_"):
             del env[key]
     env.pop("FORCE_COLOR", None)
+    env["PYTHONIOENCODING"] = "utf-8"
     if home_dir:
         env["HOME"] = home_dir
     if env_override:
@@ -56,7 +57,7 @@ def _run(
     result = subprocess.run(
         [sys.executable, "-m", "mem0_cli", *args],
         capture_output=True,
-        text=True,
+        encoding="utf-8",
         env=env,
     )
     return subprocess.CompletedProcess(

cli/python/tests/test_commands.py

@@ -8,8 +8,8 @@ from io import StringIO
 from unittest.mock import patch
 
 import pytest
-from click.exceptions import Exit as ClickExit
 from rich.console import Console
+from typer import Exit as TyperExit
 
 from mem0_cli.commands.config_cmd import (
     cmd_config_get,
@@ -181,7 +181,7 @@ class TestAddCommand:
             patch("mem0_cli.commands.memory.console", console),
             patch("mem0_cli.commands.memory.err_console", err_console),
             patch("mem0_cli.commands.memory._stdin_is_piped", return_value=False),
-            pytest.raises((SystemExit, ClickExit)),
+            pytest.raises((SystemExit, TyperExit)),
         ):
             cmd_add(
                 mock_backend,
@@ -206,7 +206,7 @@ class TestAddCommand:
         with (
             patch("mem0_cli.commands.memory.console", console),
             patch("mem0_cli.commands.memory.err_console", err_console),
-            pytest.raises((SystemExit, ClickExit)),
+            pytest.raises((SystemExit, TyperExit)),
         ):
             cmd_add(
                 mock_backend,
@@ -764,7 +764,7 @@ class TestImportCommand:
         with (
             patch("mem0_cli.commands.utils.console", console),
             patch("mem0_cli.commands.utils.err_console", err_console),
-            pytest.raises((SystemExit, ClickExit)),
+            pytest.raises((SystemExit, TyperExit)),
         ):
             cmd_import(mock_backend, "/nonexistent/file.json", user_id=None, agent_id=None)
 
@@ -801,7 +801,7 @@ class TestEntitiesListCommand:
         with (
             patch("mem0_cli.commands.entities.console", console),
             patch("mem0_cli.commands.entities.err_console", err_console),
-            pytest.raises((SystemExit, ClickExit)),
+            pytest.raises((SystemExit, TyperExit)),
         ):
             cmd_entities_list(mock_backend, "invalid", output="table")
 
@@ -944,7 +944,7 @@ class TestEntitiesDeleteCommand:
         with (
             patch("mem0_cli.commands.entities.console", console),
             patch("mem0_cli.commands.entities.err_console", err_console),
-            pytest.raises((SystemExit, ClickExit)),
+            pytest.raises((SystemExit, TyperExit)),
         ):
             cmd_entities_delete(
                 mock_backend,
@@ -1308,7 +1308,7 @@ class TestAgentMode:
             patch("mem0_cli.commands.memory.console", console),
             patch("mem0_cli.commands.memory.err_console", err_console),
             patch("sys.stdout", captured_stdout),
-            pytest.raises((SystemExit, ClickExit)),
+            pytest.raises((SystemExit, TyperExit)),
         ):
             cmd_get(mock_backend, "bad-id", output="text")
 

cli/python/tests/test_config.py

@@ -67,7 +67,8 @@ class TestConfig:
         from mem0_cli.config import CONFIG_FILE
 
         mode = os.stat(CONFIG_FILE).st_mode & 0o777
-        assert mode == 0o600
+        if os.name != "nt":
+            assert mode == 0o600
 
     def test_defaults_save_and_load(self, isolate_config):
         config = Mem0Config()

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/openclaw.mdx

@@ -4,6 +4,39 @@ description: "Release notes for the OpenClaw plugin and agent harness."
 mode: "wide"
 ---
 
+<Update label="2026-06-12" description="v1.0.13">
+
+**Fixes:**
+- **Custom categories payload:** `customCategories` (a `Record<string, string>` map) is now converted via the new `customCategoryMapToList()` helper into the `Array<Record<string, string>>` shape the Mem0 SDK expects on `add` calls — previously the raw object was passed as `custom_categories` and silently ignored ([#5345](https://github.com/mem0ai/mem0/pull/5345))
+- **Skip runtime setup during metadata registration:** `register()` now detects `registrationMode === "cli-metadata"`, registers only the CLI commands, and returns early — avoiding backend initialization, service/tool registration, and hook installation during OpenClaw's metadata-only registration pass ([#5383](https://github.com/mem0ai/mem0/pull/5383))
+
+**Security:**
+- Bumped `mem0ai` from `3.0.3` to `3.0.7` (latest Node SDK) — includes the transitive axios CVE remediation shipped in `3.0.6` ([#5460](https://github.com/mem0ai/mem0/pull/5460))
+- Added pnpm override `uuid@<11.1.1` → `>=11.1.1` to resolve an open MEDIUM Dependabot alert ([#5489](https://github.com/mem0ai/mem0/pull/5489))
+
+**Improvements:**
+- **Repo consolidation:** Plugin moved from repo-root `openclaw/` to `integrations/openclaw/`; `package.json` `repository.directory` updated to match so npm provenance links to the correct subdirectory ([#5491](https://github.com/mem0ai/mem0/pull/5491))
+
+**Tests:**
+- Added `customCategoryMapToList` unit tests and a `PlatformProvider` test asserting `custom_categories` is passed to the Mem0 SDK as a list ([#5345](https://github.com/mem0ai/mem0/pull/5345))
+- Added a regression test asserting `cli-metadata` registration registers only CLI commands and triggers no runtime side effects ([#5383](https://github.com/mem0ai/mem0/pull/5383))
+
+</Update>
+
+<Update label="2026-06-02" description="v1.0.12">
+
+**Docs:**
+- **Agent Mode onboarding:** README now documents an autonomous setup path for AI agents — `mem0 init --agent --json` mints an evaluation Mem0 API key with no email, OTP, or browser and exports it as `MEM0_API_KEY` for `openclaw mem0 init`; a human owner can later run `mem0 init --email <email>` to claim ownership without disrupting the agent ([#5123](https://github.com/mem0ai/mem0/pull/5123))
+
+**Security:**
+- Added pnpm overrides to remediate advisories in transitive dependencies: `langsmith@<0.6.0` → `^0.6.0`, `picomatch@<2.3.2` → `^2.3.2`, `vite` → `^8.0.5`, and `@qdrant/js-client-rest` → `^1.18.0` ([#5294](https://github.com/mem0ai/mem0/pull/5294))
+
+**Dependencies:**
+- Bumped `mem0ai` from `3.0.2` to `3.0.3` ([#5212](https://github.com/mem0ai/mem0/pull/5212))
+- Bumped dev dependencies `@vitest/coverage-v8` and `vitest` from `^4.0.18` to `^4.1.7`; added `vite@^8.0.5` and `@qdrant/js-client-rest@^1.18.0` ([#5294](https://github.com/mem0ai/mem0/pull/5294))
+
+</Update>
+
 <Update label="2026-04-29" description="v1.0.11">
 
 **New Features:**

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 +7,136 @@ 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:**
+- **Memory:** Add a contextual OSS-to-Platform notices system that surfaces occasional, situation-aware messages (first run, scale/performance thresholds, slow queries, and when temporal/decay features are relevant) pointing to the corresponding Mem0 Platform capabilities; disable via `MEM0_TELEMETRY=false` ([#5494](https://github.com/mem0ai/mem0/pull/5494))
+
+**Bug Fixes:**
+- **Memory:** Prevent a crash in `parse_vision_messages` when vision support is disabled ([#5487](https://github.com/mem0ai/mem0/pull/5487))
+- **Vector Stores:** Expose the `https` option on the Qdrant vector store configuration so TLS endpoints can be targeted explicitly ([#5380](https://github.com/mem0ai/mem0/pull/5380))
+- **Vector Stores:** Use valid S3 Vectors entity index names, fixing index operations that failed on invalid names ([#5416](https://github.com/mem0ai/mem0/pull/5416))
+- **Vector Stores:** Fix `search()` crashing with a `TypeError` in the LangChain vector store when a result score is `None` ([#5072](https://github.com/mem0ai/mem0/pull/5072))
+- **Vector Stores:** Use `is not None` instead of a truthiness check for vector/payload in the PGVector `update()` path, so valid empty/zero values are no longer skipped ([#5488](https://github.com/mem0ai/mem0/pull/5488))
+- **Vector Stores:** Index the Valkey `memory` field as `TEXT` rather than `TAG` so full-text search behaves correctly ([#5443](https://github.com/mem0ai/mem0/pull/5443))
+- **Vector Stores:** Implement `$not` filter support in the ChromaDB vector store ([#5485](https://github.com/mem0ai/mem0/pull/5485))
+
+</Update>
+
+<Update label="2026-06-10" description="v2.0.5">
+
+**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_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))
+- **Memory:** Parallelize entity boost searches in `Memory.search()` and `AsyncMemory.search()`. Previously up to 8 entities were embedded and queried sequentially (16 serial round-trips with remote embedders); all entity lookups now run concurrently, eliminating multi-second latency on entity-rich queries ([#5377](https://github.com/mem0ai/mem0/pull/5377))
+- **Memory:** Reject empty or whitespace-only queries in `Memory.search()`, `AsyncMemory.search()`, `MemoryClient.search()`, and `AsyncMemoryClient.search()` before any embedding or API call is made. Also strips leading/trailing whitespace from valid queries ([#5258](https://github.com/mem0ai/mem0/pull/5258))
+- **LLMs:** Add `is_reasoning_model: Optional[bool]` override to `BaseLlmConfig` (surfaced on `OpenAILlmConfig` and `AzureOpenAILlmConfig`). Fixes silent zero-extraction when using Azure deployments with versioned `gpt-5.x` names that the automatic name-based heuristic cannot recognize ([#5327](https://github.com/mem0ai/mem0/pull/5327))
+- **LLMs:** Fix xAI LLM provider: add `XAIConfig` with `xai_base_url`, forward `tools`/`tool_choice` in `generate_response()`, and parse `tool_calls` in the response. Previously the provider raised `AttributeError` at init and silently dropped tool results ([#5190](https://github.com/mem0ai/mem0/pull/5190))
+- **Vector Stores:** Fix PGVector `ConnectionPool` hang in Docker Compose environments where the app container starts before Postgres is DNS-resolvable — switched to `open=False` to avoid blocking constructor or silent zombie pool ([#5155](https://github.com/mem0ai/mem0/pull/5155))
+- **Vector Stores:** Fix PGVector `sslmode` handling for PostgreSQL URIs — the `sslmode` query parameter is now correctly extracted and forwarded when building the async connection pool ([#5308](https://github.com/mem0ai/mem0/pull/5308))
+- **Vector Stores:** Fix S3 Vectors `list()` not applying metadata filters — filtering is now done client-side after fetching, with pagination preserved and `top_k` applied after filtering to prevent pre-truncation of matching rows ([#5018](https://github.com/mem0ai/mem0/pull/5018))
+- **Vector Stores:** Fix Upstash Vector `search()` routing all queries to the default namespace — `namespace` is now passed as a top-level keyword argument to `query_many()` instead of inside the per-query dict where it was silently ignored ([#5202](https://github.com/mem0ai/mem0/pull/5202))
+- **Core:** Replace mutable default arguments with `None` sentinels in embedder configs and the proxy module, preventing cross-request state contamination ([#5302](https://github.com/mem0ai/mem0/pull/5302))
+
+</Update>
+
 <Update label="2026-05-27" description="v2.0.4">
 
 **New Features:**
@@ -78,8 +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))
 
@@ -99,7 +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>
 
@@ -939,6 +1069,75 @@ See the [OSS v1 to v2 migration guide](https://docs.mem0.ai/migration/oss-v1-to-
 </Tab>
 
 <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:**
+- **Memory:** Add a contextual OSS-to-Platform notices system that surfaces occasional, situation-aware messages (first run, scale/performance thresholds, slow queries, and when temporal/decay features are relevant) pointing to the corresponding Mem0 Platform capabilities; disable via `MEM0_TELEMETRY=false` ([#5494](https://github.com/mem0ai/mem0/pull/5494))
+
+**Security:**
+- **Dependencies:** Upgrade `@langchain/community` to `^1.1.18` to remediate CVE-2026-27795 and CVE-2026-26019 ([#5510](https://github.com/mem0ai/mem0/pull/5510))
+- **Dependencies:** Resolve all open MEDIUM Dependabot alerts via pnpm overrides ([#5489](https://github.com/mem0ai/mem0/pull/5489))
+
+</Update>
+
+<Update label="2026-06-10" description="v3.0.7">
+
+**New Features:**
+- **Embeddings:** Add `LMStudioEmbedding` provider for local embeddings via the LM Studio server ([#5377](https://github.com/mem0ai/mem0/pull/5377))
+- **Memory:** Add opt-in `explain: true` option to `Memory.search()`. When enabled, each result includes a `scoreBreakdown` object with `semantic`, `keyword`, `entityBoost`, and `temporalBoost` fields so callers can inspect and tune retrieval ranking ([#5102](https://github.com/mem0ai/mem0/pull/5102))
+
+**Bug Fixes:**
+- **Memory:** Parallelize entity boost searches in `Memory.search()`. All entity embed + store lookups now run concurrently instead of sequentially, eliminating multi-second latency on entity-rich queries with remote embedding providers ([#5377](https://github.com/mem0ai/mem0/pull/5377))
+- **Vector Stores:** Normalize similarity scores to `[0, 1]` (higher = better) — fixed score inversion in the Redis vector store adapter ([#5391](https://github.com/mem0ai/mem0/pull/5391))
+- **Embeddings:** Request `encoding_format: "float"` from the OpenAI embedder in both `embed()` and `embedBatch()`. Fixes incorrect vector dimensions when using OpenAI-compatible proxies that default to base64 encoding ([#5170](https://github.com/mem0ai/mem0/pull/5170))
+
+</Update>
+
+<Update label="2026-06-01" description="v3.0.6">
+
+**Security:**
+- **Dependencies:** Bumped `axios` to `^1.16.0` to remediate high-severity prototype-pollution CVEs (credential theft, MITM, DoS). Pinned transitive dependencies via pnpm overrides: `jws` → 4.0.1 (CVE-2025-65945), `langsmith` → ^0.6.0 (CVE-2026-45134), `tar-fs` → ^2.1.4 (CVE-2025-48387, CVE-2025-59343), `picomatch` → ^2.3.2 (CVE-2026-33671), `minimatch` → ^3.1.3 / ^5.1.8 / ^9.0.7 (CVE-2026-27903, CVE-2026-27904, CVE-2026-26996), `path-to-regexp` → ^8.4.0 (CVE-2026-4926), `rollup` → ^4.59.0 (CVE-2026-27606), `glob` → ^10.5.0 (CVE-2025-64756), `@modelcontextprotocol/sdk` → ^1.25.4 (CVE-2025-66414, CVE-2026-0621)
+
+</Update>
+
 <Update label="2026-05-27" description="v3.0.5">
 
 **New Features:**
@@ -998,7 +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
@@ -1352,6 +1551,13 @@ See the [TypeScript SDK migration guide](https://docs.mem0.ai/migration/ts-v2-to
 
 <Tab title="CLI">
 
+<Update label="2026-06-01" description="Node v0.2.8">
+
+**Security:**
+- **Dependencies:** Pinned transitive dependencies via pnpm overrides to remediate high-severity CVEs: `jws` → 4.0.1 (CVE-2025-65945), `langsmith` → ^0.6.0 (CVE-2026-45134), `tar-fs` → ^2.1.4 (CVE-2025-48387, CVE-2025-59343), `picomatch` → ^2.3.2 (CVE-2026-33671), `minimatch` → ^3.1.3 / ^5.1.8 / ^9.0.7 (CVE-2026-27903, CVE-2026-27904, CVE-2026-26996), `path-to-regexp` → ^8.4.0 (CVE-2026-4926), `rollup` → ^4.59.0 (CVE-2026-27606), `glob` → ^10.5.0 (CVE-2025-64756), `@modelcontextprotocol/sdk` → ^1.25.4 (CVE-2025-66414, CVE-2026-0621)
+
+</Update>
+
 <Update label="2026-05-16" description="Python v0.2.6 / Node v0.2.6">
 
 **Bug Fixes:**
@@ -1468,6 +1674,43 @@ A full-featured command-line interface for Mem0, available in both Python and No
 
 <Tab title="Plugins">
 
+<Update label="2026-06-01" description="openclaw-mem0 v1.0.12">
+
+**Security:**
+- **Dependencies:** Pinned transitive dependencies via pnpm overrides to remediate high-severity CVEs: `protobufjs` → ^7.5.5, `vite` → ^8.0.5, `langsmith` → ^0.6.0 (CVE-2026-45134), `picomatch` → ^2.3.2 (CVE-2026-33671), `@qdrant/js-client-rest` → ^1.18.0
+
+</Update>
+
+<Update label="2026-06-10" description="Vercel AI SDK v3.0.0">
+
+**Major Release** — Migrated to Vercel AI SDK v6 (`LanguageModelV3` / `ProviderV3`) and Mem0 v3 API.
+
+**Breaking Changes:**
+- **AI SDK v6:** Upgraded from AI SDK v5 (`LanguageModelV2`) to v6 (`LanguageModelV3`). Users must upgrade `ai` to `^6.0.199` and all `@ai-sdk/*` provider packages to `^3.x` ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+- **Mem0 v3 API:** Memory endpoints migrated from `/v1/memories/` and `/v2/memories/search/` to `/v3/memories/add/` and `/v3/memories/search/`. Entity IDs (`user_id`, `agent_id`, `run_id`) now go inside the `filters` object for search requests ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+- **Graph memory removed:** All `enable_graph`, graph prompts, and relation-extraction code removed. Graph memory is now a project-level setting on the Platform ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+- **Deprecated params removed:** `org_id`, `project_id`, `org_name`, `project_name`, `output_format`, `filter_memories`, `async_mode`, `enable_graph`, `version`, `api_version` removed from `Mem0ConfigSettings` ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+
+**New Features:**
+- **V3 provider contract:** `specificationVersion: 'v3'`, `supportedUrls` property, V3 content array in `doGenerate`, V3 stream lifecycle events in `doStream` ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+- **Mem0 source in responses:** Memories are attached as a `source` in `generateText`/`streamText` responses with `providerMetadata.mem0.memories` for programmatic access ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+
+**Bug Fixes:**
+- **Async memory storage:** `addMemories` is now properly `await`ed — memories no longer silently fail to store ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+- **Prompt mutation:** Prompt array is now cloned before injecting memory context, preventing side effects on the caller's array ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+- **Null guard on content:** `doGenerate` guards against null `content` from upstream providers ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+- **Stream response:** `doStream` now returns the full `LanguageModelV3StreamResult` object preserving all V3 fields ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+- **Response normalization:** `getMemories` and `retrieveMemories` now handle both array and `{results: [...]}` envelope responses from the v3 API ([#4741](https://github.com/mem0ai/mem0/pull/4741))
+
+</Update>
+
+<Update label="2026-06-01" description="Vercel AI SDK v2.0.6">
+
+**Security:**
+- **Dependencies:** Pinned transitive dependencies via pnpm overrides to remediate high-severity CVEs: `glob` → ^10.5.0 (CVE-2025-64756), `minimatch` → ^3.1.3 / ^5.1.8 / ^9.0.7 (CVE-2026-27903, CVE-2026-27904, CVE-2026-26996), `picomatch` → ^2.3.2 (CVE-2026-33671), `rollup` → ^4.59.0 (CVE-2026-27606)
+
+</Update>
+
 <Update label="2026-04-02" description="mem0-plugin v1.0.0">
 
 **Mem0 Plugin for Claude Code, Cursor, and Codex**

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

@@ -0,0 +1,153 @@
+---
+title: "Neon"
+description: "Use Neon as a vector store in Mem0, powered by PostgreSQL and pgvector."
+---
+
+Use [Neon](https://neon.com/) as a vector store in Mem0, powered by PostgreSQL and the
+[pgvector extension](https://neon.com/docs/extensions/pgvector).
+
+Neon is a serverless Postgres platform. Since Mem0 supports Postgres through the
+`pgvector` provider, Neon can be used with a standard Postgres connection string.
+
+## Usage
+
+<CodeGroup>
+```python Python
+import os
+
+from dotenv import load_dotenv
+from mem0 import Memory
+
+load_dotenv()
+
+config = {
+    "vector_store": {
+        "provider": "pgvector",
+        "config": {
+            "connection_string": os.environ["DATABASE_URL"],
+            "collection_name": "memories",
+            "embedding_model_dims": 1536,
+            "hnsw": True,
+        },
+    },
+}
+
+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="alice", metadata={"category": "movies"})
+
+results = m.search(
+    "What movies should I recommend?",
+    filters={"user_id": "alice"},
+)
+
+print(results)
+```
+
+```typescript TypeScript
+import "dotenv/config";
+import { Memory } from "mem0ai/oss";
+
+const m = new Memory({
+  vectorStore: {
+    provider: "pgvector",
+    config: {
+      connectionString: process.env.DATABASE_URL!,
+      ssl: {
+        rejectUnauthorized: false,
+      },
+      collectionName: "memories",
+      dimension: 1536,
+      embeddingModelDims: 1536,
+      hnsw: true,
+    },
+  },
+});
+
+const messages = [
+  { role: "user" as const, content: "I'm planning to watch a movie tonight. Any recommendations?" },
+  { role: "assistant" as const, content: "How about thriller movies? They can be quite engaging." },
+  { role: "user" as const, content: "I'm not a big fan of thriller movies but I love sci-fi movies." },
+  { role: "assistant" as const, content: "Got it! I'll avoid thriller recommendations and suggest sci-fi movies in the future." },
+];
+
+await m.add(messages, {
+  userId: "alice",
+  metadata: { category: "movies" },
+});
+
+const results = await m.search("What movies should I recommend?", {
+  filters: { user_id: "alice" },
+});
+
+console.log(results);
+```
+
+</CodeGroup>
+
+## SQL Migration
+
+You don't need to run any SQL migrations. Mem0 creates the collection table when it initializes the `pgvector` store.
+
+## Environment
+
+```env
+OPENAI_API_KEY=sk-xx...
+DATABASE_URL=postgresql://user:password@ep-example.us-east-2.aws.neon.tech/neondb?sslmode=require
+```
+
+## Config
+
+<Tabs>
+<Tab title="Python">
+| Parameter | Description | Default Value |
+| --- | --- | --- |
+| `connection_string` | Neon Postgres connection string. | Required |
+| `collection_name` | Name for the vector collection. | `mem0` |
+| `embedding_model_dims` | Embedding model dimensions. | `1536` |
+| `hnsw` | Enables HNSW indexing. | `False` |
+| `sslmode` | PostgreSQL SSL mode. Use `require` for Neon. | Driver default |
+</Tab>
+<Tab title="TypeScript">
+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.
+
+</Tab>
+</Tabs>
+
+### Indexing
+
+The `pgvector` provider can create an HNSW index for faster vector search.
+
+- Set `hnsw` to `true` to enable a Hierarchical Navigable Small World index.
+- Leave `hnsw` as `false` if you want to create or manage indexes yourself.
+
+### Similarity Search
+
+The `pgvector` provider uses cosine similarity for vector search. Make sure your
+embedding dimensions match the configured `embedding_model_dims` value.
+
+### Best Practices
+
+1. **Index Selection**:
+   - Use `hnsw` for faster search performance when memory usage is not a constraint
+   - Manage indexes manually if you need a different pgvector index strategy
+
+2. **Connection String**:
+   - Always use environment variables or even better, a secret manager for sensitive information in the connection string
+   - Format: `postgresql://user:password@host:port/database`

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/qdrant.mdx

@@ -76,6 +76,7 @@ Let's see the available parameters for the `qdrant` config:
 | `path` | Path for the qdrant database | `/tmp/qdrant` |
 | `url` | Full URL for the qdrant server | `None` |
 | `api_key` | API key for the qdrant server | `None` |
+| `https` | Whether to force HTTPS on or off. `None` lets the client decide; set `False` for plain HTTP Qdrant with API key authentication. | `None` |
 | `on_disk` | For enabling persistent storage | `False` |
 </Tab>
 <Tab title="TypeScript">
@@ -90,4 +91,4 @@ Let's see the available parameters for the `qdrant` config:
 | `apiKey` | API key for the Qdrant server | `None` |
 | `onDisk` | For enabling persistent storage | `False` |
 </Tab>
-</Tabs>
+</Tabs>

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/core-concepts/memory-operations/search.mdx

@@ -156,6 +156,33 @@ const memories = memory.search("food preferences", {
   On Mem0 Platform v3, time-aware queries use Temporal Reasoning internally while preserving the normal search response shape. See <Link href="/platform/features/temporal-reasoning">Temporal Reasoning</Link>.
 </Note>
 
+### Explain OSS search scores
+
+OSS search combines semantic similarity with optional keyword and entity signals. Pass `explain=True` when tuning retrieval quality or debugging why a memory ranked where it did:
+
+<CodeGroup>
+```python Python
+results = m.search(
+    "food preferences",
+    filters={"user_id": "alice"},
+    explain=True,
+)
+
+print(results["results"][0]["score_details"])
+```
+
+```javascript JavaScript
+const results = await memory.search("food preferences", {
+    filters: { user_id: "alice" },
+    explain: true,
+});
+
+console.log(results.results[0].score_details);
+```
+</CodeGroup>
+
+Each result includes `score_details` with the semantic score, normalized BM25 score, entity boost, raw combined score, maximum possible score, final score, and threshold used for filtering. The field is omitted unless `explain` is enabled, so existing response shapes stay unchanged.
+
 ## Filter patterns
 
 Filters help narrow down search results. Common use cases:

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"
                     ]
                   },
                   {
@@ -143,7 +143,8 @@
                     "icon": "robot",
                     "pages": [
                       "integrations/openclaw",
-                      "integrations/hermes"
+                      "integrations/hermes",
+                      "integrations/pi-agent"
                     ]
                   }
                 ]
@@ -245,6 +246,7 @@
                               "components/vectordbs/dbs/cassandra",
                               "components/vectordbs/dbs/s3_vectors",
                               "components/vectordbs/dbs/databricks",
+                              "components/vectordbs/dbs/neon",
                               "components/vectordbs/dbs/neptune_analytics",
                               "components/vectordbs/dbs/turbopuffer"
                             ]
@@ -270,7 +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"
                             ]
                           }
                         ]
@@ -302,7 +305,8 @@
                     "group": "Migration",
                     "icon": "arrow-right",
                     "pages": [
-                      "migration/oss-v2-to-v3"
+                      "migration/oss-v2-to-v3",
+                      "migration/server-pgvector-upgrade"
                     ]
                   },
                   {
@@ -437,7 +441,7 @@
                       "integrations/flowise",
                       "integrations/langchain-tools",
                       "integrations/agentops",
-                      "integrations/keywords",
+                      "integrations/respan",
                       "integrations/raycast"
                     ]
                   }
@@ -462,7 +466,8 @@
                     "icon": "robot",
                     "pages": [
                       "integrations/openclaw",
-                      "integrations/hermes"
+                      "integrations/hermes",
+                      "integrations/pi-agent"
                     ]
                   }
                 ]
@@ -528,6 +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"
                     ]
                   },
@@ -540,6 +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"
                     ]
                   },
@@ -619,6 +629,10 @@
     ]
   },
   "redirects": [
+    {
+      "source": "/components/rerankers/models/llm",
+      "destination": "/components/rerankers/models/llm_reranker"
+    },
     {
       "source": "/migration/breaking-changes",
       "destination": "/"
@@ -627,6 +641,10 @@
       "source": "/migration/v0-to-v1",
       "destination": "/"
     },
+    {
+      "source": "/migration/api-changes",
+      "destination": "/migration/oss-v2-to-v3"
+    },
     {
       "source": "/platform/features/expiration-date",
       "destination": "/"
@@ -643,10 +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"
@@ -1021,7 +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

@@ -28,7 +28,7 @@ echo 'export MEM0_API_KEY="m0-your-api-key"' >> ~/.bashrc && source ~/.bashrc
 
 ```bash
 # Install the plugin (MCP server, hooks, scripts)
-npx degit mem0ai/mem0/mem0-plugin ~/.gemini/config/plugins/mem0
+npx degit mem0ai/mem0/integrations/mem0-plugin ~/.gemini/config/plugins/mem0
 ```
 
 This installs the MCP server, lifecycle hooks, and shared scripts.
@@ -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/google-ai-adk.mdx

@@ -7,285 +7,338 @@ Integrate [**Mem0**](https://github.com/mem0ai/mem0) with [Google ADK (Agent Dev
 
 ## Overview
 
-1. Store and retrieve memories from Mem0 within Google ADK agents
-2. Multi-agent workflows with shared memory across hierarchies
-3. Retrieve relevant memories from past conversations
-4. Personalized responses based on user history
+In this guide, we'll create a Google ADK agent that:
+1. Uses ADK's native `MemoryService` interface to connect Mem0
+2. Automatically injects relevant memories using ADK's built-in `load_memory` tool
+3. Persists session history to Mem0 after each turn via an after-agent callback
+4. Shares memory seamlessly across multi-agent hierarchies
 
-## Prerequisites
+## Setup and Configuration
 
-Before setting up Mem0 with Google ADK, ensure you have:
+Install the necessary libraries:
 
-1. Installed the required packages:
 ```bash
 pip install google-adk mem0ai python-dotenv
 ```
 
-2. Valid API keys:
+Set up your API keys:
    - <a href="https://app.mem0.ai/dashboard/api-keys?utm_source=oss&utm_medium=integration-google-ai-adk" rel="nofollow">Mem0 API Key</a>
    - Google AI Studio API Key
 
-## Basic Integration Example
-
-The following example demonstrates how to create a Google ADK agent with Mem0 memory integration:
+<Note>Remember to get your API key from <a href="https://app.mem0.ai" rel="nofollow">Mem0 Platform</a> and set up a [Google AI Studio API Key](https://aistudio.google.com/apikey).</Note>
 
 ```python
 import os
-import asyncio
-from google.adk.agents import Agent
-from google.adk.runners import Runner
-from google.adk.sessions import InMemorySessionService
-from google.genai import types
-from mem0 import MemoryClient
 from dotenv import load_dotenv
 
 load_dotenv()
 
-# Set up environment variables
 # os.environ["GOOGLE_API_KEY"] = "your-google-api-key"
 # os.environ["MEM0_API_KEY"] = "your-mem0-api-key"
+```
 
-# Initialize Mem0 client
-mem0 = MemoryClient()
+## Implement Mem0MemoryService
 
-# Define memory function tools
-def search_memory(query: str, user_id: str) -> dict:
-    """Search through past conversations and memories"""
-    # For Platform API, user_id goes in filters
-    filters = {"user_id": user_id}
-    memories = mem0.search(query, filters=filters)
-    if memories.get('results', []):
-        memory_list = memories['results']
-        memory_context = "\n".join([f"- {mem['memory']}" for mem in memory_list])
-        return {"status": "success", "memories": memory_context}
-    return {"status": "no_memories", "message": "No relevant memories found"}
+Create a custom `MemoryService` by implementing ADK's `BaseMemoryService`. Save the following as **`mem0_memory_service.py`**:
 
-def save_memory(content: str, user_id: str) -> dict:
-    """Save important information to memory"""
+```python
+import asyncio
+import os
+from typing import Optional
+from typing_extensions import override
+
+from google.adk.memory.base_memory_service import BaseMemoryService, SearchMemoryResponse
+from google.adk.memory.memory_entry import MemoryEntry
+from google.adk.sessions import Session
+from google.genai.types import Content, Part
+from mem0 import MemoryClient
+
+
+class Mem0MemoryService(BaseMemoryService):
+    """MemoryService implementation backed by the Mem0 Platform."""
+
+    def __init__(self, api_key: Optional[str] = None):
+        super().__init__()
+        api_key = api_key or os.environ.get("MEM0_API_KEY")
+        self._client: Optional[MemoryClient] = MemoryClient(api_key=api_key) if api_key else None
+
+    @override
+    async def search_memory(
+        self, *, app_name: str, user_id: str, query: str
+    ) -> SearchMemoryResponse:
+        """Search for memories relevant to the current user and query."""
+        if not self._client:
+            return SearchMemoryResponse(memories=[])
+
+        try:
+            results = await asyncio.to_thread(
+                self._client.search,
+                query,
+                filters={"AND": [{"user_id": user_id}, {"app_id": app_name}]},
+                top_k=5,
+            )
+
+            entries = []
+            for mem in results.get("results", []):
+                text = mem.get("memory", "")
+                if not text:
+                    continue
+
+                raw_ts = mem.get("created_at") or mem.get("updated_at")
+                entries.append(
+                    MemoryEntry(
+                        content=Content(parts=[Part(text=text)]),
+                        author=mem.get("metadata", {}).get("author", "user"),
+                        timestamp=str(raw_ts) if raw_ts else None,
+                    )
+                )
+
+            return SearchMemoryResponse(memories=entries)
+
+        except Exception as e:
+            print(f"[Mem0MemoryService] search_memory error: {e}")
+            return SearchMemoryResponse(memories=[])
+
+    @override
+    async def add_session_to_memory(self, session: Session) -> None:
+        """Persist a completed ADK session into Mem0."""
+        if not self._client:
+            return
+
+        user_id = session.user_id
+        if not user_id:
+            return
+
+        app_name = getattr(session, "app_name", None)
+
+        try:
+            messages = []
+            for event in session.events:
+                if not (event.content and event.content.parts):
+                    continue
+                role = getattr(event.content, "role", None) or "user"
+                if role == "model":
+                    role = "assistant"
+                elif role not in ("user", "assistant"):
+                    continue
+                text_parts = [
+                    p.text for p in event.content.parts if hasattr(p, "text") and p.text
+                ]
+                if text_parts:
+                    messages.append({"role": role, "content": " ".join(text_parts)})
+
+            if messages:
+                metadata = {"app_id": app_name} if app_name else {}
+                await asyncio.to_thread(
+                    self._client.add, messages, user_id=user_id, metadata=metadata
+                )
+
+        except Exception as e:
+            print(f"[Mem0MemoryService] add_session_to_memory error: {e}")
+```
+
+## Add Auto-Save Callback
+
+This after-agent callback fires at the end of every turn and saves the session to Mem0. Save as **`memory_callbacks.py`**:
+
+```python
+async def save_session_to_memory(callback_context) -> None:
+    """Persist the completed session to Mem0 after each agent turn."""
     try:
-        result = mem0.add([{"role": "user", "content": content}], user_id=user_id)
-        return {"status": "success", "message": "Information saved to memory", "result": result}
+        await callback_context.add_session_to_memory()
+    except ValueError:
+        pass
     except Exception as e:
-        return {"status": "error", "message": f"Failed to save memory: {str(e)}"}
+        print(f"[save_session_to_memory] error: {e}")
+```
 
-# Create agent with memory capabilities
-personal_assistant = Agent(
+## Basic Integration Example
+
+The following example demonstrates creating an ADK agent with automatic Mem0 memory:
+
+```python
+import asyncio
+from google.adk.agents import LlmAgent
+from google.adk.runners import Runner
+from google.adk.sessions import InMemorySessionService
+from google.adk.tools import load_memory
+from google.genai.types import Content, Part
+
+from mem0_memory_service import Mem0MemoryService
+from memory_callbacks import save_session_to_memory
+
+memory_service = Mem0MemoryService()
+session_service = InMemorySessionService()
+
+agent = LlmAgent(
     name="personal_assistant",
     model="gemini-2.0-flash",
-    instruction="""You are a helpful personal assistant with memory capabilities.
-    Use the search_memory function to recall past conversations and user preferences.
-    Use the save_memory function to store important information about the user.
-    Always personalize your responses based on available memory.""",
+    instruction="""You are a helpful personal assistant.
+    Relevant memories from past conversations are provided to you automatically.
+    Use them to personalize your responses.""",
     description="A personal assistant that remembers user preferences and past interactions",
-    tools=[search_memory, save_memory]
+    tools=[load_memory],
+    after_agent_callback=save_session_to_memory,
 )
 
-async def chat_with_agent(user_input: str, user_id: str) -> str:
-    """
-    Handle user input with automatic memory integration.
+runner = Runner(
+    agent=agent,
+    session_service=session_service,
+    memory_service=memory_service,
+    app_name="memory_assistant",
+)
 
-    Args:
-        user_input: The user's message
-        user_id: Unique identifier for the user
 
-    Returns:
-        The agent's response
-    """
-    # Set up session and runner
-    session_service = InMemorySessionService()
+async def chat(user_input: str, user_id: str) -> str:
     session = await session_service.create_session(
         app_name="memory_assistant",
         user_id=user_id,
-        session_id=f"session_{user_id}"
     )
-    runner = Runner(agent=personal_assistant, app_name="memory_assistant", session_service=session_service)
-
-    # Create content and run agent
-    content = types.Content(role='user', parts=[types.Part(text=user_input)])
-    events = runner.run(user_id=user_id, session_id=session.id, new_message=content)
-
-    # Extract final response
-    for event in events:
-        if event.is_final_response():
-            response = event.content.parts[0].text
-
-            return response
-
+    content = Content(role="user", parts=[Part(text=user_input)])
+    async for event in runner.run_async(user_id=user_id, session_id=session.id, new_message=content):
+        if event.is_final_response() and event.content and event.content.parts:
+            return event.content.parts[0].text
     return "No response generated"
 
-# Example usage
+
 if __name__ == "__main__":
-    response = asyncio.run(chat_with_agent(
+    print(asyncio.run(chat(
         "I love Italian food and I'm planning a trip to Rome next month",
-        user_id="alice"
-    ))
-    print(response)
+        user_id="alice",
+    )))
+
+    print(asyncio.run(chat(
+        "Any food recommendations for my trip?",
+        user_id="alice",
+    )))
 ```
 
 ## Multi-Agent Hierarchy with Shared Memory
 
-Create specialized agents in a hierarchy that share memory:
+Because `memory_service` is passed to the `Runner`, every agent in the hierarchy shares the same memory automatically. Only the root coordinator needs the auto-save callback — ADK fires it once when the full turn completes:
 
 ```python
+import asyncio
+from google.adk.agents import LlmAgent
+from google.adk.runners import Runner
+from google.adk.sessions import InMemorySessionService
 from google.adk.tools.agent_tool import AgentTool
+from google.adk.tools import load_memory
+from google.genai.types import Content, Part
 
-# Travel specialist agent
-travel_agent = Agent(
+from mem0_memory_service import Mem0MemoryService
+from memory_callbacks import save_session_to_memory
+
+memory_service = Mem0MemoryService()
+session_service = InMemorySessionService()
+
+travel_agent = LlmAgent(
     name="travel_specialist",
     model="gemini-2.0-flash",
-    instruction="""You are a travel planning specialist. Use search_memory to
-    understand the user's travel preferences and history before making recommendations.
-    After providing advice, use save_memory to save travel-related information.""",
+    instruction="""You are a travel planning specialist.
+    Relevant memories about the user's travel preferences are provided automatically.
+    Use them to make personalized recommendations.""",
     description="Specialist in travel planning and recommendations",
-    tools=[search_memory, save_memory]
+    tools=[load_memory],
 )
 
-# Health advisor agent
-health_agent = Agent(
+health_agent = LlmAgent(
     name="health_advisor",
     model="gemini-2.0-flash",
-    instruction="""You are a health and wellness advisor. Use search_memory to
-    understand the user's health goals and dietary preferences.
-    After providing advice, use save_memory to save health-related information.""",
+    instruction="""You are a health and wellness advisor.
+    Relevant memories about the user's health goals are provided automatically.
+    Use them to give personalized advice.""",
     description="Specialist in health and wellness advice",
-    tools=[search_memory, save_memory]
+    tools=[load_memory],
 )
 
-# Coordinator agent that delegates to specialists
-coordinator_agent = Agent(
+coordinator = LlmAgent(
     name="coordinator",
     model="gemini-2.0-flash",
     instruction="""You are a coordinator that delegates requests to specialist agents.
-    For travel-related questions (trips, hotels, flights, destinations), delegate to the travel specialist.
-    For health-related questions (fitness, diet, wellness, exercise), delegate to the health advisor.
-    Use search_memory to understand the user before delegation.""",
+    For travel-related questions, delegate to the travel specialist.
+    For health-related questions, delegate to the health advisor.
+    Relevant memories about the user are provided automatically.""",
     description="Coordinates requests between specialist agents",
     tools=[
+        load_memory,
         AgentTool(agent=travel_agent, skip_summarization=False),
-        AgentTool(agent=health_agent, skip_summarization=False)
-    ]
+        AgentTool(agent=health_agent, skip_summarization=False),
+    ],
+    after_agent_callback=save_session_to_memory,
 )
 
-def chat_with_specialists(user_input: str, user_id: str) -> str:
-    """
-    Handle user input with specialist agent delegation and memory.
+runner = Runner(
+    agent=coordinator,
+    session_service=session_service,
+    memory_service=memory_service,
+    app_name="specialist_system",
+)
 
-    Args:
-        user_input: The user's message
-        user_id: Unique identifier for the user
 
-    Returns:
-        The specialist agent's response
-    """
-    session_service = InMemorySessionService()
-    session = session_service.create_session(
+async def chat_with_specialists(user_input: str, user_id: str) -> str:
+    session = await session_service.create_session(
         app_name="specialist_system",
         user_id=user_id,
-        session_id=f"session_{user_id}"
     )
-    runner = Runner(agent=coordinator_agent, app_name="specialist_system", session_service=session_service)
-
-    content = types.Content(role='user', parts=[types.Part(text=user_input)])
-    events = runner.run(user_id=user_id, session_id=session.id, new_message=content)
-
-    for event in events:
-        if event.is_final_response():
-            response = event.content.parts[0].text
-
-            # Store the conversation in shared memory
-            conversation = [
-                {"role": "user", "content": user_input},
-                {"role": "assistant", "content": response}
-            ]
-            mem0.add(conversation, user_id=user_id)
-
-            return response
-
+    content = Content(role="user", parts=[Part(text=user_input)])
+    async for event in runner.run_async(user_id=user_id, session_id=session.id, new_message=content):
+        if event.is_final_response() and event.content and event.content.parts:
+            return event.content.parts[0].text
     return "No response generated"
 
-# Example usage
-response = chat_with_specialists("Plan a healthy meal for my Italy trip", user_id="alice")
-print(response)
-```
-
-
-
-## Quick Start Chat Interface
-
-Simple interactive chat with memory and Google ADK:
-
-```python
-def interactive_chat():
-    """Interactive chat interface with memory and ADK"""
-    user_id = input("Enter your user ID: ") or "demo_user"
-    print(f"Chat started for user: {user_id}")
-    print("Type 'quit' to exit")
-    print("=" * 50)
-
-    while True:
-        user_input = input("\nYou: ")
-
-        if user_input.lower() == 'quit':
-            print("Goodbye! Your conversation has been saved to memory.")
-            break
-        else:
-            response = chat_with_specialists(user_input, user_id)
-            print(f"Assistant: {response}")
 
 if __name__ == "__main__":
-    interactive_chat()
+    response = asyncio.run(chat_with_specialists("Plan a healthy meal for my Italy trip", user_id="alice"))
+    print(response)
 ```
 
 ## Key Features
 
-### 1. Memory-Enhanced Function Tools
-- **Function Tools**: Standard Python functions that can search and save memories
-- **Tool Context**: Access to session state and memory through function parameters
-- **Structured Returns**: Dictionary-based returns with status indicators for better LLM understanding
-
-### 2. Multi-Agent Memory Sharing
-- **Agent-as-a-Tool**: Specialists can be called as tools while maintaining shared memory
-- **Hierarchical Delegation**: Coordinator agents route to specialists based on context
-- **Memory Categories**: Store interactions with metadata for better organization
-
-### 3. Flexible Memory Operations
-- **Search Capabilities**: Retrieve relevant memories through conversation history
-- **User Segmentation**: Organize memories by user ID
-- **Memory Management**: Built-in tools for saving and retrieving information
+1. **Automatic Memory Injection**: ADK's built-in `load_memory` tool searches Mem0 at the start of each turn and injects relevant memories directly into the agent context — no prompt instructions needed.
+2. **Automatic Session Saving**: The `save_session_to_memory` callback persists every completed turn to Mem0 without any manual calls.
+3. **Native ADK Integration**: `Mem0MemoryService` implements ADK's `BaseMemoryService` and integrates via the `Runner` — works natively across the entire agent hierarchy.
+4. **User Scoping**: `user_id` is passed automatically from the ADK session context, ensuring memories are always scoped to the correct user.
+5. **Multi-Agent Support**: A single `Mem0MemoryService` instance shared through the `Runner` gives all agents — coordinators and specialists — access to the same user memory.
 
 ## Configuration Options
 
-Customize memory behavior and agent setup:
+### Using Vertex AI
+
+To use Google Cloud Vertex AI instead of AI Studio, set the following environment variables before creating agents:
 
 ```python
-# Configure memory search with filters
-# For Platform API, all filters including user_id go in filters object
-memories = mem0.search(
-    query="travel preferences",
-    filters={
-        "AND": [
-            {"user_id": "alice"},
-            {"categories": {"contains": "travel"}}
-        ]
-    },
-    top_k=5
-)
-
-# Configure agent with custom model settings
-agent = Agent(
-    name="custom_agent",
-    model="gemini-2.0-flash",  # or use LiteLLM for other models
-    instruction="Custom agent behavior",
-    tools=[memory_tools],
-    # Additional ADK configurations
-)
-
-# Use Google Cloud Vertex AI instead of AI Studio
+import os
 os.environ["GOOGLE_GENAI_USE_VERTEXAI"] = "True"
 os.environ["GOOGLE_CLOUD_PROJECT"] = "your-project-id"
 os.environ["GOOGLE_CLOUD_LOCATION"] = "us-central1"
 ```
 
+### Advanced Memory Filtering
+
+You can customize how memories are searched by modifying `Mem0MemoryService.search_memory`. For example, to filter by category:
+
+```python
+results = await asyncio.to_thread(
+    self._client.search,
+    query,
+    filters={
+        "AND": [
+            {"user_id": user_id},
+            {"app_id": app_name},
+            {"categories": {"contains": "travel"}}
+        ]
+    },
+    top_k=10,
+)
+```
+
+<Note>`InMemorySessionService` stores sessions in memory and is intended for prototyping. For production, use a persistent session service and clean up sessions when they are no longer needed.</Note>
+
+## Conclusion
+
+By implementing `Mem0MemoryService` as an ADK `BaseMemoryService`, you get persistent, user-scoped memory across single agents and complex multi-agent hierarchies with minimal code. Memory injection and session saving happen automatically, keeping your agent prompts clean and your token usage efficient.
+
 <CardGroup cols={2}>
   <Card title="Healthcare Agent Cookbook" icon="heart-pulse" href="/cookbooks/integrations/healthcare-google-adk">
     Build HIPAA-compliant healthcare agents with Google ADK
@@ -294,4 +347,3 @@ os.environ["GOOGLE_CLOUD_LOCATION"] = "us-central1"
     Compare with OpenAI's agent framework
   </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()
 ```