feat(cli): comprehensive docs, version bump, and purple branding (#4680)

Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.github/workflows/openclaw-cd.yml

@@ -0,0 +1,43 @@
+name: Publish @mem0/openclaw-mem0 📦 to npm
+
+on:
+  release:
+    types: [published]
+
+jobs:
+  build-n-publish:
+    name: Build and publish @mem0/openclaw-mem0 📦 to npm
+    if: startsWith(github.event.release.tag_name, 'openclaw-v')
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+    defaults:
+      run:
+        working-directory: openclaw
+    steps:
+      - uses: actions/checkout@v4
+
+      - 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: openclaw/pnpm-lock.yaml
+
+      - name: Upgrade npm for OIDC trusted publishing
+        run: npm install -g npm@latest
+
+      - name: Install dependencies
+        run: pnpm install --frozen-lockfile
+
+      - name: Build
+        run: pnpm build
+
+      - name: Publish to npm
+        run: npm publish --provenance --access public

CONTRIBUTING.md

@@ -75,6 +75,7 @@ All packages are published automatically via GitHub Actions when a GitHub Releas
 | `mem0ai` (TypeScript SDK) | npm | `ts-v*` | `ts-v2.4.6` |
 | `@mem0/cli` (Node CLI) | npm | `cli-node-v*` | `cli-node-v0.1.2` |
 | `@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
 

cli/cli-spec.json

@@ -10,8 +10,8 @@
     "logoMini": "\u25c6 mem0",
     "tagline": "The Memory Layer for AI Agents",
     "colors": {
-      "brand": "#F1C96C",
-      "accent": "#F5D78E",
+      "brand": "#8b5cf6",
+      "accent": "#a78bfa",
       "success": "#22c55e",
       "error": "#ef4444",
       "warning": "#f59e0b",

cli/node/README.md

@@ -2,10 +2,12 @@
 
 The official command-line interface for [mem0](https://mem0.ai) — the memory layer for AI agents. TypeScript implementation.
 
+> **Built for AI agents.** Pass `--agent` (or `--json`) as a global flag on any command to get structured JSON output optimized for programmatic consumption — sanitized fields, no colors or spinners, and errors as JSON too.
+
 ## Prerequisites
 
 - Node.js **18+**
-- pnpm (`npm install -g pnpm`)
+- pnpm (`npm install -g pnpm`) — for development only
 
 ## Installation
 
@@ -13,22 +15,307 @@ The official command-line interface for [mem0](https://mem0.ai) — the memory l
 npm install -g @mem0/cli
 ```
 
-Or from source:
+## Quick start
 
 ```bash
-cd node
-pnpm install
-pnpm build
-pnpm link --global
+# Interactive setup wizard
+mem0 init
 
-# Now use it like a normal CLI
-mem0 --help
+# Or login via email
+mem0 init --email alice@company.com
+
+# Or authenticate with an existing API key
+mem0 init --api-key m0-xxx
+
+# Add a memory
+mem0 add "I prefer dark mode and use vim keybindings" --user-id alice
+
+# Search memories
+mem0 search "What are Alice's preferences?" --user-id alice
+
+# List all memories for a user
+mem0 list --user-id alice
+
+# Get a specific memory
+mem0 get <memory-id>
+
+# Update a memory
+mem0 update <memory-id> "I switched to light mode"
+
+# Delete a memory
+mem0 delete <memory-id>
 ```
 
-## Running during development
+## Commands
+
+### `mem0 init`
+
+Interactive setup wizard. Prompts for your API key and default user ID.
 
 ```bash
-cd node
+mem0 init
+mem0 init --api-key m0-xxx --user-id alice
+mem0 init --email alice@company.com
+```
+
+If an existing configuration is detected, the CLI asks for confirmation before overwriting. Use `--force` to skip the prompt (useful in CI/CD).
+
+```bash
+mem0 init --api-key m0-xxx --user-id alice --force
+```
+
+| Flag | Description |
+|------|-------------|
+| `--api-key` | API key (skip prompt) |
+| `-u, --user-id` | Default user ID (skip prompt) |
+| `--email` | Login via email verification code |
+| `--code` | Verification code (use with `--email` for non-interactive login) |
+| `--force` | Overwrite existing config without confirmation |
+
+### `mem0 add`
+
+Add a memory from text, a JSON messages array, a file, or stdin.
+
+```bash
+mem0 add "I prefer dark mode" --user-id alice
+mem0 add --file conversation.json --user-id alice
+echo "Loves hiking on weekends" | mem0 add --user-id alice
+```
+
+| Flag | Description |
+|------|-------------|
+| `-u, --user-id` | Scope to a user |
+| `--agent-id` | Scope to an agent |
+| `--messages` | Conversation messages as JSON |
+| `-f, --file` | Read messages from a JSON file |
+| `-m, --metadata` | Custom metadata as JSON |
+| `--categories` | Categories (JSON array or comma-separated) |
+| `--graph / --no-graph` | Enable or disable graph memory extraction |
+| `-o, --output` | Output format: `text`, `json`, `quiet` |
+
+### `mem0 search`
+
+Search memories using natural language.
+
+```bash
+mem0 search "dietary restrictions" --user-id alice
+mem0 search "preferred tools" --user-id alice --output json --top-k 5
+```
+
+| Flag | Description |
+|------|-------------|
+| `-u, --user-id` | Filter by user |
+| `-k, --top-k` | Number of results (default: 10) |
+| `--threshold` | Minimum similarity score (default: 0.3) |
+| `--rerank` | Enable reranking |
+| `--keyword` | Use keyword search instead of semantic |
+| `--filter` | Advanced filter expression (JSON) |
+| `--graph / --no-graph` | Enable or disable graph in search |
+| `-o, --output` | Output format: `text`, `json`, `table` |
+
+### `mem0 list`
+
+List memories with optional filters and pagination.
+
+```bash
+mem0 list --user-id alice
+mem0 list --user-id alice --category preferences --output json
+mem0 list --user-id alice --after 2024-01-01 --page-size 50
+```
+
+| Flag | Description |
+|------|-------------|
+| `-u, --user-id` | Filter by user |
+| `--page` | Page number (default: 1) |
+| `--page-size` | Results per page (default: 100) |
+| `--category` | Filter by category |
+| `--after` | Created after date (YYYY-MM-DD) |
+| `--before` | Created before date (YYYY-MM-DD) |
+| `-o, --output` | Output format: `text`, `json`, `table` |
+
+### `mem0 get`
+
+Retrieve a specific memory by ID.
+
+```bash
+mem0 get 7b3c1a2e-4d5f-6789-abcd-ef0123456789
+mem0 get 7b3c1a2e-4d5f-6789-abcd-ef0123456789 --output json
+```
+
+### `mem0 update`
+
+Update the text or metadata of an existing memory.
+
+```bash
+mem0 update <memory-id> "Updated preference text"
+mem0 update <memory-id> --metadata '{"priority": "high"}'
+echo "new text" | mem0 update <memory-id>
+```
+
+### `mem0 delete`
+
+Delete a single memory, all memories for a scope, or an entire entity.
+
+```bash
+# Delete a single memory
+mem0 delete <memory-id>
+
+# Delete all memories for a user
+mem0 delete --all --user-id alice --force
+
+# Delete all memories project-wide
+mem0 delete --all --project --force
+
+# Preview what would be deleted
+mem0 delete --all --user-id alice --dry-run
+```
+
+| Flag | Description |
+|------|-------------|
+| `--all` | Delete all memories matching scope filters |
+| `--entity` | Delete the entity and all its memories |
+| `--project` | With `--all`: delete all memories project-wide |
+| `--dry-run` | Preview without deleting |
+| `--force` | Skip confirmation prompt |
+
+### `mem0 import`
+
+Bulk import memories from a JSON file.
+
+```bash
+mem0 import data.json --user-id alice
+```
+
+The file should be a JSON array where each item has a `memory` (or `text` or `content`) field and optional `user_id`, `agent_id`, and `metadata` fields.
+
+### `mem0 config`
+
+View or modify the local CLI configuration.
+
+```bash
+mem0 config show              # Display current config (secrets redacted)
+mem0 config get api_key       # Get a specific value
+mem0 config set user_id bob   # Set a value
+```
+
+### `mem0 entity`
+
+List or delete entities (users, agents, apps, runs).
+
+```bash
+mem0 entity list users
+mem0 entity list agents --output json
+mem0 entity delete --user-id alice --force
+```
+
+### `mem0 event`
+
+Inspect background processing events created by async operations (e.g. bulk deletes, large add jobs).
+
+```bash
+# List recent events
+mem0 event list
+
+# Check the status of a specific event
+mem0 event status <event-id>
+```
+
+| Flag | Description |
+|------|-------------|
+| `-o, --output` | Output format: `text`, `json` |
+
+### `mem0 status`
+
+Verify your API connection and display the current project.
+
+```bash
+mem0 status
+```
+
+### `mem0 version`
+
+Print the CLI version.
+
+```bash
+mem0 version
+```
+
+## Agent mode
+
+Pass `--agent` (or its alias `--json`) as a **global flag** on any command to get output designed for AI agent tool loops:
+
+```bash
+mem0 --agent search "user preferences" --user-id alice
+mem0 --agent add "User prefers dark mode" --user-id alice
+mem0 --agent list --user-id alice
+mem0 --agent delete --all --user-id alice --force
+```
+
+Every command returns the same envelope shape:
+
+```json
+{
+  "status": "success",
+  "command": "search",
+  "duration_ms": 134,
+  "scope": { "user_id": "alice" },
+  "count": 2,
+  "data": [
+    { "id": "abc-123", "memory": "User prefers dark mode", "score": 0.97, "created_at": "2026-01-15", "categories": ["preferences"] }
+  ]
+}
+```
+
+What agent mode does differently from `--output json`:
+
+- **Sanitized `data`**: only the fields an agent needs (id, memory, score, etc.) — no internal API noise
+- **No human output**: spinners, colors, and banners are suppressed entirely
+- **Errors as JSON**: errors go to stdout as `{"status": "error", "command": "...", "error": "..."}` with a non-zero exit code
+
+Use `mem0 help --json` to get the full command tree as JSON — useful for agents that need to self-discover available commands.
+
+## Output formats
+
+Control how results are displayed with `--output`:
+
+| Format | Description |
+|--------|-------------|
+| `text` | Human-readable with colors and formatting (default) |
+| `json` | Structured JSON for piping to `jq` (raw API response) |
+| `table` | Tabular format (default for `list`) |
+| `quiet` | Minimal — just IDs or status codes |
+| `agent` | Structured JSON envelope with sanitized fields (set by `--agent`/`--json`) |
+
+## Global flags
+
+These flags are available on all commands:
+
+| Flag | Description |
+|------|-------------|
+| `--json` | Enable agent mode: structured JSON envelope output, no colors or spinners |
+| `--agent` | Alias for `--json` |
+| `--api-key` | Override the configured API key for this request |
+| `--base-url` | Override the configured API base URL for this request |
+| `-o, --output` | Set the output format |
+
+## Environment variables
+
+| Variable | Description |
+|----------|-------------|
+| `MEM0_API_KEY` | API key (overrides config file) |
+| `MEM0_BASE_URL` | API base URL |
+| `MEM0_USER_ID` | Default user ID |
+| `MEM0_AGENT_ID` | Default agent ID |
+| `MEM0_APP_ID` | Default app ID |
+| `MEM0_RUN_ID` | Default run ID |
+| `MEM0_ENABLE_GRAPH` | Enable graph memory (`true` / `false`) |
+
+Environment variables take precedence over values in the config file, which take precedence over defaults.
+
+## Development
+
+```bash
+cd cli/node
 pnpm install
 
 # Development mode (runs TypeScript directly, no build needed)
@@ -39,36 +326,11 @@ pnpm dev search "test" --user-id alice
 # Or build first, then run the compiled JS
 pnpm build
 node dist/index.js --help
-node dist/index.js add "test memory" --user-id alice
 ```
 
-## Quick Start
+## Documentation
 
-```bash
-# Set up your configuration
-mem0 init
-
-# Add a memory
-mem0 add "I prefer dark mode and use vim keybindings" --user-id alice
-
-# Search memories
-mem0 search "What are Alice's preferences?" --user-id alice
-
-# List all memories
-mem0 list --user-id alice
-```
-
-## Environment Variables
-
-| Variable | Description |
-|----------|-------------|
-| `MEM0_API_KEY` | API key (overrides config file) |
-| `MEM0_BASE_URL` | API base URL |
-| `MEM0_USER_ID` | Default user ID |
-| `MEM0_AGENT_ID` | Default agent ID |
-| `MEM0_APP_ID` | Default app ID |
-| `MEM0_RUN_ID` | Default run ID |
-| `MEM0_ENABLE_GRAPH` | Enable graph memory (true/false) |
+Full documentation is available at [docs.mem0.ai/platform/cli](https://docs.mem0.ai/platform/cli).
 
 ## License
 

cli/node/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@mem0/cli",
-  "version": "0.1.2",
+  "version": "0.2.1",
   "description": "The official CLI for mem0 — the memory layer for AI agents",
   "type": "module",
   "bin": {

cli/node/src/branding.ts

@@ -19,8 +19,8 @@ export const LOGO = `
 export const LOGO_MINI = "◆ mem0";
 export const TAGLINE = "The Memory Layer for AI Agents";
 
-export const BRAND_COLOR = "#F1C96C";
-export const ACCENT_COLOR = "#F5D78E";
+export const BRAND_COLOR = "#8b5cf6";
+export const ACCENT_COLOR = "#a78bfa";
 export const SUCCESS_COLOR = "#22c55e";
 export const ERROR_COLOR = "#ef4444";
 export const WARNING_COLOR = "#f59e0b";

cli/node/tests/branding.test.ts

@@ -39,7 +39,7 @@ afterEach(() => {
 
 describe("branding constants", () => {
   it("has correct brand color", () => {
-    expect(BRAND_COLOR).toBe("#F1C96C");
+    expect(BRAND_COLOR).toBe("#8b5cf6");
   });
 
   it("has correct tagline", () => {

cli/python/README.md

@@ -1,6 +1,12 @@
-# mem0 CLI
+# mem0 CLI (Python)
 
-The official command-line interface for [mem0](https://mem0.ai) — the memory layer for AI agents.
+The official command-line interface for [mem0](https://mem0.ai) — the memory layer for AI agents. Python implementation.
+
+> **Built for AI agents.** Pass `--agent` (or `--json`) as a global flag on any command to get structured JSON output optimized for programmatic consumption — sanitized fields, no colors or spinners, and errors as JSON too.
+
+## Prerequisites
+
+- Python **3.10+**
 
 ## Installation
 
@@ -18,28 +24,325 @@ pip install mem0-cli
 
 > **Note:** On macOS with Homebrew Python, `pip install` outside a virtual environment will fail with an `externally-managed-environment` error ([PEP 668](https://peps.python.org/pep-0668/)). Use `pipx` instead, or install inside a virtual environment.
 
-## Quick Start
+## Quick start
 
 ```bash
-# Set up your configuration
+# Interactive setup wizard
 mem0 init
 
+# Or login via email
+mem0 init --email alice@company.com
+
+# Or authenticate with an existing API key
+mem0 init --api-key m0-xxx
+
 # Add a memory
 mem0 add "I prefer dark mode and use vim keybindings" --user-id alice
 
 # Search memories
 mem0 search "What are Alice's preferences?" --user-id alice
 
-# List all memories
+# List all memories for a user
 mem0 list --user-id alice
+
+# Get a specific memory
+mem0 get <memory-id>
+
+# Update a memory
+mem0 update <memory-id> "I switched to light mode"
+
+# Delete a memory
+mem0 delete <memory-id>
+```
+
+## Commands
+
+### `mem0 init`
+
+Interactive setup wizard. Prompts for your API key and default user ID.
+
+```bash
+mem0 init
+mem0 init --api-key m0-xxx --user-id alice
+mem0 init --email alice@company.com
+```
+
+If an existing configuration is detected, the CLI asks for confirmation before overwriting. Use `--force` to skip the prompt (useful in CI/CD).
+
+```bash
+mem0 init --api-key m0-xxx --user-id alice --force
+```
+
+| Flag | Description |
+|------|-------------|
+| `--api-key` | API key (skip prompt) |
+| `-u, --user-id` | Default user ID (skip prompt) |
+| `--email` | Login via email verification code |
+| `--code` | Verification code (use with `--email` for non-interactive login) |
+| `--force` | Overwrite existing config without confirmation |
+
+### `mem0 add`
+
+Add a memory from text, a JSON messages array, a file, or stdin.
+
+```bash
+mem0 add "I prefer dark mode" --user-id alice
+mem0 add --file conversation.json --user-id alice
+echo "Loves hiking on weekends" | mem0 add --user-id alice
+```
+
+| Flag | Description |
+|------|-------------|
+| `-u, --user-id` | Scope to a user |
+| `--agent-id` | Scope to an agent |
+| `--messages` | Conversation messages as JSON |
+| `-f, --file` | Read messages from a JSON file |
+| `-m, --metadata` | Custom metadata as JSON |
+| `--categories` | Categories (JSON array or comma-separated) |
+| `--graph / --no-graph` | Enable or disable graph memory extraction |
+| `-o, --output` | Output format: `text`, `json`, `quiet` |
+
+### `mem0 search`
+
+Search memories using natural language.
+
+```bash
+mem0 search "dietary restrictions" --user-id alice
+mem0 search "preferred tools" --user-id alice --output json --top-k 5
+```
+
+| Flag | Description |
+|------|-------------|
+| `-u, --user-id` | Filter by user |
+| `-k, --top-k` | Number of results (default: 10) |
+| `--threshold` | Minimum similarity score (default: 0.3) |
+| `--rerank` | Enable reranking |
+| `--keyword` | Use keyword search instead of semantic |
+| `--filter` | Advanced filter expression (JSON) |
+| `--graph / --no-graph` | Enable or disable graph in search |
+| `-o, --output` | Output format: `text`, `json`, `table` |
+
+### `mem0 list`
+
+List memories with optional filters and pagination.
+
+```bash
+mem0 list --user-id alice
+mem0 list --user-id alice --category preferences --output json
+mem0 list --user-id alice --after 2024-01-01 --page-size 50
+```
+
+| Flag | Description |
+|------|-------------|
+| `-u, --user-id` | Filter by user |
+| `--page` | Page number (default: 1) |
+| `--page-size` | Results per page (default: 100) |
+| `--category` | Filter by category |
+| `--after` | Created after date (YYYY-MM-DD) |
+| `--before` | Created before date (YYYY-MM-DD) |
+| `-o, --output` | Output format: `text`, `json`, `table` |
+
+### `mem0 get`
+
+Retrieve a specific memory by ID.
+
+```bash
+mem0 get 7b3c1a2e-4d5f-6789-abcd-ef0123456789
+mem0 get 7b3c1a2e-4d5f-6789-abcd-ef0123456789 --output json
+```
+
+### `mem0 update`
+
+Update the text or metadata of an existing memory.
+
+```bash
+mem0 update <memory-id> "Updated preference text"
+mem0 update <memory-id> --metadata '{"priority": "high"}'
+echo "new text" | mem0 update <memory-id>
+```
+
+### `mem0 delete`
+
+Delete a single memory, all memories for a scope, or an entire entity.
+
+```bash
+# Delete a single memory
+mem0 delete <memory-id>
+
+# Delete all memories for a user
+mem0 delete --all --user-id alice --force
+
+# Delete all memories project-wide
+mem0 delete --all --project --force
+
+# Preview what would be deleted
+mem0 delete --all --user-id alice --dry-run
+```
+
+| Flag | Description |
+|------|-------------|
+| `--all` | Delete all memories matching scope filters |
+| `--entity` | Delete the entity and all its memories |
+| `--project` | With `--all`: delete all memories project-wide |
+| `--dry-run` | Preview without deleting |
+| `--force` | Skip confirmation prompt |
+
+### `mem0 import`
+
+Bulk import memories from a JSON file.
+
+```bash
+mem0 import data.json --user-id alice
+```
+
+The file should be a JSON array where each item has a `memory` (or `text` or `content`) field and optional `user_id`, `agent_id`, and `metadata` fields.
+
+### `mem0 config`
+
+View or modify the local CLI configuration.
+
+```bash
+mem0 config show              # Display current config (secrets redacted)
+mem0 config get api_key       # Get a specific value
+mem0 config set user_id bob   # Set a value
+```
+
+### `mem0 entity`
+
+List or delete entities (users, agents, apps, runs).
+
+```bash
+mem0 entity list users
+mem0 entity list agents --output json
+mem0 entity delete --user-id alice --force
+```
+
+### `mem0 event`
+
+Inspect background processing events created by async operations (e.g. bulk deletes, large add jobs).
+
+```bash
+# List recent events
+mem0 event list
+
+# Check the status of a specific event
+mem0 event status <event-id>
+```
+
+| Flag | Description |
+|------|-------------|
+| `-o, --output` | Output format: `text`, `json` |
+
+### `mem0 status`
+
+Verify your API connection and display the current project.
+
+```bash
+mem0 status
+```
+
+### `mem0 version`
+
+Print the CLI version.
+
+```bash
+mem0 version
+```
+
+## Agent mode
+
+Pass `--agent` (or its alias `--json`) as a **global flag** on any command to get output designed for AI agent tool loops:
+
+```bash
+mem0 --agent search "user preferences" --user-id alice
+mem0 --agent add "User prefers dark mode" --user-id alice
+mem0 --agent list --user-id alice
+mem0 --agent delete --all --user-id alice --force
+```
+
+Every command returns the same envelope shape:
+
+```json
+{
+  "status": "success",
+  "command": "search",
+  "duration_ms": 134,
+  "scope": { "user_id": "alice" },
+  "count": 2,
+  "data": [
+    { "id": "abc-123", "memory": "User prefers dark mode", "score": 0.97, "created_at": "2026-01-15", "categories": ["preferences"] }
+  ]
+}
+```
+
+What agent mode does differently from `--output json`:
+
+- **Sanitized `data`**: only the fields an agent needs (id, memory, score, etc.) — no internal API noise
+- **No human output**: spinners, colors, and banners are suppressed entirely
+- **Errors as JSON**: errors go to stdout as `{"status": "error", "command": "...", "error": "..."}` with a non-zero exit code
+
+Use `mem0 help --json` to get the full command tree as JSON — useful for agents that need to self-discover available commands.
+
+## Output formats
+
+Control how results are displayed with `--output`:
+
+| Format | Description |
+|--------|-------------|
+| `text` | Human-readable with colors and formatting (default) |
+| `json` | Structured JSON for piping to `jq` (raw API response) |
+| `table` | Tabular format (default for `list`) |
+| `quiet` | Minimal — just IDs or status codes |
+| `agent` | Structured JSON envelope with sanitized fields (set by `--agent`/`--json`) |
+
+## Global flags
+
+These flags are available on all commands:
+
+| Flag | Description |
+|------|-------------|
+| `--json` | Enable agent mode: structured JSON envelope output, no colors or spinners |
+| `--agent` | Alias for `--json` |
+| `--api-key` | Override the configured API key for this request |
+| `--base-url` | Override the configured API base URL for this request |
+| `-o, --output` | Set the output format |
+
+## Environment variables
+
+| Variable | Description |
+|----------|-------------|
+| `MEM0_API_KEY` | API key (overrides config file) |
+| `MEM0_BASE_URL` | API base URL |
+| `MEM0_USER_ID` | Default user ID |
+| `MEM0_AGENT_ID` | Default agent ID |
+| `MEM0_APP_ID` | Default app ID |
+| `MEM0_RUN_ID` | Default run ID |
+| `MEM0_ENABLE_GRAPH` | Enable graph memory (`true` / `false`) |
+
+Environment variables take precedence over values in the config file, which take precedence over defaults.
+
+## Development
+
+```bash
+cd cli/python
+python -m venv .venv && source .venv/bin/activate
+pip install -e ".[dev]"
+
+# Run during development
+python -m mem0_cli --help
+mem0 add "test memory" --user-id alice
 ```
 
 ## Releasing
 
 1. Update `version` in `pyproject.toml`
-2. Create a GitHub Release with tag `cli-v<version>` (e.g. `cli-v0.2.0`)
+2. Create a GitHub Release with tag `cli-v<version>` (e.g. `cli-v0.2.1`)
 
-For a pre-release, use a beta version like `0.2.0b1` and check the **pre-release** checkbox.
+For a pre-release, use a beta version like `0.2.1b1` and check the **pre-release** checkbox.
+
+## Documentation
+
+Full documentation is available at [docs.mem0.ai/platform/cli](https://docs.mem0.ai/platform/cli).
 
 ## License
 

cli/python/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "mem0-cli"
-version = "0.2.0"
+version = "0.2.1"
 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__ = "0.1.0"
+__version__ = "0.2.1"

cli/python/src/mem0_cli/branding.py

@@ -26,8 +26,8 @@ LOGO_MINI = "◆ mem0"
 
 TAGLINE = "The Memory Layer for AI Agents"
 
-BRAND_COLOR = "#F1C96C"  # Golden
-ACCENT_COLOR = "#F5D78E"
+BRAND_COLOR = "#8b5cf6"  # Purple
+ACCENT_COLOR = "#a78bfa"
 SUCCESS_COLOR = "#22c55e"
 ERROR_COLOR = "#ef4444"
 WARNING_COLOR = "#f59e0b"

cli/python/tests/test_cli_integration.py

@@ -83,11 +83,6 @@ class TestCLIIntegration:
         assert "add" in result.stdout
         assert "search" in result.stdout
 
-    def test_version_flag(self):
-        result = _run(["--version"])
-        assert result.returncode == 0
-        assert "0.1.0" in result.stdout
-
     def test_add_help(self):
         result = _run(["add", "--help"])
         assert result.returncode == 0

cli/python/tests/test_commands.py

@@ -30,7 +30,6 @@ from mem0_cli.commands.memory import (
 from mem0_cli.commands.utils import (
     cmd_import,
     cmd_status,
-    cmd_version,
 )
 
 
@@ -742,15 +741,6 @@ class TestStatusCommand:
         assert '"status"' in output
 
 
-class TestVersionCommand:
-    def test_version(self):
-        console, buf = _make_console()
-        with patch("mem0_cli.commands.utils.console", console):
-            cmd_version()
-        output = buf.getvalue()
-        assert "0.1.0" in output
-
-
 class TestImportCommand:
     def test_import_json(self, mock_backend, tmp_path):
         file_path = tmp_path / "import.json"

docs/api-reference/organizations-projects.mdx

@@ -82,7 +82,7 @@ new_project = client.project.create(
 
 ### Update Project Settings
 
-Modify project configuration including custom instructions, categories, and graph settings:
+Modify project configuration including custom instructions, categories, graph settings, and language preferences:
 
 ```python
 # Update project with custom categories
@@ -101,6 +101,9 @@ client.project.update(
 # Enable graph memory for the project
 client.project.update(enable_graph=True)
 
+# Use the input language for memory storage and retrieval
+client.project.update(multilingual=True)
+
 # Update multiple settings at once
 client.project.update(
     custom_instructions="...",
@@ -108,7 +111,8 @@ client.project.update(
         {"personal_info": "User personal information and preferences"},
         {"work_context": "Professional context and work-related information"}
     ],
-    enable_graph=True
+    enable_graph=True,
+    multilingual=True
 )
 ```
 

docs/components/llms/models/google_AI.mdx

@@ -24,6 +24,7 @@ config = {
         "provider": "gemini",
         "config": {
             "model": "gemini-2.0-flash-001",
+            "api_key": "your-gemini-api-key",
             "temperature": 0.2,
             "max_tokens": 2000,
             "top_p": 1.0
@@ -52,6 +53,7 @@ const config = {
         provider: "gemini",
         config: {
             model: "gemini-2.0-flash-001",
+            apiKey: process.env.GOOGLE_API_KEY || '',
             temperature: 0.1
         }
     }

docs/openapi.json

@@ -3686,6 +3686,10 @@
 											"type": "object"
 										},
 										"description": "List of custom categories to be used for memory categorization."
+									},
+									"multilingual": {
+										"type": "boolean",
+										"description": "Whether to use the input language for memory storage and retrieval."
 									}
 								}
 							}

mem0-ts/src/client/mem0.types.ts

@@ -167,6 +167,7 @@ export interface PromptUpdatePayload {
   exclusion_prompt?: string;
   memory_depth?: string | null;
   usecase_setting?: string | number;
+  multilingual?: boolean;
   [key: string]: any;
 }
 

mem0/client/main.py

@@ -676,6 +676,7 @@ class MemoryClient:
         exclusion_prompt: Optional[str] = None,
         memory_depth: Optional[str] = None,
         usecase_setting: Optional[str] = None,
+        multilingual: Optional[bool] = None,
     ) -> Dict[str, Any]:
         """Update the project settings.
 
@@ -689,6 +690,7 @@ class MemoryClient:
             exclusion_prompt: Exclusion prompt for the project
             memory_depth: Memory depth for the project
             usecase_setting: Usecase setting for the project
+            multilingual: Whether to use the input language for memory storage and retrieval
 
         Returns:
             Dictionary containing the API response.
@@ -718,6 +720,7 @@ class MemoryClient:
             and exclusion_prompt is None
             and memory_depth is None
             and usecase_setting is None
+            and multilingual is None
         ):
             raise ValueError(
                 "Currently we only support updating custom_instructions or "
@@ -736,6 +739,7 @@ class MemoryClient:
                 "exclusion_prompt": exclusion_prompt,
                 "memory_depth": memory_depth,
                 "usecase_setting": usecase_setting,
+                "multilingual": multilingual,
             }
         )
         response = self.client.patch(
@@ -756,6 +760,7 @@ class MemoryClient:
                 "exclusion_prompt": exclusion_prompt,
                 "memory_depth": memory_depth,
                 "usecase_setting": usecase_setting,
+                "multilingual": multilingual,
                 "sync_type": "sync",
             },
         )
@@ -1554,6 +1559,7 @@ class AsyncMemoryClient:
         retrieval_criteria: Optional[List[Dict[str, Any]]] = None,
         enable_graph: Optional[bool] = None,
         version: Optional[str] = None,
+        multilingual: Optional[bool] = None,
     ) -> Dict[str, Any]:
         """Update the project settings.
 
@@ -1563,6 +1569,7 @@ class AsyncMemoryClient:
             retrieval_criteria: New retrieval criteria for the project
             enable_graph: Enable or disable the graph for the project
             version: Version of the project
+            multilingual: Whether to use the input language for memory storage and retrieval
 
         Returns:
             Dictionary containing the API response.
@@ -1588,6 +1595,7 @@ class AsyncMemoryClient:
             and retrieval_criteria is None
             and enable_graph is None
             and version is None
+            and multilingual is None
         ):
             raise ValueError(
                 "Currently we only support updating custom_instructions or custom_categories or retrieval_criteria, so you must provide at least one of them"
@@ -1600,6 +1608,7 @@ class AsyncMemoryClient:
                 "retrieval_criteria": retrieval_criteria,
                 "enable_graph": enable_graph,
                 "version": version,
+                "multilingual": multilingual,
             }
         )
         response = await self.async_client.patch(
@@ -1616,6 +1625,7 @@ class AsyncMemoryClient:
                 "retrieval_criteria": retrieval_criteria,
                 "enable_graph": enable_graph,
                 "version": version,
+                "multilingual": multilingual,
                 "sync_type": "async",
             },
         )

mem0/client/project.py

@@ -399,6 +399,7 @@ class Project(BaseProject):
         custom_categories: Optional[List[str]] = None,
         retrieval_criteria: Optional[List[Dict[str, Any]]] = None,
         enable_graph: Optional[bool] = None,
+        multilingual: Optional[bool] = None,
     ) -> Dict[str, Any]:
         """
         Update project settings.
@@ -408,6 +409,7 @@ class Project(BaseProject):
             custom_categories: New categories for the project
             retrieval_criteria: New retrieval criteria for the project
             enable_graph: Enable or disable the graph for the project
+            multilingual: Whether to use the input language for memory storage and retrieval
 
         Returns:
             Dictionary containing the API response.
@@ -424,11 +426,12 @@ class Project(BaseProject):
             and custom_categories is None
             and retrieval_criteria is None
             and enable_graph is None
+            and multilingual is None
         ):
             raise ValueError(
                 "At least one parameter must be provided for update: "
                 "custom_instructions, custom_categories, retrieval_criteria, "
-                "enable_graph"
+                "enable_graph, multilingual"
             )
 
         payload = self._prepare_params(
@@ -437,6 +440,7 @@ class Project(BaseProject):
                 "custom_categories": custom_categories,
                 "retrieval_criteria": retrieval_criteria,
                 "enable_graph": enable_graph,
+                "multilingual": multilingual,
             }
         )
         response = self._client.patch(
@@ -452,6 +456,7 @@ class Project(BaseProject):
                 "custom_categories": custom_categories,
                 "retrieval_criteria": retrieval_criteria,
                 "enable_graph": enable_graph,
+                "multilingual": multilingual,
                 "sync_type": "sync",
             },
         )
@@ -716,6 +721,7 @@ class AsyncProject(BaseProject):
         custom_categories: Optional[List[str]] = None,
         retrieval_criteria: Optional[List[Dict[str, Any]]] = None,
         enable_graph: Optional[bool] = None,
+        multilingual: Optional[bool] = None,
     ) -> Dict[str, Any]:
         """
         Update project settings.
@@ -725,6 +731,7 @@ class AsyncProject(BaseProject):
             custom_categories: New categories for the project
             retrieval_criteria: New retrieval criteria for the project
             enable_graph: Enable or disable the graph for the project
+            multilingual: Whether to use the input language for memory storage and retrieval
 
         Returns:
             Dictionary containing the API response.
@@ -741,11 +748,12 @@ class AsyncProject(BaseProject):
             and custom_categories is None
             and retrieval_criteria is None
             and enable_graph is None
+            and multilingual is None
         ):
             raise ValueError(
                 "At least one parameter must be provided for update: "
                 "custom_instructions, custom_categories, retrieval_criteria, "
-                "enable_graph"
+                "enable_graph, multilingual"
             )
 
         payload = self._prepare_params(
@@ -754,6 +762,7 @@ class AsyncProject(BaseProject):
                 "custom_categories": custom_categories,
                 "retrieval_criteria": retrieval_criteria,
                 "enable_graph": enable_graph,
+                "multilingual": multilingual,
             }
         )
         response = await self._client.patch(
@@ -769,6 +778,7 @@ class AsyncProject(BaseProject):
                 "custom_categories": custom_categories,
                 "retrieval_criteria": retrieval_criteria,
                 "enable_graph": enable_graph,
+                "multilingual": multilingual,
                 "sync_type": "async",
             },
         )

mem0/configs/vector_stores/elasticsearch.py

@@ -1,7 +1,7 @@
 from collections.abc import Callable
 from typing import Any, Dict, List, Optional
 
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, ConfigDict, Field, model_validator
 
 
 class ElasticsearchConfig(BaseModel):
@@ -63,3 +63,5 @@ class ElasticsearchConfig(BaseModel):
                 f"Please input only the following fields: {', '.join(allowed_fields)}"
             )
         return values
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)

mem0/configs/vector_stores/mongodb.py

@@ -1,6 +1,6 @@
 from typing import Any, Dict, Optional
 
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, ConfigDict, Field, model_validator
 
 
 class MongoDBConfig(BaseModel):
@@ -23,3 +23,5 @@ class MongoDBConfig(BaseModel):
                 f"Please provide only the following fields: {', '.join(allowed_fields)}."
             )
         return values
+
+    model_config = ConfigDict(arbitrary_types_allowed=False)

mem0/configs/vector_stores/neptune.py

@@ -5,7 +5,7 @@ This module provides configuration settings for integrating with Amazon Neptune
 as a vector store backend for Mem0's memory layer.
 """
 
-from pydantic import BaseModel, Field
+from pydantic import BaseModel, ConfigDict, Field
 
 
 class NeptuneAnalyticsConfig(BaseModel):
@@ -22,6 +22,4 @@ class NeptuneAnalyticsConfig(BaseModel):
     collection_name: str = Field("mem0", description="Default name for the collection")
     endpoint: str = Field("endpoint", description="Graph ID for the runtime")
 
-    model_config = {
-        "arbitrary_types_allowed": False,
-    }
+    model_config = ConfigDict(arbitrary_types_allowed=False)

mem0/configs/vector_stores/opensearch.py

@@ -1,6 +1,6 @@
 from typing import Any, Dict, Optional, Type, Union
 
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, ConfigDict, Field, model_validator
 
 
 class OpenSearchConfig(BaseModel):
@@ -39,3 +39,5 @@ class OpenSearchConfig(BaseModel):
                 f"Extra fields not allowed: {', '.join(extra_fields)}. Allowed fields: {', '.join(allowed_fields)}"
             )
         return values
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)

mem0/configs/vector_stores/pgvector.py

@@ -1,6 +1,6 @@
 from typing import Any, Dict, Optional
 
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, ConfigDict, Field, model_validator
 
 
 class PGVectorConfig(BaseModel):
@@ -50,3 +50,5 @@ class PGVectorConfig(BaseModel):
                 f"Extra fields not allowed: {', '.join(extra_fields)}. Please input only the following fields: {', '.join(allowed_fields)}"
             )
         return values
+
+    model_config = ConfigDict(arbitrary_types_allowed=True)

mem0/configs/vector_stores/supabase.py

@@ -1,7 +1,7 @@
 from enum import Enum
 from typing import Any, Dict, Optional
 
-from pydantic import BaseModel, Field, model_validator
+from pydantic import BaseModel, ConfigDict, Field, model_validator
 
 
 class IndexMethod(str, Enum):
@@ -42,3 +42,5 @@ class SupabaseConfig(BaseModel):
                 f"Extra fields not allowed: {', '.join(extra_fields)}. Please input only the following fields: {', '.join(allowed_fields)}"
             )
         return values
+
+    model_config = ConfigDict(arbitrary_types_allowed=False)

mem0/configs/vector_stores/valkey.py

@@ -1,15 +1,31 @@
-from pydantic import BaseModel
+from typing import Any, Dict
+
+from pydantic import BaseModel, ConfigDict, Field, model_validator
 
 
 class ValkeyConfig(BaseModel):
     """Configuration for Valkey vector store."""
 
-    valkey_url: str
-    collection_name: str
-    embedding_model_dims: int
-    timezone: str = "UTC"
-    index_type: str = "hnsw"  # Default to HNSW, can be 'hnsw' or 'flat'
-    # HNSW specific parameters with recommended defaults
-    hnsw_m: int = 16  # Number of connections per layer (default from Valkey docs)
-    hnsw_ef_construction: int = 200  # Search width during construction
-    hnsw_ef_runtime: int = 10  # Search width during queries
+    valkey_url: str = Field(..., description="Valkey server URL (e.g., redis://localhost:6379)")
+    collection_name: str = Field(..., description="Name of the index / collection")
+    embedding_model_dims: int = Field(..., description="Dimensions of the embedding model")
+    timezone: str = Field("UTC", description="Timezone for timestamp handling")
+    index_type: str = Field("hnsw", description="Index type: 'hnsw' (default) or 'flat'")
+    hnsw_m: int = Field(16, description="HNSW: number of connections per layer")
+    hnsw_ef_construction: int = Field(200, description="HNSW: search width during index construction")
+    hnsw_ef_runtime: int = Field(10, description="HNSW: search width during queries")
+
+    @model_validator(mode="before")
+    @classmethod
+    def validate_extra_fields(cls, values: Dict[str, Any]) -> Dict[str, Any]:
+        allowed_fields = set(cls.model_fields.keys())
+        input_fields = set(values.keys())
+        extra_fields = input_fields - allowed_fields
+        if extra_fields:
+            raise ValueError(
+                f"Extra fields not allowed: {', '.join(extra_fields)}. "
+                f"Please input only the following fields: {', '.join(allowed_fields)}"
+            )
+        return values
+
+    model_config = ConfigDict(arbitrary_types_allowed=False)

mem0/vector_stores/qdrant.py

@@ -1,8 +1,10 @@
 import logging
+import re
 from typing import Optional
 
 from qdrant_client import QdrantClient
 from qdrant_client.models import (
+    DatetimeRange,
     Distance,
     FieldCondition,
     Filter,
@@ -139,6 +141,23 @@ class Qdrant(VectorStoreBase):
         ]
         self.client.upsert(collection_name=self.collection_name, points=points)
 
+    # ISO 8601 datetime pattern for detecting datetime strings in range filters
+    _ISO_DATETIME_RE = re.compile(
+        r"^\d{4}-\d{2}-\d{2}"  # date part
+        r"([T ]\d{2}:\d{2}(:\d{2})?"  # optional time part
+        r"(\.\d+)?"  # optional fractional seconds
+        r"(Z|[+-]\d{2}:?\d{2})?"  # optional timezone
+        r")?$"
+    )
+
+    @staticmethod
+    def _is_datetime_range(range_kwargs: dict) -> bool:
+        """Check if all values in range kwargs are ISO datetime strings."""
+        return all(
+            isinstance(v, str) and Qdrant._ISO_DATETIME_RE.match(v)
+            for v in range_kwargs.values()
+        )
+
     def _build_field_condition(self, key: str, value) -> Optional[FieldCondition]:
         """
         Build a single FieldCondition from a key-value filter pair.
@@ -177,6 +196,13 @@ class Qdrant(VectorStoreBase):
                     f"Use AND to combine them as separate conditions."
                 )
             range_kwargs = {op: value[op] for op in range_ops if op in value}
+            if self._is_datetime_range(range_kwargs):
+                try:
+                    return FieldCondition(key=key, range=DatetimeRange(**range_kwargs))
+                except (ValueError, TypeError) as e:
+                    raise ValueError(
+                        f"Invalid datetime value in range filter for field '{key}': {e}"
+                    ) from e
             return FieldCondition(key=key, range=Range(**range_kwargs))
         elif "eq" in value:
             return FieldCondition(key=key, match=MatchValue(value=value["eq"]))

openclaw/CHANGELOG.md

@@ -2,6 +2,17 @@
 
 All notable changes to the `@mem0/openclaw-mem0` plugin will be documented in this file.
 
+## [1.0.1] - 2026-04-02
+
+### Added
+- **CD workflow**: Added continuous deployment workflow for `@mem0/openclaw-mem0` with OIDC trusted publishing ([#4672](https://github.com/mem0ai/mem0/pull/4672))
+- **Plugin configuration manifest**: Added `compat` and `build` metadata to `package.json` specifying minimum gateway version and OpenClaw SDK compatibility (`>=2026.3.24-beta.2`) ([#4667](https://github.com/mem0ai/mem0/pull/4667))
+- **LICENSE**: Added Apache-2.0 license file to the package ([#4667](https://github.com/mem0ai/mem0/pull/4667))
+
+### Fixed
+- **Dream gate correctness**: Fixed cheap-first ordering, session isolation, and verified completion in the dream gate memory consolidation pipeline ([#4666](https://github.com/mem0ai/mem0/pull/4666))
+- **Graceful startup without API key**: Plugin now starts gracefully when no API key is configured instead of crashing on init ([#4669](https://github.com/mem0ai/mem0/pull/4669))
+
 ## [1.0.0] - 2026-04-01
 
 ### Added

openclaw/config.ts

@@ -4,33 +4,10 @@
 
 import type { Mem0Config, Mem0Mode } from "./types.ts";
 
-// ============================================================================
-// Env Var Resolution
-// ============================================================================
-
-function resolveEnvVars(value: string): string {
-  return value.replace(/\$\{([^}]+)\}/g, (_, envVar) => {
-    const envValue = process.env[envVar];
-    if (!envValue) {
-      throw new Error(`Environment variable ${envVar} is not set`);
-    }
-    return envValue;
-  });
-}
-
-function resolveEnvVarsDeep(obj: Record<string, unknown>): Record<string, unknown> {
-  const result: Record<string, unknown> = {};
-  for (const [key, value] of Object.entries(obj)) {
-    if (typeof value === "string") {
-      result[key] = resolveEnvVars(value);
-    } else if (value && typeof value === "object" && !Array.isArray(value)) {
-      result[key] = resolveEnvVarsDeep(value as Record<string, unknown>);
-    } else {
-      result[key] = value;
-    }
-  }
-  return result;
-}
+// NOTE: No process.env access in this module. OpenClaw resolves ${VAR}
+// syntax in openclaw.json before passing pluginConfig to register().
+// Plugin-side env var resolution was removed to clear OpenClaw's
+// security scanner warning ("credential harvesting" pattern).
 
 // ============================================================================
 // Default Custom Instructions & Categories
@@ -200,18 +177,16 @@ export const mem0ConfigSchema = {
     // The plugin should register successfully and log a setup message.
     const needsSetup = mode === "platform" && (typeof cfg.apiKey !== "string" || !cfg.apiKey);
 
-    // Resolve env vars in oss config
+    // OpenClaw resolves ${VAR} in pluginConfig before register() — no plugin-side expansion needed
     let ossConfig: Mem0Config["oss"];
     if (cfg.oss && typeof cfg.oss === "object" && !Array.isArray(cfg.oss)) {
-      ossConfig = resolveEnvVarsDeep(
-        cfg.oss as Record<string, unknown>,
-      ) as unknown as Mem0Config["oss"];
+      ossConfig = cfg.oss as Mem0Config["oss"];
     }
 
     return {
       mode,
       apiKey:
-        typeof cfg.apiKey === "string" ? resolveEnvVars(cfg.apiKey) : undefined,
+        typeof cfg.apiKey === "string" ? cfg.apiKey : undefined,
       userId:
         typeof cfg.userId === "string" && cfg.userId ? cfg.userId : "default",
       orgId: typeof cfg.orgId === "string" ? cfg.orgId : undefined,

openclaw/package.json

@@ -1,9 +1,14 @@
 {
   "name": "@mem0/openclaw-mem0",
-  "version": "1.0.0",
+  "version": "1.0.2",
   "type": "module",
   "description": "Mem0 memory backend for OpenClaw — platform or self-hosted open-source",
   "license": "Apache-2.0",
+  "repository": {
+    "type": "git",
+    "url": "https://github.com/mem0ai/mem0",
+    "directory": "openclaw"
+  },
   "keywords": [
     "openclaw",
     "plugin",

server/main.py

@@ -124,6 +124,11 @@ class MemoryCreate(BaseModel):
     prompt: Optional[str] = Field(None, description="Custom prompt to use for fact extraction.")
 
 
+class MemoryUpdate(BaseModel):
+    text: str = Field(..., description="New content to update the memory with.")
+    metadata: Optional[Dict[str, Any]] = Field(None, description="Metadata to update.")
+
+
 class SearchRequest(BaseModel):
     query: str = Field(..., description="Search query.")
     user_id: Optional[str] = None
@@ -199,18 +204,18 @@ def search_memories(search_req: SearchRequest, _api_key: Optional[str] = Depends
 
 
 @app.put("/memories/{memory_id}", summary="Update a memory")
-def update_memory(memory_id: str, updated_memory: Dict[str, Any], _api_key: Optional[str] = Depends(verify_api_key)):
+def update_memory(memory_id: str, updated_memory: MemoryUpdate, _api_key: Optional[str] = Depends(verify_api_key)):
     """Update an existing memory with new content.
-    
+
     Args:
         memory_id (str): ID of the memory to update
-        updated_memory (str): New content to update the memory with
-        
+        updated_memory (MemoryUpdate): New content and optional metadata to update the memory with
+
     Returns:
         dict: Success message indicating the memory was updated
     """
     try:
-        return MEMORY_INSTANCE.update(memory_id=memory_id, data=updated_memory)
+        return MEMORY_INSTANCE.update(memory_id=memory_id, data=updated_memory.text, metadata=updated_memory.metadata)
     except Exception as e:
         logging.exception("Error in update_memory:")
         raise HTTPException(status_code=500, detail=str(e))

tests/test_server_auth.py

@@ -94,7 +94,7 @@ class TestAuthDisabled:
         assert resp.status_code == 200
 
     def test_update_memory_without_key(self):
-        resp = self.client.put("/memories/mem-1", json={"data": "updated"})
+        resp = self.client.put("/memories/mem-1", json={"text": "updated"})
         assert resp.status_code == 200
 
     def test_history_without_key(self):
@@ -276,7 +276,7 @@ class TestAuthEnabled:
         assert resp.status_code == 200
 
     def test_update_memory_with_key(self):
-        resp = self._authed("PUT", "/memories/mem-1", json={"data": "updated"})
+        resp = self._authed("PUT", "/memories/mem-1", json={"text": "updated"})
         assert resp.status_code == 200
 
     def test_history_with_key(self):
@@ -346,7 +346,7 @@ class TestAuthenticatedCRUDFlow:
         self.mock.search.assert_called_once()
 
         # 5. Update
-        resp = self._authed("PUT", "/memories/mem-1", json={"data": "updated content"})
+        resp = self._authed("PUT", "/memories/mem-1", json={"text": "updated content"})
         assert resp.status_code == 200
         self.mock.update.assert_called_once()
 

tests/test_server_params.py

@@ -505,3 +505,59 @@ class TestCallSignatureMatch:
         assert resp.status_code == 200
         _, kwargs = mock_memory.search.call_args
         assert kwargs["query"] == "food"
+
+
+# ===========================================================================
+# MemoryUpdate: text and metadata forwarding (fix for #3933)
+# ===========================================================================
+
+class TestUpdateMemory:
+    """Verify that PUT /memories/{id} extracts text and metadata from the
+    request body and forwards them correctly to Memory.update()."""
+
+    def test_text_forwarded_as_data(self, client, mock_memory):
+        resp = client.put("/memories/mem-1", json={"text": "Likes tennis"})
+        assert resp.status_code == 200
+        _, kwargs = mock_memory.update.call_args
+        assert kwargs["data"] == "Likes tennis"
+
+    def test_metadata_forwarded(self, client, mock_memory):
+        resp = client.put("/memories/mem-1", json={
+            "text": "Likes tennis",
+            "metadata": {"category": "sports"},
+        })
+        assert resp.status_code == 200
+        _, kwargs = mock_memory.update.call_args
+        assert kwargs["metadata"] == {"category": "sports"}
+
+    def test_metadata_omitted_passes_none(self, client, mock_memory):
+        resp = client.put("/memories/mem-1", json={"text": "Likes tennis"})
+        assert resp.status_code == 200
+        _, kwargs = mock_memory.update.call_args
+        assert kwargs["metadata"] is None
+
+    def test_missing_text_returns_422(self, client):
+        """text is required — omitting it should fail validation."""
+        resp = client.put("/memories/mem-1", json={"metadata": {"k": "v"}})
+        assert resp.status_code == 422
+
+    def test_dict_not_passed_as_data(self, client, mock_memory):
+        """Regression test for #3933: the entire dict must NOT be passed as data."""
+        resp = client.put("/memories/mem-1", json={"text": "updated content"})
+        assert resp.status_code == 200
+        _, kwargs = mock_memory.update.call_args
+        assert isinstance(kwargs["data"], str)
+
+
+class TestUpdateOpenAPISchema:
+    """Verify the MemoryUpdate schema appears in the OpenAPI docs."""
+
+    def test_update_schema_includes_text(self, client):
+        schema = client.get("/openapi.json").json()
+        update_props = schema["components"]["schemas"]["MemoryUpdate"]["properties"]
+        assert "text" in update_props
+
+    def test_update_schema_includes_metadata(self, client):
+        schema = client.get("/openapi.json").json()
+        update_props = schema["components"]["schemas"]["MemoryUpdate"]["properties"]
+        assert "metadata" in update_props

tests/vector_stores/test_qdrant.py

@@ -6,6 +6,7 @@ from unittest.mock import MagicMock, patch
 
 from qdrant_client import QdrantClient
 from qdrant_client.models import (
+    DatetimeRange,
     Distance,
     FieldCondition,
     Filter,
@@ -814,3 +815,111 @@ class TestQdrantEnhancedFilters(unittest.TestCase):
         self.assertIsNotNone(result.must_not)
         # Deduplicated: NOT wins, $not is skipped — exactly 1 entry
         self.assertEqual(len(result.must_not), 1)
+
+
+class TestQdrantDatetimeRangeFilters(unittest.TestCase):
+    """Tests for datetime range filter support (issue #4591)."""
+
+    def setUp(self):
+        self.client_mock = MagicMock(spec=QdrantClient)
+        self.qdrant = Qdrant(
+            collection_name="test_collection",
+            embedding_model_dims=128,
+            client=self.client_mock,
+        )
+
+    def test_iso_datetime_gte_lte_uses_datetime_range(self):
+        """ISO datetime strings in range filters should use DatetimeRange."""
+        cond = self.qdrant._build_field_condition(
+            "created_at", {"gte": "2025-01-01T00:00:00Z", "lte": "2025-12-31T23:59:59Z"}
+        )
+        self.assertIsInstance(cond, FieldCondition)
+        self.assertIsInstance(cond.range, DatetimeRange)
+        self.assertIsNotNone(cond.range.gte)
+        self.assertIsNotNone(cond.range.lte)
+
+    def test_iso_date_only_uses_datetime_range(self):
+        """Date-only strings (YYYY-MM-DD) should also use DatetimeRange."""
+        cond = self.qdrant._build_field_condition(
+            "created_at", {"gte": "2025-01-01", "lt": "2025-02-01"}
+        )
+        self.assertIsInstance(cond.range, DatetimeRange)
+
+    def test_iso_datetime_with_offset_uses_datetime_range(self):
+        """Datetime with timezone offset should use DatetimeRange."""
+        cond = self.qdrant._build_field_condition(
+            "updated_at", {"gt": "2025-06-15T10:30:00+05:30"}
+        )
+        self.assertIsInstance(cond.range, DatetimeRange)
+
+    def test_numeric_range_still_uses_range(self):
+        """Numeric values should still use Range (not DatetimeRange)."""
+        cond = self.qdrant._build_field_condition(
+            "priority", {"gte": 5, "lte": 10}
+        )
+        self.assertIsInstance(cond.range, Range)
+        self.assertEqual(cond.range.gte, 5)
+        self.assertEqual(cond.range.lte, 10)
+
+    def test_float_range_still_uses_range(self):
+        """Float values should still use Range."""
+        cond = self.qdrant._build_field_condition(
+            "score", {"gt": 0.5, "lt": 0.9}
+        )
+        self.assertIsInstance(cond.range, Range)
+
+    def test_datetime_range_via_create_filter(self):
+        """DatetimeRange should work through _create_filter."""
+        result = self.qdrant._create_filter(
+            {"created_at": {"gte": "2025-01-01T00:00:00Z", "lte": "2025-12-31T23:59:59Z"}}
+        )
+        self.assertIsInstance(result, Filter)
+        self.assertEqual(len(result.must), 1)
+        self.assertIsInstance(result.must[0].range, DatetimeRange)
+
+    def test_malformed_datetime_raises_with_field_context(self):
+        """Malformed date-like string should raise ValueError with field name."""
+        with self.assertRaises(ValueError) as ctx:
+            self.qdrant._build_field_condition(
+                "created_at", {"gte": "2025-13-45"}
+            )
+        self.assertIn("created_at", str(ctx.exception))
+
+    def test_mixed_datetime_and_numeric_raises_error(self):
+        """Mixed datetime string + numeric value in same range should raise an error.
+
+        When not all values are datetime strings, _is_datetime_range returns False
+        and Range receives a string, causing a Pydantic ValidationError.
+        """
+        from pydantic import ValidationError
+
+        with self.assertRaises(ValidationError):
+            self.qdrant._build_field_condition(
+                "field", {"gte": "2025-01-01", "lte": 100}
+            )
+
+    def test_iso_datetime_with_fractional_seconds(self):
+        """Fractional seconds should use DatetimeRange."""
+        cond = self.qdrant._build_field_condition(
+            "created_at", {"gte": "2025-01-01T00:00:00.123456Z"}
+        )
+        self.assertIsInstance(cond.range, DatetimeRange)
+
+    def test_iso_datetime_space_separated(self):
+        """Space-separated datetime should use DatetimeRange."""
+        cond = self.qdrant._build_field_condition(
+            "created_at", {"gte": "2025-01-01 10:30:00"}
+        )
+        self.assertIsInstance(cond.range, DatetimeRange)
+
+    def test_datetime_with_numeric_mixed_filters(self):
+        """Datetime and numeric range filters can coexist in same query."""
+        result = self.qdrant._create_filter({
+            "created_at": {"gte": "2025-01-01"},
+            "priority": {"gte": 5},
+        })
+        self.assertIsInstance(result, Filter)
+        self.assertEqual(len(result.must), 2)
+        types = {type(c.range) for c in result.must}
+        self.assertIn(DatetimeRange, types)
+        self.assertIn(Range, types)