JDSS/mem0
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

docs: align agent plugin guides with shared runtime behavior (#7269)

Browse Source
This commit is contained in:
Kartik
2026-09-09 01:03:26 +05:30
committed by GitHub
parent 73e7b8763a
commit 02f7a9b2c4
17 changed files with 146 additions and 63 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/integrations/antigravity.mdx
+7 -1
View File
@@ -78,7 +78,7 @@ The plugin translates Antigravity events into the shared Mem0 capture lifecycle.
|------|-------|-------------|
| **Invocation** | `PreInvocation` | Initializes the first invocation and recovers pending capture |
| **Post-tool** | `PostToolUse` | Records useful tool results and failures |
| **Stop** | `Stop` | Captures the completed exchange for a later session |
| **Stop** | `Stop` | Reads completed transcript messages and starts a background flush |
Recall is explicit through `search_memories` and the search skill. The current Antigravity adapter does not inject query-specific memory during `PreInvocation` because that event does not include the user's prompt.
@@ -106,6 +106,12 @@ MEM0_CWD="$PWD" agy
The adapter uses `MEM0_CWD` only when Antigravity omits the workspace. If neither value is available, it skips recall and capture instead of writing memories under an incorrect repository scope.
## Search and capture
The local `search_memories` tool accepts `query`, `top_k`, `category`, `scope` (`repo`, `dir`, or `mine`), and optional `run_id` with every scope. Use a known session ID to recall memories saved in that session; omit it to search across sessions. See [search scopes](/integrations/claude-code#search-scope) for the shared Python search contract, including legacy repository memory compatibility.
Captured prompts and responses retain their full redacted text without a per-message character cutoff. Large extraction inputs are split across requests without dropping message text; recall output and tool-result previews have separate limits.
## Troubleshooting
- **No tools appearing**: Restart your Antigravity session after installation
docs/integrations/claude-code.mdx
+6 -6
View File
@@ -42,14 +42,14 @@ claude plugin uninstall mem0@mem0-plugins # uninstall the plugin (keeps the
Once installed, memory works without any action from you:
- **Capture** happens in the background as you work. Hooks save user messages, Claude's answers, changed files, and test/build results locally. Nothing calls a model or slows your session.
- **Recall** happens automatically before Claude's first response in a new session. The plugin searches your memories with your prompt and injects up to five relevant ones.
- **Capture** happens in the background as you work. Hooks save user messages, Claude's answers, changed files, and test/build results locally. Capture records evidence locally; memory extraction runs through Mem0 in a background worker.
- **Recall** happens automatically before Claude's first response in a new session. If the first prompt has at least 20 characters, the plugin searches with that prompt and injects up to five relevant memories. For shorter prompts or later questions, use explicit search.
### Commands
| Command | What it does |
| --- | --- |
| `/mem0:search` | Search memories from earlier sessions. Supports `--top-k <n>`, `--category <name>`, and `--scope <repo\|dir\|mine>`. |
| `/mem0:search` | Search memories from earlier sessions. Supports `--top-k <n>`, `--category <name>`, `--scope <repo\|dir\|mine>`, and `--run-id <session-id>`. |
| `/mem0:status` | Check if memory is working: config, capture state, pending flushes, API key validity. |
| `/mem0:forget` | Delete your memories for this repo (shared project memory stays unless you pass `--include-project-memory`). |
| `/mem0:pause` | Pause memory capture. |
@@ -60,7 +60,7 @@ Categories for `--category`: `project_knowledge`, `decisions_and_constraints`, `
### Search tool
After the automatic first-prompt search, Claude can also call `search_memories` with a specific question, and you can run `/mem0:search` yourself. Explicit searches return up to 3 results by default (configurable to 20). All results are capped at 4,000 characters.
After the automatic first-prompt search, Claude can also call `search_memories` with a specific question, and you can run `/mem0:search` yourself. Explicit searches return up to 3 results by default (configurable to 20). The combined search output is capped at 4,000 characters by default, configurable with `max_context_chars`. This recall limit does not truncate captured messages sent for extraction.
### Sidekick agent
@@ -80,7 +80,7 @@ At startup, Sidekick receives the memories already recalled for its parent sessi
The plugin follows a simple cycle: capture during a session, extract memories in the background, recall in the next session.
<Frame>
<img src="/images/plugin-sequence.svg" alt="Sequence diagram: session start triggers first-prompt search, hooks capture activity during the session, a background worker extracts memories after every five exchanges or on idle/exit, and the next session recalls them." />
<img src="/images/plugin-sequence.svg" alt="Sequence diagram: the first user prompt triggers search, hooks capture activity during the session, a background worker extracts memories after every five exchanges or on idle/exit, and the next session recalls them." />
</Frame>
**Step by step:**
@@ -153,7 +153,7 @@ Breaking update. Your memories carry over, most local config does not.
- **Commands replaced.** Old commands replaced by `/mem0:search`, `/mem0:status`, `/mem0:forget`, `/mem0:pause`, `/mem0:resume`, `/mem0:remember`.
- **MCP server replaced.** Nine read/write tools replaced by the single read-only `search_memories` tool.
- **Local config ignored.** `~/.mem0/settings.json` and per-project `mem0.md` files are no longer read.
- **Old memories searchable, not by category.** Normal search finds pre-upgrade memories, but category filters do not.
- **Old memories remain searchable.** Pre-upgrade memories may use different categories. Omit category filters if an older memory is missing from the results.
```bash
claude plugin marketplace update mem0-plugins
docs/integrations/codex.mdx
+14 -8
View File
@@ -3,7 +3,7 @@ title: Codex
description: "Add persistent memory to OpenAI Codex with automatic capture, automatic recall, a search tool, and six memory skills."
---
Add persistent memory to [**OpenAI Codex**](https://openai.com/index/codex/) with the Mem0 plugin. Codex forgets everything between tasks. This plugin fixes that by connecting to Mem0's cloud memory layer via MCP, automatically capturing learnings at key lifecycle points, and retrieving relevant context before every response.
Add persistent memory to [**OpenAI Codex**](https://openai.com/index/codex/) with the Mem0 plugin. Codex forgets everything between tasks. This plugin fixes that by connecting to Mem0's cloud memory layer via MCP, automatically capturing learnings at key lifecycle points, and retrieving relevant context on the first prompt of a session. Codex can use the search tool for recall later in the session.
<Info>Current plugin version: `0.3.1`.</Info>
@@ -79,7 +79,7 @@ bearer_token_env_var = "MEM0_API_KEY"
Make sure `MEM0_API_KEY` is exported in the shell you launch Codex from, then restart Codex.
This gives you the MCP tools but not the lifecycle hooks or SDK skill.
This gives you the hosted MCP tools but not the plugin's lifecycle hooks or six memory skills.
### Managing the Plugin
@@ -115,7 +115,7 @@ Lifecycle hooks that shell out to local scripts (Option A) are not applicable in
| Native subagent memory lifecycle | Yes | No |
| Memory skills | 6 | No |
Codex plugins cannot currently bundle a named custom agent. If you define project or user agents under `.codex/agents/` or `~/.codex/agents/`, the full Mem0 plugin gives every native subagent the parent turn's retrieved memory context and records its completed result.
Mem0's Codex package does not bundle a named custom agent. If you define project or user agents under `.codex/agents/` or `~/.codex/agents/`, the full Mem0 plugin gives every native subagent the parent turn's retrieved memory context and records its completed result.
## Direct MCP tools
@@ -139,8 +139,8 @@ Option A registers the hooks with the plugin. No separate hook installer or glob
| Hook | Event | What it does |
|------|-------|-------------|
| **Session start** | `SessionStart` | Loads prior memories and displays status banner |
| **User prompt** | `UserPromptSubmit` | Searches relevant memories before each message |
| **Session start** | `SessionStart` | Initializes the project session and recovers pending capture |
| **User prompt** | `UserPromptSubmit` | Records each prompt; searches on the first prompt when it has at least 20 characters |
| **Post-tool** | `PostToolUse` | Records useful tool outcomes for the completed exchange |
| **Subagent start** | `SubagentStart` | Reuses the parent turn's retrieved memory context in the child |
| **Subagent stop** | `SubagentStop` | Records the child transcript path and completed result |
@@ -148,18 +148,18 @@ Option A registers the hooks with the plugin. No separate hook installer or glob
| **Pre-compact** | `PreCompact` | Flushes pending capture before context compaction |
| **Session end** | `SessionEnd` | Flushes any remaining capture in the background |
What you type is stored as yours. What Codex produces (session summaries and compaction summaries) is stored as the assistant's, so its suggestions never become your stated preferences.
What you type is stored as yours. Codex's captured responses are stored as the assistant's, so its suggestions never become your stated preferences.
## Example Workflow
```text
# Task 1: Setting up a new service
You: Create a REST API for the notifications service using Express and TypeScript.
You: Create a REST API for the notifications service using Express and TypeScript. Prefer explicit error types over generic catch-all handlers.
# Codex searches memories, finds your preferences from prior tasks.
# Mem0 stores what you said as yours:
# - Your preference: "Prefers explicit error types over generic catch-all"
# ...and what Codex did as the assistant's, in the session summary:
# ...and completed work reported by Codex as the assistant's:
# - Decision: "Notifications service uses Express + TypeScript + Zod validation"
# - Convention: "All API routes follow /api/v1/{resource} pattern"
@@ -170,6 +170,12 @@ You: Add WebSocket support for real-time notification delivery.
# Follows the same patterns established in the first task.
```
## Search and capture
The local `search_memories` tool accepts `query`, `top_k`, `category`, `scope` (`repo`, `dir`, or `mine`), and optional `run_id` with every scope. Use a known session ID to recall memories saved in that session; omit it to search across sessions. See [search scopes](/integrations/claude-code#search-scope) for the shared Python search contract, including legacy repository memory compatibility.
Captured prompts and responses retain their full redacted text without a per-message character cutoff. Large extraction inputs are split across requests without dropping message text; recall output and tool-result previews have separate limits.
## Troubleshooting
- **"Connection failed"**: Verify `MEM0_API_KEY` is set: `echo $MEM0_API_KEY`
docs/integrations/cursor.mdx
+7 -1
View File
@@ -139,7 +139,7 @@ Cursor's `subagentStart` hook also cannot inject parent context. The bundled Sid
```text
# Session 1: Debugging a performance issue
You: The API endpoint /users is taking 3 seconds. Help me optimize it.
You: The API endpoint /users is taking 3 seconds. Help me optimize it. Prefer query-level fixes over caching.
# Cursor agent searches memories, proceeds with investigation.
# Mem0 stores what you said as yours:
@@ -155,6 +155,12 @@ You: The /orders endpoint is also slow, same pattern as before.
# Immediately checks for N+1 queries and missing indexes.
```
## Search and capture
The local `search_memories` tool accepts `query`, `top_k`, `category`, `scope` (`repo`, `dir`, or `mine`), and optional `run_id` with every scope. Use a known session ID to recall memories saved in that session; omit it to search across sessions. See [search scopes](/integrations/claude-code#search-scope) for the shared Python search contract, including legacy repository memory compatibility.
Captured prompts and responses retain their full redacted text without a per-message character cutoff. Large extraction inputs are split across requests without dropping message text; recall output and tool-result previews have separate limits.
## Troubleshooting
- **"Connection failed"**: Verify `MEM0_API_KEY` is set: `echo $MEM0_API_KEY`
docs/integrations/deepseek-plugin.mdx
+2 -2
View File
@@ -18,7 +18,7 @@ The plugin provides automatic memory plus two agent-callable tools:
| `search_memory` | Recall facts from Mem0 relevant to a query |
| `add_memory` | Store a fact in Mem0 for future sessions |
Unlike file-based memory plugins, Mem0 is a managed backend: server-side extraction, semantic dedup, and conflict resolution, with the same memory reusable across every agent you connect.
Unlike file-based memory plugins, Mem0 is a managed backend: server-side extraction, semantic dedup, and conflict resolution, with memories reusable by integrations that use compatible user identities and search filters.
## How it works
@@ -108,7 +108,7 @@ For a Mem0 Platform on-prem or dedicated deployment, point `config.host` at that
| `autoRecall` | no | `true` | Recall relevant memory before model requests |
| `autoCapture` | no | `true` | Store completed human and assistant turns |
Both tools also accept optional per-call `userId`, `agentId`, and `runId` params so a single install can partition memory by entity, agent, or session; when omitted they fall back to the configured `userId`.
Both tools also accept optional per-call `userId`, `agentId`, and `runId` params so a single install can partition memory by entity, agent, or session; `userId` defaults to the configured user, while `agentId` and `runId` are omitted unless supplied. Automatic recall and capture use the configured user without an agent, repository, or session filter. Automatic capture preserves full redacted user and assistant message text without a per-message character cutoff.
## Telemetry
docs/integrations/kimi.mdx
+9 -3
View File
@@ -38,7 +38,7 @@ Run `/plugins info mem0` to confirm that the plugin, MCP server, skills, hooks,
## What you get
- **Automatic capture:** Kimi records completed exchanges locally and flushes durable project knowledge to Mem0 in the background.
- **Automatic recall:** Relevant memories are added before Kimi answers the first prompt in a session.
- **Automatic recall:** Relevant memories are added before Kimi answers the first prompt in a session, if that prompt has at least 20 characters.
- **Explicit search:** Kimi can call `search_memories` when it needs a more specific answer.
- **Six memory skills:** Search, status, remember, forget, pause, and resume use the same memory behavior as the other Mem0 coding-agent plugins.
- **Project scoping:** Memories stay attached to the repository, with separate personal and shared project lanes.
@@ -52,8 +52,8 @@ Kimi's native lifecycle events are translated into the shared Mem0 memory lifecy
| Kimi event | What Mem0 does |
| --- | --- |
| `SessionStart` | Loads recent project context |
| `UserPromptSubmit` | Searches for relevant memories before the response |
| `SessionStart` | Initializes the project session and recovers pending capture |
| `UserPromptSubmit` | Records each prompt; searches on the first prompt when it has at least 20 characters |
| `PostToolUse` / `PostToolUseFailure` | Records useful tool results and failures |
| `Stop` | Captures the completed exchange |
| `PreCompact` / `SessionEnd` | Flushes pending capture in the background |
@@ -87,6 +87,12 @@ Kimi should return `ORCHID-9274` from memory.
Run `/reload` or start a new session after enabling, disabling, or reinstalling the plugin.
## Search and capture
The local `search_memories` tool accepts `query`, `top_k`, `category`, `scope` (`repo`, `dir`, or `mine`), and optional `run_id` with every scope. Use a known session ID to recall memories saved in that session; omit it to search across sessions. See [search scopes](/integrations/claude-code#search-scope) for the shared Python search contract, including legacy repository memory compatibility.
Captured prompts and responses retain their full redacted text without a per-message character cutoff. Large extraction inputs are split across requests without dropping message text; recall output and tool-result previews have separate limits.
## Troubleshooting
| Problem | Fix |
docs/integrations/openclaw.mdx
+3 -3
View File
@@ -343,8 +343,8 @@ openclaw mem0 status --json
|-----|------|---------|-------------|
| `mode` | `"platform"` \| `"open-source"` | `"platform"` | Which backend to use |
| `userId` | `string` | OS username | Scope memories per user |
| `autoRecall` | `boolean` | `true` | Inject memories before each turn. Ignored when `skills` is configured. |
| `autoCapture` | `boolean` | `true` | Store facts after each turn. Ignored when `skills` is configured. |
| `autoRecall` | `boolean` | `true` | Inject memories before each turn, including when skills mode is configured. |
| `autoCapture` | `boolean` | `true` | Store facts after each turn, including when skills mode is configured. |
| `topK` | `number` | `5` | Max memories per recall |
| `searchThreshold` | `number` | `0.3` | Min similarity (0–1) |
@@ -443,7 +443,7 @@ If `openclaw plugins update` fails:
### Auto-Capture and Auto-Recall
Auto-capture and auto-recall are **enabled by default**. When skills mode is configured (the default after `openclaw mem0 init`), these are ignored in favor of the skills-based triage and recall protocol.
Auto-capture and auto-recall are **enabled by default**. They also run when skills mode is configured (the default after `openclaw mem0 init`). Set `autoRecall` or `autoCapture` to `false` to disable the corresponding automatic hook while using skills.
To disable either:
docs/integrations/opencode.mdx
+4 -2
View File
@@ -113,13 +113,15 @@ The plugin uses the [mem0ai](https://www.npmjs.com/package/mem0ai) TypeScript SD
| OpenCode Event | Hook | What happens |
|----------------|------|-------------|
| `config` | **Config** | Registers the `/mem0-*` slash commands (`config.command`) and adds the plugin's own `opencode-skills/` dir to OpenCode's `skills.paths` for in-place skill discovery (no copying) |
| `chat.message` | **Chat message** | Searches prior memories on session start, searches relevant memories before each prompt, auto-captures learnings periodically |
| `chat.message` | **Chat message** | Searches prior memories on session start, searches relevant memories before each prompt, sends every third qualifying user prompt for extraction |
| `tool.execute.before` | **Pre-tool** | Blocks MEMORY.md writes, steering them to the `add_memory` tool |
| `tool.execute.after` | **Post-tool** | Scans Bash errors and pre-fetches related error memories |
| `experimental.chat.messages.transform` | **Messages transform** | Injects memory context (session memories, search results, error lookups) into the prompt |
| `experimental.session.compacting` | **Compaction** | Stores session state memory, then injects prior memories into compaction context so nothing is lost |
| `experimental.session.compacting` | **Compaction** | Stores session state memory, then injects prior memories into compaction context |
| `shell.env` | **Shell env** | Exports `MEM0_USER_ID`, `MEM0_APP_ID`, `MEM0_SESSION_ID`, and `MEM0_BRANCH` to all shell executions |
Automatic capture sends the selected user prompt with its full redacted text, without a per-message character cutoff. It does not capture every prompt or the full assistant transcript. These automatic writes use user and project scope, with the session ID in `metadata.session_id`; session-scoped tools use top-level `run_id`. A session-scoped search therefore does not include automatic writes that lack `run_id`.
## Troubleshooting
- **No tools appearing**: Restart OpenCode after installing
docs/integrations/pi-agent.mdx
+6 -6
View File
@@ -11,7 +11,7 @@ Add persistent memory to [**Pi Agent**](https://pi.dev) with `@mem0/pi-agent-plu
The plugin provides:
1. **Auto-capture**: Extracts durable facts from both user and assistant messages automatically
2. **Semantic recall**: Retrieves relevant memories via the `mem0_memory` tool before each response
2. **Semantic recall**: Automatically searches project memories before each agent turn; `mem0_memory` supports additional explicit searches
3. **Monorepo-aware scoping**: Uses git root for project detection, consistent across subdirectories
4. **Confirmation dialogs**: Destructive commands ask before acting via Pi's built-in UI
5. **6 skills + 6 commands**: Essential memory management from slash commands and agent-guided workflows
@@ -117,10 +117,12 @@ Memories are scoped using Mem0's `user_id`, `app_id`, and `run_id` parameters:
| Scope | Filters | Use Case |
|-------|---------|----------|
| `project` | user_id + app_id (git root) | **Default.** Project-specific knowledge: decisions, architecture, config |
| `session` | user_id + app_id + run_id | Ephemeral context for the current session only |
| `session` | user_id + app_id + run_id | Memories saved with the current session ID (no automatic expiration) |
| `global` | user_id only | All memories across all your projects |
The `app_id` is auto-detected from the git repository root (`git rev-parse --show-toplevel`), so all subdirectories within a monorepo share the same memory pool. Falls back to the working directory name for non-git directories. The `run_id` is derived from Pi's session file path.
The `app_id` is auto-detected from the git repository root (`git rev-parse --show-toplevel`), so all subdirectories within a monorepo share the same memory pool. Falls back to the working directory name for non-git directories. The `run_id` is derived from Pi's session file path. Automatic recall and capture use project scope, regardless of `defaultScope`; automatic writes do not include `run_id`. Use session-scoped tools or commands to save and recall session-specific memories. Captured user and assistant message text is redacted without a per-message character cutoff.
Global tool operations require `/mem0-scope global` or `defaultScope: "global"` in plugin configuration. A model-supplied `scope` argument cannot enable cross-project access on its own. Empty or wildcard user, project, and session identities are rejected.
## Confirmation Dialogs
@@ -144,7 +146,7 @@ You: What do you know about my preferences?
## Troubleshooting
- **"No API key found"**: Verify `MEM0_API_KEY` is set: `echo $MEM0_API_KEY`. If empty, add it to your shell profile (see Prerequisites)
- **Extension not loading**: Check Pi startup output for errors. Run `pi -e ./src/entry.ts` from the plugin directory for verbose output
- **Extension not loading**: Check Pi startup output for errors. For a source checkout, run `pnpm build`, then `pi -e ./dist/entry.js` from the plugin directory
- **Memories not capturing**: Verify `autoCapture` is `true` (default). Check `/mem0-status` for connection health
- **Wrong project detected**: The plugin uses the git repository root as `app_id`. If not in a git repo, it falls back to the working directory name. Run `/mem0-status` to see the detected project
@@ -158,5 +160,3 @@ You: What do you know about my preferences?
</CardGroup>
<Snippet file="star-on-github.mdx" />
Global tool operations require `/mem0-scope global` or `defaultScope: "global"` in plugin configuration. A model-supplied `scope` argument cannot enable cross-project access on its own. Empty or wildcard user, project, and session identities are rejected.