Claude-Mem

Install

/plugin marketplace add thedotmack/claude-mem
/plugin install claude-mem

This is third-party code. Review the repository files before installing.

What it does

The plugin uses lifecycle hooks to record what the agent did and what was decided, storing it in SQLite. In a new session context from past sessions is injected automatically. Memory search runs through the mem-search skill and the search, timeline and get_observations MCP tools, with hybrid search backed by Chroma. It includes a web viewer for the memory stream and tags to exclude sensitive content.

Who it is for. Developers running long projects in Claude Code who are tired of re-explaining context.

Example request

Did we already fix the auth bug? Search memory for how we solved it

Limitations

Per the README the project is renamed Grok Mem, but the package is still claude-mem. The installer asks you to sign in and uses hosted memory by default, which you can skip with --provider or CLAUDE_MEM_ONLINE_OPTIN=false. npm install -g claude-mem installs only the SDK without hooks. Vector search needs uv, and the worker is managed by Bun.

How to disable. Remove the claude-mem plugin in Claude Code. Settings live in ~/.claude-mem/settings.json.

Security check

• Hooks record agent actions and tool output
• Runs a local worker with an HTTP API
• Offers hosted memory storage by default

README in short

The README covers installing via npx claude-mem install for Claude Code, OpenCode, Antigravity and others, and via the plugin marketplace. The architecture includes five lifecycle hooks, a local worker with an HTTP API, SQLite and Chroma. Search follows a three-step pattern to save tokens. Apache 2.0 license, docs at docs.claude-mem.ai.

SKILL.md

---
name: mem-search
description: Search claude-mem's persistent cross-session memory database. Use when user asks "did we already solve this?", "how did we do X last time?", or needs work from previous sessions.
---

# Memory Search

Search past work across all sessions. Simple workflow: search -> filter -> fetch -> (rarely) disclose raw tool I/O.

## When to Use

Use when users ask about PREVIOUS sessions (not current conversation):

- "Did we already fix this?"
- "How did we solve X last time?"
- "What happened last week?"

## Layered Workflow (ALWAYS Follow)

**NEVER fetch full details without filtering first. 10x token savings.**

### Step 1: Search - Get Index with IDs

Use the `search` MCP tool:

```
search(query="authentication", limit=20, project="my-project")
```

**Returns:** Table with IDs, timestamps, types, titles (~50-100 tokens/result)

```
| ID | Time | T | Title | Read |
|----|------|---|-------|------|
| #11131 | 3:48 PM | 🟣 | Added JWT authentication | ~75 |
| #10942 | 2:15 PM | 🔴 | Fixed auth token expiration | ~50 |
```

**Parameters:**

- `query` (string) - Search term
- `limit` (number) - Max results, default 20, max 100
- `project` (string) - Project name filter
- `type` (string, optional) - "observations", "sessions", or "prompts"
- `obs_type` (string, optional) - Comma-separated: bugfix, feature, decision, discovery, change
- `dateStart` (string, optional) - YYYY-MM-DD or epoch ms
- `dateEnd` (string, optional) - YYYY-MM-DD or epoch ms
- `offset` (number, optional) - Skip N results
- `orderBy` (string, optional) - "date_desc" (default), "date_asc", "relevance"

### Step 2: Timeline - Get Context Around Interesting Results

Use the `timeline` MCP tool:

```
timeline(anchor=11131, depth_before=3, depth_after=3, project="my-project")
```

Or find anchor automatically from query:

Related