MyAgentHubs/aimemo

English | 中文
Zero-dependency MCP memory server for AI agents — persistent, searchable, local-first, single binary.
🧠 Why aimemo
- **No infra to babysit.** Single Go binary. No Docker, no Node.js runtime, no cloud account, no API keys. brew install in 30 seconds.
- **Memory stays with the project.** Stored in .aimemo/ next to your code — commit it to git or add it to .gitignore. Switch branches; memory follows the directory.
- **Claude picks up exactly where it left off.** memory_context fires automatically on every session start. Claude sees what it was doing, what was blocked, what decisions were made. You stop repeating yourself.
- **Full-text search that ranks correctly.** FTS5 + BM25 scoring weighted by recency and access frequency. Relevant memories surface first; old noise fades naturally.
- **Concurrent sessions, no corruption.** SQLite WAL mode lets multiple Claude windows write simultaneously without locking each other out.
- **You stay in control.** Every tool Claude has, you have from the terminal. Inspect, edit, retract, export. Your memory is readable Markdown or JSON — never locked in a proprietary format.
⚡ Quick Start
Restart Claude Code. On the next session, Claude will automatically load project context.
Quick Start for OpenClaw
If you're using OpenClaw skills, see the OpenClaw Integration section below for per-skill memory isolation.
🔧 How It Works
aimemo serve runs as a stdio MCP server; Claude Code manages the process lifecycle, so there is nothing to keep alive yourself. When Claude starts a session it calls memory_context to load relevant prior context; as it works it calls memory_store and memory_link to record decisions and relationships. You can call aimemo search, aimemo list, or aimemo get at any time to read or edit the same data from your terminal. Everything lives in a SQLite database inside .aimemo/, discovered by walking up from the current directory — the same way Git finds .git/.
🛠 MCP Tools
| Tool | Description | When Claude calls it |
|------|-------------|----------------------|
| memory_context | Returns ranked, recent observations for the current project | Session start — automatic |
| memory_store | Saves an observation (fact, decision, journal entry, TODO) | After completing a task or making a decision |
| memory_search | Full-text search across all observations, BM25-ranked | When it needs to recall something specific |
| memory_forget | Soft-deletes an observation by ID | When instructed to discard something |
| memory_link | Creates a named relationship between two observations | When it identifies a dependency or connection |
All tool schemas total under 2,000 tokens. Each call has a hard 5-second timeout — the server never stalls your session. Empty-state queries return in under 5 ms.
📋 CLI Reference
Setup
| Command | Description |
|---------|-------------|
| aimemo init | Create .aimemo/ in the current directory |
| aimemo serve | Start the MCP stdio server (called by Claude Code automatically) |
| aimemo doctor | Verify DB health, FTS5 support, WAL mode, and MCP registration |
Memory
| Command | Description |
|---------|-------------|
| aimemo add [observations...] [--tag] | Add an entity with one or more observations |
| aimemo observe | Add a new observation to an existing entity |
| aimemo retract | Remove a specific observation from an entity |
| aimemo forget [--permanent] | Soft-delete an entity (recoverable); use --permanent to hard-delete |