# recall

Local persistent memory for AI agents without external API keys or cloud tokens. It maintains project history and manages multi-agent file locks.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 8
- Author: RecallWorks
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/RecallWorks/Recall
- Updated: 2026-06-16
- HTML: https://affpapa.org/en/nevibecode/mcp/recall

## What it does

Recall provides offline persistent context by saving entries directly inside `~/.recall/`. The server runs local ONNX embeddings on your machine, so semantic search and file retrieval need zero network traffic. Functions such as `index_file` and `recall` let coding assistants pull context from previous sessions alongside exact text citations.

The system requires Python 3.11+. The package exposes 22 MCP tools in total: 16 manage memories and project checkpoints.

The remaining six tools coordinate parallel agents. Functions like `claim` assign advisory locks with automatic TTL expiration to stop concurrent agents from overwriting the same script, while `handoff` transfers task intent across windows.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add recall -- uvx ai-recallworks
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-recallworks <command>

### Codex

**Platform CLI**
```bash
codex mcp add recall -- uvx ai-recallworks
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-recallworks <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "recall": {
            "command": "uvx",
            "args": [
                "ai-recallworks"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-recallworks <command>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "recall": {
            "type": "stdio",
            "command": "uvx",
            "args": [
                "ai-recallworks"
            ]
        }
    }
}
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-recallworks <command>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add recall uvx ai-recallworks
```
uvx runs the command named after the package; if the README names another one, use uvx --from ai-recallworks <command>

## When to use it
- retain architecture decisions across separate sessions
- index source files for local semantic retrieval with citations
- prevent file edit collisions when executing multiple agents
- transfer active context between planner and executor roles

## Example prompts
- Find what we decided regarding database migrations last week.
- Index the documentation directory and check our rate limit policy.
- Claim src/auth.py so other running agents avoid modifying it during the refactor.

## Similar
- [technology-selection](https://affpapa.org/en/nevibecode/skills/technology-selection.md) — skill · 3400 installs
- [memory-bridge](https://affpapa.org/en/nevibecode/skills/ruvnet-memory-bridge.md) — skill · 744 installs
- [mempalace-recall](https://affpapa.org/en/nevibecode/skills/mempalace-recall.md) — skill · 1400 installs
- [trovex](https://affpapa.org/en/nevibecode/mcp/trovex.md) — MCP server · ★ 11
- [Palace](https://affpapa.org/en/nevibecode/mcp/palace.md) — MCP server · ★ 10
- [ai-agents-architect](https://affpapa.org/en/nevibecode/skills/sickn33-ai-agents-architect.md) — skill · 1500 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md