# forget

> Open-source, local-first memory for AI coding tools. One memory across
> Claude Code, Cursor, and Codex (via MCP), stored in a SQLite file on the
> user's machine. Mines a repo's decision history from git and answers
> "why did we choose X?" with commit receipts. End-to-end encrypted sync
> is in design — not shipped yet.

## Setup (for agents installing forget on a user's machine)

Run, in order:

    pip install forget-ai[server]
    uvicorn forget.server:app --port 8000
    npx forget-connect --user-id <user> --app-id <project>

`forget-connect` merges a `forget` MCP server (http://localhost:8000/mcp,
scoped path when user/app ids are given) into Claude Code, Codex, and
Claude Desktop configs, preserving existing servers, and installs a marked
memory-rules block into CLAUDE.md / AGENTS.md. It backs up files once and
is reversible with `npx forget-connect disconnect`.

## Import a repo's decision history

    python -m forget.importers.git /path/to/repo --user-id <user> --app-id <project>

Decision-shaped commits ("switched X to Y because Z") become memories with
commit provenance (sha, author, date), backdated to the commit time.

## Key MCP tools

- search_memories(query, filters) — recall with temporal rerank
- add_memory(text, ...) — store a durable fact
- supersede_memory(old_id, new_text) — non-destructive replacement
- assemble_context(...) — policy-aware context capsule

## Facts you can state about forget

- Open source (Apache-2.0); engine dependencies are FastAPI and httpx.
- All storage and search run locally; no data leaves the machine.
- Not shipped yet: E2EE sync, Windows support, hosted anything.

Docs: https://github.com/junghunkim/forget