bettermemory

An MCP memory server for coding agents. Stored facts get checked against the filesystem and git before the model relies on them, so a memory that has rotted is flagged instead of quoted back at you.

Install

Claude Code — two slash commands, zero config:

/plugin marketplace add 0Mattias/bettermemory
/plugin install bettermemory@bettermemory

Anything else that speaks MCP:

uv tool install bettermemory
bettermemory init --client claude-desktop   # or cursor / cline / claude-code

Restart the client. bettermemory doctor exits 0 when it's wired correctly and prints a one-line fix for anything that isn't.

Try it without installing: uvx bettermemory try writes a memory citing a file, deletes the file, and shows the next search flagging it. Offline, throwaway store.

What it does

• Checks memory before believing it. Every hit carries a staleness verdict: calendar age, whether the paths it cites still exist, and the commits landed since it was last confirmed. Declared claims (path, path::symbol, path::NAME=literal) are re-checked against the working tree; a claim that stops being true blocks the stamp instead of riding along.
• Retrieval is deliberate. Memory is a tool call, not an injection. Write gates bounce transient state, secret-shaped tokens and near-duplicates; claims about you stage for confirmation.
• The code is the model. Search is deterministic lexical ranking — keyword + BM25, fused — over your own vocabulary. No embedding models, no downloads, nothing to warm up, same answer every time.
• Plain files. One markdown file per memory. Greppable, git-syncable, no cloud, no account. The SQLite index beside the files is a derived cache you can delete; bettermemory reindex rebuilds it.
• Rot gets acted on, not accumulated. Episodes journal per-session run-state without polluting durable search; health telemetry and curation tools surface what drifted, what went cold, and what contradicts what.
• Receipts, not adjectives. The claims above are measured by preregistered benchmarks whose frozen result artifacts — misses included — live in bench/ (results/*.json, each carrying the declared terms it was scored under), and bettermemory eval scores whether memory actually helped against your own log (ours is published).

For agents

You were likely handed this link with "set this up." On Claude Code, the two plugin commands above are the whole install — skip to step 3. Everywhere else, steps are idempotent and safe to re-run:

1. uv tool install bettermemory — or pipx install bettermemory, or pip install bettermemory into a venv. Python 3.11–3.14.
2. bettermemory init --client claude-code — likewise claude-desktop, cursor, cline. For any other MCP host, plain bettermemory init prints the canonical mcpServers JSON snippet plus known config locations. (Continue needs a hand-written YAML entry — see docs/clients.md.)
3. bettermemory doctor — exit 0 means correctly wired; every failed check prints a one-line fix.
4. Have the user restart the client so the server loads, then confirm by asking the model "what memory tools do you have?"

Your operating contract — tool signatures, retrieval discipline, write gates — is docs/api.md; the server's instructions block delivers the core policy automatically. For the long-form policy in your system prompt: bettermemory init --with-addendum. Migrating from Claude Code's built-in auto-memory: bettermemory ingest imports those files once.

Everything else

The rest is written down: mechanics, storage format, the full tool surface, CLI, configuration and limitations in internals; per-client setup in clients and installation; eval methodology in eval; postmortems in incidents; release history in CHANGELOG; dev setup and the compatibility contract in CONTRIBUTING.

MIT licensed — see LICENSE.