Bettermemory MCP server

<!-- mcp-name: io.github.0Mattias/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 / hermes

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

verdict: calendar age, whether the paths it cites still exist, the commits landed since it was last confirmed, and how the record entered the store (written here, pulled, or placed by hand). 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.

• Checks memory before believing it. Every hit carries a staleness

injection. Write gates bounce transient state, secret-shaped tokens and near-duplicates; claims about you stage for confirmation.

• Retrieval is deliberate. Memory is a tool call, not an

keyword + BM25, fused — over your own vocabulary. No embedding models, no downloads, nothing to warm up, same answer every time.

• The code is the model. Search is deterministic lexical ranking —

git-syncable, no cloud, no account. The SQLite index beside the files is a derived cache you can delete; bettermemory reindex rebuilds it.

• Plain files. One markdown file per memory. Greppable,

run-state without polluting durable search; health telemetry and curation tools surface what drifted, what went cold, and what contradicts what.

• Rot gets acted on, not accumulated. Episodes journal per-session

preregistered benchmarks whose frozen result artifacts — misses included — live in [bench/][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][eval-results]).

• Receipts, not adjectives. The claims above are measured by

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:

Shortened. The full README is on GitHub.