Engram MCP server

Engram

The second brain your AI agents read and write.

▶ Watch the full-length video (real-time, full quality)

↗ Try the live demo — no signup. Search retainer price and watch the retired note get withheld.

Engram is a self-hosted MCP server + dashboard that gives Claude Code, Cursor, Hermes, and any Model Context Protocol agent shared, long-term memory they read and write — over a plain, git-backed folder of markdown you own. Built for the case a single agent's memory never hits: a team running several agents against one brain.**

Autonomous agents forget everything between sessions — and worse, they can't tell what they remember is still true. An agent pulls an old README, a retired price, an API doc you changed months ago, and quotes it with full confidence, because keyword and vector search both rank by resemblance, not truth. Engram makes "is this still true" a first-class, written property: mark a fact superseded or expired and search withholds it — and tells the agent what it skipped and why. Per-agent read/write tokens and a git audit trail of who-wrote-what keep it sane when the writers are a fleet, not just you.

Unlike a headless memory store, you can watch it happen. A fast dashboard lets you search your brain, see exactly what every agent and teammate changed (with per-file diffs), jump back into recent notes, and curate it all — while agents read and write the same vault over one MCP endpoint. No database: your .md files are the source of truth, git is the durable store, and an in-memory index powers full-text search + a wikilink knowledge graph.

Opinionated about how it stores memory — git-backed markdown, no database, agents write (not

just read), self-hosted. Unopinionated about what you keep in it — any markdown vault, any folder

structure, any MCP client. Point it at a fresh repo or your existing Obsidian vault: no import

step, no lock-in.

Shortened. The full README is on GitHub.