Engram
以下摘录自该仓库的 README(片段) · 在 GitHub 读完整 README →
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Engram makes **"is this still true"** a first-class, written property: mark a fact superseded or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.
---
**What it's for** · **How it compares** · **Features** ·
**Works with** · **Quick start** · **MCP tools** ·
**Deploy** · **FAQ** · **Contributing**
---
What it's for
- **Shared memory for a team running multiple agents** — one vault, many agents reading and writing
concurrently, with per-agent read/write tokens and a git audit trail of who changed what.
- **Memory that knows what's still true** — retire a price, a term, or a changed API doc and your agents
stop quoting it; they're told what they skipped and why. The failure a single agent's memory never fixes.
- **Long-term memory for Claude Code** and other coding agents — stop re-explaining your project every session.
- **A self-hosted, Obsidian-compatible second brain** exposed over MCP — your notes, your server, your git repo.
- **Memory you can see, not a black box** — a dashboard to search, watch (with diffs), and curate what your agents remember.
- **Markdown RAG without the vector database** — full-text search + a link graph over human-readable files.
How it compares
Most agent memory is built to answer *"what did I store about this?"* Engram is built to answer
*"what is still true about this?"* — a different question, and the one that bites when an agent
quotes a price you retired months ago.
| | **Engram** | Vector-store memory (mem0, Zep, …) | Markdown memory (Basic Memory, …) | Plain RAG over docs |
|---|---|---|---|---|
| **Storage** | markdown files, git is the database | embeddings in a vector DB | markdown files | embeddings in a vector DB |
| **Ranking** | relevance **× authority** | similarity | relevance | similarity |
| **Knows a fact is retired** | ✅ superseded_by + valid_until, enforced at search | — | — | — |
| **Explains what it withheld** | ✅ excluded[] with a reason per note | — | — | — |
| **Retire + replace atomically** | ✅ brain_supersede, one commit | — | — | — |
| **Refuses contradicting writes** | ✅ at write time, not read time | — | — | n/a (read-only) |
| **Audit trail** | ✅ git, per-write attribution, per-file diffs | varies | git, if you commit | — |
| **Per-agent access control** | ✅ read / write token scopes | varies | — | — |
| **Human UI** | ✅ dashboard, search, diffs, graph | varies | — | — |