# Engram: AI memory you can edit in Obsidian

Engram gives AI agents shared Markdown memory that people can edit in Obsidian or the web app. It fits workflows that use several MCP clients.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 12
- Author: engram-app
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/engram-app/Engram
- Updated: 2026-10-24
- HTML: https://affpapa.org/en/nevibecode/mcp/engram-ai-memory-you-can-edit-in-obsidian

## What it does

Engram provides a shared note store for AI assistants. Its MCP server supports semantic and keyword search, while agents can read and change plain Markdown notes. People can work with the same notes in Obsidian or through the web app.

The hosted service is available at `https://mcp.engram.page`; clients authenticate with OAuth, so there is no local setup for that option. Self-hosting uses Docker Compose: clone the repository, copy `.env.example` to `.env`, fill in the three secrets, and run `docker compose up -d`. The app exposes port `4000`, with MinIO available through the S3 profile for large vaults.

The hosted connection will not complete without OAuth. Full-vault Obsidian syncing requires the separate Engram Obsidian Sync plugin.

## Requirements
- Remote server: `https://mcp.engram.page`
- Works with: Obsidian

## Install

### Claude Code (native platform)

**Platform CLI: remote server**
```bash
claude mcp add --transport http engram https://mcp.engram.page
```

### Codex

**Platform CLI: remote server**
```bash
codex mcp add engram-ai-memory-you-can-edit-in-obsidian --url https://mcp.engram.page
```

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "engram-ai-memory-you-can-edit-in-obsidian": {
            "url": "https://mcp.engram.page"
        }
    }
}
```

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "engram-ai-memory-you-can-edit-in-obsidian": {
            "type": "http",
            "url": "https://mcp.engram.page"
        }
    }
}
```

### Gemini CLI

**Platform CLI: remote server**
```bash
gemini mcp add -t http engram-ai-memory-you-can-edit-in-obsidian https://mcp.engram.page
```

## When to use it
- store AI notes as Markdown
- search project memory by meaning or keywords
- share memory across MCP clients
- edit agent memory in Obsidian or the web app
- run Engram with Docker Compose

## Example prompts
- Save the database migration decision to Engram memory.
- Search Engram for notes about the project’s migration and summarize them.
- Update the Markdown note with our project rules by adding the new testing requirement.

## Similar
- [obsidian-markdown](https://affpapa.org/en/nevibecode/skills/agricidaniel-obsidian-markdown.md) — skill · 545 installs
- [obsidian-kb-artifacts](https://affpapa.org/en/nevibecode/skills/obsidian-kb-artifacts.md) — skill · 319 installs
- [obsidian-mcp-server](https://affpapa.org/en/nevibecode/mcp/obsidian-mcp-server.md) — MCP server · ★ 701
- [obsidian-cli](https://affpapa.org/en/nevibecode/skills/obsidian-cli.md) — skill · 81000 installs
- [obsidian](https://affpapa.org/en/nevibecode/skills/obsidian.md) — skill · 6400 installs
- [Obsidian Automation](https://affpapa.org/en/nevibecode/skills/obsidian-automation.md) — skill · 4800 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md