Engram: AI memory you can edit in Obsidian MCP Server
io.github.engram-app/engram
Shared memory for Claude and ChatGPT—edit your notes in Obsidian, your AI reads and writes them.
What is the Engram: AI memory you can edit in Obsidian MCP server?
Engram is an MCP server that provides shared memory between AI assistants and users through plain markdown notes. Your notes sync in real-time across Obsidian, a web app, and any MCP client, with semantic and keyword search capabilities. It's self-hostable, source-available, and built on Elixir/Phoenix.
Engram bridges your personal knowledge base with AI assistants by storing shared memory as plain markdown files. You edit notes in Obsidian or the web app; Claude, ChatGPT, and other MCP clients read and write to the same vault. It supports semantic search, real-time sync, and self-hosting with optional S3 storage and advanced embeddings.
How to install Engram: AI memory you can edit in Obsidian
Copy-paste configuration for popular MCP clients.
Tools & capabilities
Tools this server exposes to the agent.
Read notes— Retrieve and search notes from your vault using semantic and keyword searchWrite notes— Create and edit notes that persist in your markdown vaultSync vault— Real-time synchronization between Obsidian, web app, and MCP clientsSearch (semantic + keyword)— Find notes using both semantic similarity and keyword matching
Use cases
- Store conversation context and facts that Claude can reference across sessions
- Build a personal knowledge base that both you and your AI assistants can read and edit
- Maintain project notes, research, or decision logs that stay synchronized across tools
- Use Obsidian as your primary editor while giving Claude direct access to your vault
- Self-host your memory system on your own infrastructure for privacy
Engram: AI memory you can edit in Obsidian MCP server FAQ
Engram is a shared memory system for AI assistants and users. Your notes are plain markdown stored in a vault; you edit them in Obsidian or a web app, and Claude, ChatGPT, or any MCP client can read and write to the same files.
Engram is dual-licensed. It's free under PolyForm Small Business 1.0.0 for organizations under $1M USD prior-year revenue and fewer than 100 employees. Larger organizations require a commercial license.
Connect the remote MCP server at https://mcp.engram.page, or self-host using Docker Compose. See the MCP setup docs at engram.page/docs/mcp/ for detailed configuration.
No. You can use the remote server at https://mcp.engram.page, or self-host via Docker Compose for full control and privacy. Self-hosting requires filling in three environment secrets.
Yes. Install the Engram Obsidian Sync plugin (github.com/engram-app/Engram-obsidian) to sync your entire vault in real-time between Obsidian and the Engram server.
Engram supports both semantic search (using embeddings) and keyword search. You can optionally switch to Voyage AI embeddings for better semantic results.
README (reference)
Source of truth, from the repository.
Engram

MCP-native · semantic + keyword search · real-time sync · self-hostable · source-available · Elixir/Phoenix
Quickstart · Self-host · MCP · API · Architecture · Plugin · Discord
</div>Your notes stay plain markdown that you and your AI assistants both read and write. Pairs with the Engram Obsidian Sync plugin to sync your whole vault.
Self-Host (Docker Compose)
Don't want to run the commands yourself? Open the Quickstart docs, select the whole page, and paste it into your AI assistant — it's written top-to-bottom as imperatives the AI can execute in order.
Otherwise:
git clone https://github.com/engram-app/Engram.git
cd Engram
cp .env.example .env # then fill in the three secrets at the top
docker compose up -d
App at http://localhost:4000. Migrations run on boot. Only port 4000 is host-exposed; everything else stays on the private Docker network.
Large vaults? Enable MinIO for S3-style attachments:
docker compose --profile s3 up -d — see
storage docs.
Better embeddings? Switch to Voyage AI in .env — see
embeddings docs.
Full self-host documentation
| Topic | Link |
|---|---|
| Quickstart | https://engram.page/docs/self-host/quickstart/ |
| Environment vars | https://engram.page/docs/self-host/environment-variables/ |
| Encryption & keys | https://engram.page/docs/self-host/encryption/ |
| Backup & restore | https://engram.page/docs/self-host/backup-restore/ |
| Upgrades | https://engram.page/docs/self-host/upgrade/ |
| Troubleshooting | https://engram.page/docs/self-host/troubleshooting/ |
| Architecture | https://engram.page/docs/self-host/architecture/ |
| MCP setup | https://engram.page/docs/mcp/ |
| HTTP API | https://engram.page/docs/api/ |
Community
Questions, ideas, or bug reports? Join us on Discord.
Contributing
Local dev setup, tests, and PR rules: see CONTRIBUTING.md.
License
Dual-licensed:
- PolyForm Small Business 1.0.0 — free for organizations under $1M USD prior-year revenue and < 100 employees + contractors.
- Commercial License — required for larger orgs. See
LICENSE-COMMERCIAL.md or email
support@engram.page.
External contributions sign the Engram CLA. See CONTRIBUTING.md.
Security
See SECURITY.md for vulnerability disclosure. Self-host LAN deployments are out of scope of our published SLA — security depends on the operator's network and infra.
Copyright (c) 2026 Rasbandit Software Solutions LLC d/b/a Engram.
Related MCP servers
Trace code history, commit reasoning, and PR context directly from Git logs.
View repository →Cited, confidence-stamped patent intelligence over US university tech-transfer out-licensing.
Аccess to personalized Enigmata astrological forecasts (day/week/month/thematic) for AI assistants

AgentReady website scans for AI agents, AI Hub search, newsletter and contact, from Enpitech.
View repository →
io.github.enrichgateagent-png/beacon-mcp
Search 17,900+ open-source AI agents by capability, ranked by GitHub traction. Free, no key.
Find kids enrichment activities: camps, classes, after-school programs, and tutoring near you.
