Engram: AI memory you can edit in Obsidian

io.github.engram-appPublished by GitHub account engram-appv0.78.1Updated Nov 7, 2026

Shared memory for Claude, ChatGPT and any MCP client. Read and edit it in Obsidian or the web app.

The publisher's own server: Engram

VerifiedStreamable HTTPWeb executableFiles & StorageKnowledge & Memory

Overview

AI-generated overview

Hosted MCP memory server that gives Claude, ChatGPT and other MCP clients shared notes they can read and write, editable in Obsidian or the web app.

What you can do
  • Read and write shared memory notes that multiple AI clients can access
  • Search memory with semantic and keyword search
  • Keep notes in sync in real time across clients
  • Edit the same notes in Obsidian via a sync plugin or in the web app
  • Optionally self-host the server with Docker Compose, including S3-style attachment storage and alternative embeddings
When to use it
Useful when you want several AI assistants to share one persistent, human-editable memory of notes and context, and you want to review or correct that memory yourself in Obsidian or a web app.
Requirements
Remote endpoint at mcp.engram.page; nothing to install. Sign-in via OAuth is required. Self-hosting instead needs Docker Compose, a cloned repository, a .env file with three secrets, and optionally MinIO for attachments or Voyage AI for embeddings.
Before you install
The hosted service stores your notes on a third party's servers and requires an OAuth sign-in. Assistants can write and change that memory, so review edits. Self-hosted LAN deployments are outside the published SLA and depend on the operator's network and infrastructure.

Installation

In SourceWeft

  1. Open Engram: AI memory you can edit in Obsidian in the dashboard and add it to a workspace.
  2. Connect the required credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.engram-app%2Fengram/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config. The client completes OAuth sign-in on first connect.

{
  "mcpServers": {
    "engram-ai-memory-you-can-edit-in-obsidia": {
      "type": "http",
      "url": "https://mcp.engram.page/"
    }
  }
}

README

Engram

[Engram — your notes are your AI's memory, synced everywhere and read by your AI]

MCP-native · semantic + keyword search · real-time sync · self-hostable · source-available · Elixir/Phoenix

[MCP] [Last commit] [Stars] [License] [Sponsor] [Ko-fi]

Connect · Quickstart · Self-host · MCP · API · Architecture · Plugin · Discord

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.

Connect

Nothing to install. Point any MCP client at the hosted server and sign in when prompted (OAuth):

https://mcp.engram.page
  • Claude Code: claude mcp add --transport http engram https://mcp.engram.page
  • Claude.ai / ChatGPT: add a custom connector with the URL above.
  • Cursor: {"mcpServers": {"engram": {"url": "https://mcp.engram.page"}}} in ~/.cursor/mcp.json
  • VS Code: {"servers": {"engram": {"type": "http", "url": "https://mcp.engram.page"}}} in .vscode/mcp.json

More clients: MCP docs.

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:

bash
git clone https://github.com/engram-app/Engram.gitcd Engramcp .env.example .env       # then fill in the three secrets at the topdocker 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

TopicLink
Quickstarthttps://engram.page/docs/self-host/quickstart/
Environment varshttps://engram.page/docs/self-host/environment-variables/
Encryption & keyshttps://engram.page/docs/self-host/encryption/
Backup & restorehttps://engram.page/docs/self-host/backup-restore/
Upgradeshttps://engram.page/docs/self-host/upgrade/
Troubleshootinghttps://engram.page/docs/self-host/troubleshooting/
Architecturehttps://engram.page/docs/self-host/architecture/
MCP setuphttps://engram.page/docs/mcp/
HTTP APIhttps://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:

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.

Source: README.md at commit 2eb61e7

Tools

0
This server asks you to sign in, so SourceWeft could not read its tools without an account and has not indexed them. What a connected account sees can depend on that account and its permissions.

Version history

50
  1. v0.78.1LatestNov 7, 2026
  2. v0.73.0Nov 6, 2026
  3. v0.72.7Nov 5, 2026
  4. v0.72.5Nov 5, 2026
  5. v0.72.4Nov 4, 2026
  6. v0.72.3Nov 4, 2026
  7. v0.72.2Nov 3, 2026
  8. v0.72.0Nov 3, 2026
  9. v0.71.0Nov 1, 2026
  10. v0.70.0Nov 1, 2026
  11. v0.69.0Oct 30, 2026
  12. v0.68.0Oct 29, 2026
  13. v0.65.2Oct 25, 2026
  14. v0.63.2Oct 25, 2026
  15. v0.63.1Oct 24, 2026
  16. v0.61.0Oct 22, 2026
  17. v0.60.2Oct 21, 2026
  18. v0.60.0Oct 21, 2026
  19. v0.58.1Oct 20, 2026
  20. v0.58.0Oct 20, 2026
  21. v0.57.0Oct 19, 2026
  22. v0.56.0Oct 19, 2026
  23. v0.55.0Oct 19, 2026
  24. v0.54.0Oct 18, 2026
  25. v0.53.1Oct 16, 2026
  26. v0.53.0Oct 16, 2026
  27. v0.52.0Oct 15, 2026
  28. v0.51.1Oct 15, 2026
  29. v0.51.0Oct 14, 2026
  30. v0.50.2Oct 13, 2026
  31. v0.50.0Oct 12, 2026
  32. v0.49.0Oct 12, 2026
  33. v0.48.0Oct 11, 2026
  34. v0.47.1Oct 10, 2026
  35. v0.47.0Oct 10, 2026
  36. v0.46.0Oct 9, 2026
  37. v0.45.0Oct 9, 2026
  38. v0.44.0Oct 9, 2026
  39. v0.43.0Oct 7, 2026
  40. v0.41.1Oct 5, 2026
  41. v0.41.0Oct 4, 2026
  42. v0.40.0Oct 4, 2026
  43. v0.39.0Oct 1, 2026
  44. v0.38.1Oct 1, 2026
  45. v0.38.0Sep 30, 2026
  46. v0.37.0Sep 30, 2026
  47. v0.36.0Sep 27, 2026
  48. v0.35.0Sep 26, 2026
  49. v0.34.0Sep 25, 2026
  50. v0.32.0Sep 25, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

    Declare a license in the repository or the registry entry.

Other Engram integrations

Engram

tools.engramOfficial publisher

Engram gives AI assistants a shared memory layer that persists across tools, sessions, repositories and teammates.

Streamable HTTPWeb executableAuth
Knowledge & Memory17 toolsNov 8, 2026

Engram

Published by GitHub account TushaeBXN

Local, private long-term memory for AI: verbatim, searchable, correctable. No LLM or API key.

STDIODesktop only
AI & MLNot validated yetOct 25, 2026

Engram

Published by GitHub account devinmlowe

Engram is a local-first cognitive memory server for coding agents: it captures conversations, extracts structured knowledge, and serves hybrid recall, graph and

STDIODesktop only
Knowledge & MemoryNot validated yetOct 25, 2026

Engram

Published by GitHub account tstockham96

Engram gives an AI assistant a local SQLite memory vault with semantic recall, a knowledge graph, and LLM-powered consolidation.

STDIODesktop only
Knowledge & MemoryNot validated yetOct 24, 2026

Engram

Published by GitHub account tomcat65

Self-hosted coordination bus and shared knowledge graph that lets multiple AI coding agents share state, message each other and resume context across sessions.

STDIODesktop only
Knowledge & MemoryNot validated yetOct 27, 2026