Magnemo

Magnemo

Tools gave your agent hands. MCP gave it a nervous system. Magnemo gives it a brain.

Governed memory for AI agents. Every entry with a receipt. Your agent writes thedraft; nothing is kept until you say yes.

The one paste

Open your AI (Claude Code, Cursor, Windsurf, or anything that speaks MCP) in any of your project folders, and paste this:

Set up Magnemo in this project:
1. Install it: pip install magnemo. It needs Python 3.11 or newer. If pip can't find it, install uv (curl -LsSf https://astral.sh/uv/install.sh | sh) and then run: uv tool install magnemo
2. Initialize the vault: magnemo init
3. Register the MCP server: run magnemo mount — it writes this project's MCP config itself.
4. Verify: run magnemo doctor and confirm everything passes.
5. Stage the first memory: one line on what this project is, using magnemo stage. Show me the note id.
6. Then tell me the exact command to approve it. After I approve, run magnemo bootpack and tell me what you remember — then remind me to restart you, so the memory mounts for every session after this one.
If anything fails, show me what went wrong and fix it if you can.

You'll know it worked — your AI will tell you who it is now.

For builders. Magnemo is an MCP server with four tools — retrieve, stage,bootpack, handoff — and a CLI for your side: review, promote, reject.It runs on your machine, in plain markdown files you own, with zero network calls(the doctor line proves it). Every promotion is a person's click, recorded withwho wrote the entry, when, and through which gate — memory with a witness. Trust iscomputed from that record, never asserted. It mounts beside any memory you alreadyrun (a folder of notes, Obsidian, a RAG stack). Python 3.11+, zero dependencies,Apache-2.0.

Fresh vault? THE CHARTER section will say it isn't promoted yet — that is thegovernance speaking: Magnemo never fabricates canon. Stage a charter, review it,promote it, and every boot thereafter serves it back verbatim.(magnemo not found after install? pip's script folder isn't on PATH —python3 -m magnemo always works.)

Open beta — read KNOWN_LIMITS.md before trusting it with anything you can't lose. Honest caveats, no fine print.

Install in your client

One server, said ten ways. Every block below is the same thing: uvx magnemo-mcp with MAGNEMO_VAULT pointing atthe folder your memory lives in (make one with magnemo init ./vault). Tested on this Mac where it says so;the rest is from each client's own docs and marked untested — corrections welcome, open an issue.

Claude Code — tested.

claude mcp add magnemo -e MAGNEMO_VAULT=/absolute/path/to/vault -- uvx magnemo-mcp

(claude mcp list shows magnemo … ✔ Connected. Add -s project to write it into the repo's .mcp.json for your team.)Only have the desktop app? claude may not be a command in your shell. On a Mac the app keeps its own copy at~/Library/Application Support/Claude/claude-code/<version>/claude.app/Contents/MacOS/claude; run that in place of claude.

Claude Desktop — tested. Download the extension from the latest release —magnemo-0.6.7.mcpb — and open it; Claude Desktop asks for thevault folder and does the rest. (The connectors directory listing follows once it is accepted.)

Cursor — untested here (not installed on this Mac); the link and the block follow Cursor's docs.Or ~/.cursor/mcp.json (or .cursor/mcp.json in the project):

{
  "mcpServers": {
    "magnemo": {
      "command": "uvx",
      "args": ["magnemo-mcp"],
      "env": { "MAGNEMO_VAULT": "/absolute/path/to/vault" }
    }
  }
}

VS Code / Copilot — untested here; per VS Code's docs.Or .vscode/mcp.json in the workspace:

{
  "servers": {
    "magnemo": {
      "type": "stdio",
      "command": "uvx",
      "args": ["magnemo-mcp"],
      "env": { "MAGNEMO_VAULT": "/absolute/path/to/vault" }
    }
  }
}

Windsurf — untested; ~/.codeium/windsurf/mcp_config.json:

{
  "mcpServers": {
    "magnemo": {
      "command": "uvx",
      "args": ["magnemo-mcp"],
      "env": { "MAGNEMO_VAULT": "/absolute/path/to/vault" }
    }
  }
}

Cline — untested; Cline → MCP Servers → Configure → cline_mcp_settings.json:

{
  "mcpServers": {
    "magnemo": {
      "command": "uvx",
      "args": ["magnemo-mcp"],
      "env": { "MAGNEMO_VAULT": "/absolute/path/to/vault" },
      "disabled": false
    }
  }
}

Continue — untested; ~/.continue/config.yaml (or a file in .continue/mcpServers/):

mcpServers:
  - name: magnemo
    command: uvx
    args: ["magnemo-mcp"]
    env:
      MAGNEMO_VAULT: /absolute/path/to/vault

Gemini CLI — untested; ~/.gemini/settings.json:

{
  "mcpServers": {
    "magnemo": {
      "command": "uvx",
      "args": ["magnemo-mcp"],
      "env": { "MAGNEMO_VAULT": "/absolute/path/to/vault" }
    }
  }
}

Codex CLI — untested; ~/.codex/config.toml:

[mcp_servers.magnemo]
command = "uvx"
args = ["magnemo-mcp"]
env = { MAGNEMO_VAULT = "/absolute/path/to/vault" }

Zed — untested; settings.json → context_servers:

{
  "context_servers": {
    "magnemo": {
      "source": "custom",
      "command": "uvx",
      "args": ["magnemo-mcp"],
      "env": { "MAGNEMO_VAULT": "/absolute/path/to/vault" }
    }
  }
}

After the install, the loop is the same everywhere: your agent writes to staging, you review.

magnemo yes             # promote the top of the queue (yes <id-fragment> · yes --all)
magnemo no <id> --reason "…"   # reject one — the reason is required; rejections teach
magnemo review          # the interactive queue, when you want to read first
magnemo doctor          # python, vault, config, ledger, and the mount — proves the zero-network line too

Anything that speaks MCP over stdio mounts the same way. The remote door (ChatGPT and hosted clients) is on its way in 0.7.0.

Agents draft, people keep — the one rule

Agents get four MCP tools. Promotion is not one of them.

The vault

vault/
  dev/      knowledge/ playbooks/ decisions/ debt/        ← example: a dev team's partition
  ops/      knowledge/ playbooks/ clients/ decisions/ style/  ← example: an ops team's partition
  shared/   tickets/ changelog/                            ← interop bus (gated)
  _staging/   agent writes await review here
  _index/     machine-managed
  _ledger/    trust_ledger.jsonl — append-only, never forgets

Every note is markdown with provenance frontmatter (author, written, source,status, reviewed_by, supersedes, strength). Provenance is the file format.

Privacy

Your memory lives on your computer, in plain files you can open. The engine makes no network calls, andmagnemo doctor checks that every time it runs. The full page: https://magnemo.ai/privacy

Guarantees (Phase 1 — Governed Recall)

• Agent writes NEVER reach canonical stores directly — staging only, always.
• Search returns canonical (keyholder-approved) notes only. Staged claims are invisible.
• Partition walls enforced per agent (MAGNEMO_PARTITIONS); cross-partition = DENIED.
• Supersession is explicit: old notes archive with a forward link. Nothing deletes.
• Rejections are kept and recorded — rejections teach.
• Every promote/reject lands in the append-only Trust Ledger with actor + reason.

Tests

python -m unittest discover -s tests -v     # incl. full MCP round-trips (legacy + four-verb)
# or: pip install -e ".[test]" && pytest

Everything that shipped

Release by release, with the design notes that used to live here: CHANGELOG.md.

— Silver Valley Technologies Inc. · Phase 1 of 3 · The memory that learns isthe memory that is governed.

mcp-name: ai.magnemo/magnemo · Source · Security · Privacy