Sign in

One memory across your AI tools.

Your decisions and project facts, recalled from Claude, Codex, Cursor or any MCP tool. Nothing is shared until someone who didn't write it approves it.

  • Claude Code
  • claude.ai
  • Claude Desktop
  • Claude mobile
  • Codex
  • Cursor
  • Gemini CLI
  • VS Code

Each connects over MCP, the open protocol AI tools use to reach other services. The Claude Code plugin is in daily use against this server; the others connect through each tool's own MCP settings (what we have not tested live).

Get startedAsk about access
waitingnew memory

Staging database passwords live in Vault. Never put them in a .env file.

  1. Savedby Claude Code
  2. Checkedno secrets found
  3. Approvedwaits for someone who didn't write it
  4. Sharednot yet

Approve it, and your other AI tools can recall it.

How a memory gets approved

How a memory gets approved
As text
  1. An agent, here crew/scout, saves a memory.
  2. The memory waits, held: only its author and its reviewers can read it. It is scanned for leaked secrets, such as private keys, known providers' API tokens and passwords set in config (DB_PASSWORD=…), and a match refuses the write.
  3. Someone who did not write it, nor what it builds on, approves it: a person, here eugene, or a reviewer agent. The key that wrote a memory never approves it.
  4. The memory is promoted, approved and shared: every agent with access to its workarea recalls it. A workarea is a named area of memory, such as a team or a project, and a key reads only the workareas it is granted.
  5. Two opt-in exceptions, each confined to one workarea, are described under workareas.

Nothing shared unapproved

An agent's memory waits until a person, or a reviewer agent, who didn't write it approves it.

Every memory shows its source

Who wrote it, who approved it and, where given, the repository, commit and file it came from.

Answers say why they matched

Each hit names the words it matched, so you can see why it came back.

Get started

The public server is by invitation: email contact@doublegate.io. Invited? Sign in with GitHub or Google, and issue a key for your agent on your account page, /web. Then:

  1. Install oml on Linux. The installer checks the download against the release's signed checksums. On a Mac, build it from source; on Windows, use PowerShell (install options).
  2. Store your key. oml login asks for it, checks it with the server and keeps it in a file only you can read.
  3. Set up Claude Code. oml setup claude-code installs the plugin with that key. Then run /reload-plugins in Claude Code, or restart it.
  4. claude.ai or the Claude app? On your account page, under Connect Claude on the web or a phone, issue a connector key and copy its code. On claude.ai, open Customize > Connectors, add https://memory.doublegate.io/mcp and paste the code. Your phone gets it too.

No invitation? Try a local server in about five minutes. claude.ai and phones cannot reach a server on your laptop; they need one on a public HTTPS address.

Your memories stay on the server you choose. On the public server its operator can read them; its request logs hold no memory text and are kept 30 days (what is logged).

Claude Code guideclaude.ai and phone guideConnect Codex, Cursor or GeminiRun your ownRelease notes (pre-1.0)

Linux
# install the CLI (Linux)
$ r=https://raw.githubusercontent.com/e8kor
$ u=$r/open-memory-lab/v0.6.1/scripts/install
$ curl -fsSL --proto '=https' --tlsv1.2 \
    "$u/install.sh" | sh

# store your key; paste it when asked
$ oml login https://memory.doublegate.io

# install the Claude Code plugin
$ oml setup claude-code
# then, in Claude Code: /reload-plugins