MongoDB sandboxes
for AI agents

Git for MongoDB underneath.

Give every agent run its own real MongoDB database, forked from your data. Review what it changed, merge what works, and discard the rest.

Open source under MIT. Self-hosted, on your own MongoDB.

orders / order-1

Illustration
mainagent

main

price
49

Unchanged

planner

price
49

Same baseline

Start from the same data.

Give the planner agent its own branch of orders. Both start with the same document.

Branch pointprice: 49

Illustrated workflow. Run the real engine locally. How it works

Install the CLI with npm
npm install -g argonctl@2.9.0 --allow-scripts=argonctl

Installs the argon CLI with npm 11.16+ and a supported Node.js version. Allows only argonctl's binary installer.

Published release: v2.9.0

One CLI named argon. It runs the engine, the local console, the MCP server and the wire proxy.

Read the release notes

Git for MongoDB, command by command

Every sandbox is a branch, so the workflow is the one you know from Git.

See each command with its output and limits

Use the tools you already have

An agent branch checks out as a real MongoDB database. Keep your usual driver; use Argon to manage its history and review its work.

  • Connect an agent

    Give Claude Code or Cursor database tools through MCP.

    Set up MCP
  • Build in Python

    Run the review workflow with the SDK, then add it to your agent.

    Use the Python SDK
  • Use your own stack

    Create sandboxes and inspect changes from any HTTP client.

    Call the REST API
  • Pair with a code sandbox

    Run agent-written code on an isolated boxd machine against an Argon sandbox.

    See the boxd integration

Verify it yourself

The two-agent example checks the starting data, a real conflict, the accepted change, and the restored result.

Review your first change

Start with a sample order. See what the agent changed.

Explore walkthrough