Find tools › Open-source projects › Research the web

Agent-Cockpit

Open-source project · by chutingyean

A local visual board that makes sure your computer helper's research findings always match the code used.

Some setup532 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • Track research claims and experiment code dependencies automatically
  • Catch unreported code changes made by AI assistants in real time
  • Pause research workflows to answer decisions requested by AI agents

How to start

  1. Navigate to your research project folder in your command line.

  2. Run npx -y @tingyen/agent-cockpit init to create the configuration and helper hooks.

  3. Launch the server by running npx -y @tingyen/agent-cockpit serve.

  4. Open http://127.0.0.1:4180 in your web browser to view the evidence whiteboard.

Good to know. Uses the AGPL-3.0 open-source license, requires Node.js 22.13+, and installs pre-commit hooks directly into your local git configuration.

Before you install

  • Found automaticallyNot reviewed by a person yet. Check it before installing.
  • License: AGPL-3.0You are allowed to use it under these terms.
  • Last updated 2026-11-06

More detail

An MCP server and local whiteboard that tracks code changes, experiment runs, and research claims made by AI coding agents.

AI research agents often alter scripts without updating dependent results, leading to silent errors. Reach for this tool to automatically link claims to exact script executions and code hashes on a visual board.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-11-09. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map