← All projects
AI testing & safety

Failproof AI

Watches what AI agents do on your computer and blocks risky actions before they happen.

New this week

What it does

Failproof AI hooks into AI agent tools such as Claude Code, Codex and OpenClaw. It records each run and checks every action the agent tries against a set of rules.

Rules can block things like reading secret files, deleting folders, risky database commands or pushing code straight to the main branch. You can choose from built-in rules or write your own.

A local dashboard shows what each agent did and what was blocked. Its makers say this history stays on your machine.

Who it's for

Developers and teams who run AI coding agents and want guardrails and a record of their actions.

Can I use it without coding?

Developers only. Installed and set up with commands; rules can be written in code. New to this? Start here.

Can I run it?

Runs on
Mac, Windows, Linux
Computer
An ordinary computer is fine
Privacy
Runs on your own device: your data stays with you
API key
Not needed

Try it

Using Claude Code, Cursor or another AI coding assistant? Paste the prompt and it will walk you through the setup.New to this?

Before you install

  • Only download from the official GitHub page. Copies with similar names exist for many popular projects.
  • No standard license listed. Check the GitHub page before using it for business.
  • More on staying safe