← All projects
Developer building blocks

Agent Governance Toolkit

Microsoft's toolkit for setting firm rules on what AI agents may do, and recording what they did.

New this week

What it does

AI agents can send emails, query databases and call other tools on their own. This toolkit from Microsoft checks each action in ordinary code before it happens, so actions that break the rules are blocked, rather than relying on the AI to behave.

It also gives each agent its own identity, runs agents in sandboxes and keeps tamper-evident records for audits. The README says it works with any agent framework and is currently a public preview.

Who it's for

Teams putting AI agents into real use who need control, accountability and compliance.

Can I use it without coding?

Developers only. It is a Python package that developers add to their agent code. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Computer
An ordinary computer is fine
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.
  • License (MIT): Very permissive: free to use, change and share, including for business.
  • More on staying safe