← All projects
AI testing & safety

A.I.G (AI-Infra-Guard)

A security testing platform that scans AI agents, tools and servers for weaknesses.

New this week

What it does

A.I.G, from Tencent, is a red-teaming platform. Red teaming means testing a system the way an attacker would, to find problems before someone else does.

It scans AI agents, agent skills and MCP servers (plug-ins that give AI new abilities), checks AI software for known security flaws, and tests how well AI models resist jailbreaks, tricks that get a model to break its own rules.

It runs as a web app with Docker. The README notes it has no login system and should only be used inside a company or on your own machine, not on the public internet.

Who it's for

Security teams and AI engineers who need to check their AI systems for risks.

Can I use it without coding?

With some setup. You run it with Docker and use it through a web page. New to this? Start here.

Can I run it?

Cost
FreeNothing to pay or sign up for.
Runs on
Server
Computer
An ordinary computer is fine
API key
Not needed

Try it

  1. Install Docker, then start A.I.G using the project's Docker instructions.
  2. Open the A.I.G web page on your own computer and choose what to scan.

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 (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe