Plain-AyI
← All projects
Running AI at scale

Opik

Track, test and monitor AI apps and agents so teams can see what they're doing and catch mistakes.

What it does

Opik helps teams building AI apps understand how those apps behave. It records each step an AI app or agent takes, including every call to an AI model and every tool it uses, so problems can be traced.

It can test apps automatically against sets of examples, including using another AI to judge answers for things like made-up facts. It also offers dashboards for watching apps once they're live, a place to try prompts, and tools to improve prompts.

It's made by Comet. Its makers say the full platform is free to host yourself.

Who it's for

Engineers and AI teams moving AI apps from prototype into real-world use.

Can I use it without coding?

Developers only. Needs code to connect your app, plus hosting the platform or using Comet's service. New to this? Start here.

Can I run it?

Cost
Free, with optional paid extrasThe open-source version is free; the makers also sell a hosted or pro version.
Runs on
Server, Cloud
Privacy
Your choice: run it on your device or use an online service
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 (Apache-2.0): Permissive: free to use, change and share, including for business.
  • More on staying safe

Where people are talking about it