Plain-AyI
← All projects
Running AI at scale

Arize Phoenix

A dashboard for watching, testing and debugging AI apps so teams can see what their AI is doing.

New this week

What it does

Phoenix is an open-source tool from the company Arize for keeping an eye on AI applications. It records each step an AI app takes, such as the prompts sent and answers received, so developers can find where things go wrong.

It also helps teams test their apps: build sets of example questions, score answers (often using another AI as the judge), compare prompts and models side by side, and keep track of prompt changes.

It works with many popular AI frameworks and can run on your own computer, in a container or in the cloud. Arize also sells a separate managed version.

Who it's for

Developers and teams building AI apps who need to test, monitor and troubleshoot them.

Can I use it without coding?

Developers only. Developers add it to their apps' code; it then gives a web dashboard to explore the results. 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
Mac, Windows, Linux, Server, Cloud
Computer
An ordinary computer is fine
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.
  • No standard license listed. Check the GitHub page before using it for business.
  • More on staying safe

Where people are talking about it