Find tools › Open-source projects › Test & monitor AI apps

phoenix

Open-source project · by Arize-ai

A free dashboard that shows step by step what your AI app did and grades its answers.

For developersPopular616,502 installs a month

What it costs

Free and open source; you may pay for the AI model it uses.

Use it to

  • See why an AI agent gave a wrong answer
  • Score chatbot replies against a test set
  • Try prompt changes and compare the results

How to start

  1. Install Python, then in a terminal run pip install arize-phoenix.

  2. Start the dashboard with phoenix serve and open it in your browser.

  3. Add Phoenix tracing to your AI app's code, following the docs.

Before you install

  • Checked by a personWe read what it does before listing it.
  • Last updated 2026-11-18

More detail

Arize Phoenix provides OpenTelemetry-based tracing, evaluation, dataset management, and experimentation for LLM applications.

It solves the challenge of debugging and benchmarking complex AI workflows and multi-step agent applications. Reach for it when you need to inspect what your LLM code is doing under the hood, run evals, or manage prompts.

Similar tools

Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map