Arize-ai/phoenix

AI Observability & Evaluation

94
/ 100
Verified

Provides OpenTelemetry-based tracing, LLM-powered evaluation, versioned datasets, and experiment tracking across LLM frameworks (LangGraph, LlamaIndex, Claude/OpenAI agent SDKs) and providers. Features a web UI with prompt optimization playground, dataset management, and call replay capabilities. Runs locally, in notebooks, or containerized with Helm support, and integrates via auto-instrumentation through the OpenInference standard.

8,847 stars and 1,013,605 monthly downloads. Used by 7 other packages. Actively maintained with 330 commits in the last 30 days. Available on PyPI.

Maintenance 25 / 25
Adoption 25 / 25
Maturity 25 / 25
Community 19 / 25

How are scores calculated?

Stars

8,847

Forks

753

Language

Jupyter Notebook

License

Last pushed

Mar 13, 2026

Monthly downloads

1,013,605

Commits (30d)

330

Dependencies

46

Reverse dependents

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/Arize-ai/phoenix"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.