Arize Phoenix

Open-source tool to trace, evaluate and improve AI agents, run locally or self-hosted

Observability tool by Arize AI

IndexedOther★ 11,985

Install

Pick your client. Read the repository before you give any tool access to your data.

pip install arize-phoenix

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

Phoenix collects traces of model calls, retrieval, tool use and custom logic over OpenTelemetry, with auto-instrumentation for common frameworks. It scores traces and spans with LLM-based, code-based or human evaluators, and supports prompt iteration and experiments on datasets.

Use cases: monitoring-observability, llm-evaluation

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Fact sheet

Category: Tracing · open source
Self-host: Yesarize.com
Open source: Yesarize.com
Works with: llamaindex, langchain, dspy, mastra, vercel-ai-sdkarize.com
Protocols: opentelemetryarize.com

Facts read from the vendor's own pages by claude-haiku-5-5 on Oct 24, 2026; a fact is shown only with the page it came from.

Signals

Stars: 11,985
Forks: 1,236
Open issues: 1,028
Last commit: Oct 24, 2026 (4 days ago)
Last release: Oct 24, 2026 (4 days ago)

Details

Packages: pypi arize-phoenix
License: Other
Repository: github.com/Arize-ai/phoenix
Website: arize.com/phoenix/
Docs: arize.com/docs/phoenix
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Website Docs README