Configs2026年4月1日·1 分钟阅读

Phoenix — Open Source AI Observability

Phoenix is an AI observability platform for tracing, evaluating, and debugging LLM apps. 9.1K+ stars. OpenTelemetry, evals, prompt management.

AI Open Source
AI Open Source · Community
介绍

Phoenix is an open-source AI observability platform for tracing, evaluation, and troubleshooting LLM apps. With 9,100+ GitHub stars, it provides OpenTelemetry-based tracing, LLM evaluation benchmarks, datasets and experiments, a prompt playground, and prompt version management. Integrates with LangChain, LlamaIndex, CrewAI, OpenAI, Anthropic.

Best for: Teams debugging production LLM applications Works with: Claude Code, OpenAI Codex, Cursor, Gemini CLI, Windsurf

Key Features

  • OpenTelemetry tracing for every LLM call
  • LLM evaluation with built-in metrics
  • Versioned datasets and experiments
  • Prompt playground and management
  • Self-hosted or cloud

FAQ

Q: What is Phoenix? A: AI observability platform with 9.1K+ stars. OpenTelemetry tracing, evals, prompt management.

Q: How do I install Phoenix? A: pip install arize-phoenix. Access at localhost:6006.

🙏

来源与感谢

Arize-ai/phoenix — 9,100+ GitHub stars

讨论

登录后参与讨论。
还没有评论，来写第一条吧。

相关资产

Google Benchmark — Microbenchmark Library for C++

Google Benchmark is a library for measuring and reporting the performance of C++ code with statistical rigor.

AI Open Source

Mockito — The Most Popular Java Mocking Framework

Mockito lets Java developers create clean mock objects and verify interactions with a simple, readable API.

AI Open Source

Catch2 — Modern C++ Test Framework with Natural Expressions

Catch2 is a header-only C++ testing framework known for its expressive assertion syntax and zero-config setup.

AI Open Source
◈首页🔍搜索👤我的