Arize Phoenix

Open source

Arize Phoenix is an open-source AI observability platform for tracing, evaluating and experimenting with LLM applications.

GitHub stars
12k
Last 30 days
+442(+4%)
Last commit
today
Repository age
4 years
Version
arize-phoenix-v21.1.0
Licence
Custom
Self-hosted
Yes

About Arize Phoenix

Phoenix is built for experimentation, evaluation and troubleshooting of LLM apps. It traces an application's runtime using OpenTelemetry-based instrumentation, runs LLM-based evaluations of responses and retrieval, and keeps versioned datasets and experiments for comparing changes to prompts, models and retrieval.

Beyond tracing, it has a playground for comparing models and replaying traced calls, prompt management with version control and tagging, PXI, an agent built in for debugging traces, and a remote MCP server so tools such as Claude Code and Cursor can query traces, datasets and experiments. It is vendor and language agnostic, with support for frameworks like LangGraph, CrewAI, LlamaIndex and DSPy and providers such as OpenAI, Anthropic and AWS Bedrock.

Phoenix is open source and self-hosted. Install with pip install arize-phoenix and phoenix serve, run it with uvx, or deploy container images on Docker or Kubernetes through the Helm chart. For a managed platform, Arize sells Arize AX, and the same OpenTelemetry and OpenInference instrumentation works with both.

Key features

  • OpenTelemetry-based tracing of LLM applications
  • LLM-powered evaluation of responses and retrieval
  • Versioned datasets for experiments and fine-tuning
  • Prompt playground with model comparison and trace replay
  • Prompt management with version control and tagging
  • Remote MCP server for coding agents
  • Setup command detects framework and wires up trace export

Good fit for

  • Tracing agent and RAG applications
  • Evaluating prompt changes
  • Comparing models in a playground
  • Querying traces from coding agents
Built with
Python tools
Tags
llm
observability
tracing
evaluation
opentelemetry
prompt-engineering
mcp
ai-engineering

Arize Phoenix: questions and answers

What is Arize Phoenix used for?
Arize Phoenix is an open-source AI observability platform for tracing, evaluating and experimenting with LLM applications. It is a good fit for tracing agent and RAG applications, evaluating prompt changes, and comparing models in a playground.
Is Arize Phoenix open source?
Yes. Arize Phoenix is open source under a custom licence. Its source code is on GitHub at Arize-ai/phoenix and is written mainly in Python.
Is Arize Phoenix free?
Yes. Arize Phoenix is open source, so the software itself is free to use under the terms of its own licence. A managed cloud version is also available.
Can I self-host Arize Phoenix?
Yes. Arize Phoenix can be self-hosted on your own server or infrastructure.
What is Arize Phoenix an alternative to?
Arize Phoenix is an open-source alternative to Weights & Biases, LangSmith, Arize AI and Braintrust. Other open-source alternatives to Weights & Biases include Langfuse, Opik and Laminar.
Is Arize Phoenix actively maintained?
Yes. The most recent commit to Arize Phoenix was on 15 November 2026. The project has 12k stars on GitHub, with 442 added in the last 30 days.

Open-source alternatives to Arize Phoenix

See all

SaaS alternatives to Arize Phoenix

See all