Phoenix is an open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. It provides:
- Tracing - Trace your LLM application's runtime using OpenTelemetry-based instrumentation.
- Evaluation - Leverage LLMs to benchmark your application's performance using response and retrieval evals.
- Datasets - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
- Experiments - Track and evaluate changes to prompts, LLMs, and retrieval.
- Playground- Optimize prompts, compare models, adjust parameters, and replay traced LLM calls.
- Prompt Management- Manage and test prompt changes systematically using version control, tagging, and experimentation.
Phoenix is vendor and language agnostic with out-of-the-box support for popular frameworks (OpenAI Agents SDK, Claude Agent SDK, LangGraph, Vercel AI SDK, Mastra, CrewAI, LlamaIndex, DSPy) and LLM providers (OpenAI, Anthropic, Google GenAI, Google ADK, AWS Bedrock, OpenRouter, LiteLLM, and more). For details on auto-instrumentation, check out the OpenInference project.
Phoenix runs practically anywhere, including your local machine, a Jupyter notebook, a containerized deployment, or in the cloud.
Installation
Install Phoenix via pip or conda
pip install arize-phoenix
Phoenix container images are available via Docker Hub and can be deployed using Docker or Kubernetes. Arize AI also provides cloud instances at app.phoenix.arize.com.
Packages
The arize-phoenix package includes the entire Phoenix platform. However, if you have deployed the Phoenix platform, there are lightweight Python sub-packages and TypeScript packages that can be used in conjunction with the platform.
Python Subpackages
| Package | Version & Docs | Description |
|---|---|---|
| arize-phoenix-otel |   | Provides a lightweight wrapper around OpenTelemetry primitives with Phoenix-aware defaults |
| arize-phoenix-client |  | Lightweight client for interacting with the Phoenix server via its OpenAPI REST interface |
| arize-phoenix-evals |  | Tooling to evaluate LLM applications including RAG relevance, answer relevance, and more |
TypeScript Subpackages
| Package | Version & Docs | Description |
|---|---|---|
| @arizeai/phoenix-otel |   | Provides a lightweight wrapper around OpenTelemetry primitives with Phoenix-aware defaults |
| @arizeai/phoenix-client |  | Client for the Arize Phoenix API |
| @arizeai/phoenix-evals |  | TypeScript evaluation library for LLM applications (alpha release) |
| @arizeai/phoenix-mcp |   | MCP server implementation for Arize Phoenix providing unified interface to Phoenix's capabilities |
| @arizeai/phoenix-cli |  | CLI for fetching traces, datasets, and experiments for use with Claude Code, Cursor, and other coding agents |
Tracing Integrations
Phoenix is built on top of OpenTelemetry and is vendor, language, and framework agnostic. For details about tracing integrations and example applications, see the OpenInference project.
Python Integrations
| Integration | Package | Version | |
|---|---|---|---|
| <picture><source media="(prefers-color-scheme: dark)" srcset="https://unpkg.com/@lobehub/icons-static-png@latest/dark/openai.png"><img height="14" src="https://unpkg.com/@lobehub/icons-static-png@latest/light/openai.png"></picture> | OpenAI | openinference-instrumentation-openai |  |
| <picture><source media="(prefers-color-scheme: dark)" srcset="https://unpkg.com/@lobehub/icons-static-png@latest/dark/openai.png"><img height="14" src="https://unpkg.com/@lobehub/icons-static-png@latest/light/openai.png"></picture> | OpenAI Agents | openinference-instrumentation-openai-agents |  |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/llamaindex-color.png" height="14"> | LlamaIndex | openinference-instrumentation-llama-index |  |
| DSPy | openinference-instrumentation-dspy |  | |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/bedrock-color.png" height="14"> | AWS Bedrock | openinference-instrumentation-bedrock |  |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/langchain-color.png" height="14"> | LangChain | openinference-instrumentation-langchain |  |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/mistral-color.png" height="14"> | MistralAI | openinference-instrumentation-mistralai |  |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/google-color.png" height="14"> | Google GenAI | openinference-instrumentation-google-genai |  |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/google-color.png" height="14"> | Google ADK | openinference-instrumentation-google-adk |  |
| Guardrails | openinference-instrumentation-guardrails |  | |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/vertexai-color.png" height="14"> | VertexAI | openinference-instrumentation-vertexai |  |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/crewai-color.png" height="14"> | CrewAI | openinference-instrumentation-crewai |  |
| Haystack | openinference-instrumentation-haystack |  | |
| LiteLLM | openinference-instrumentation-litellm |  | |
| <picture><source media="(prefers-color-scheme: dark)" srcset="https://unpkg.com/@lobehub/icons-static-png@latest/dark/groq.png"><img height="14" src="https://unpkg.com/@lobehub/icons-static-png@latest/light/groq.png"></picture> | Groq | openinference-instrumentation-groq |  |
| Instructor | openinference-instrumentation-instructor |  | |
| <picture><source media="(prefers-color-scheme: dark)" srcset="https://unpkg.com/@lobehub/icons-static-png@latest/dark/anthropic.png"><img height="14" src="https://unpkg.com/@lobehub/icons-static-png@latest/light/anthropic.png"></picture> | Anthropic | openinference-instrumentation-anthropic |  |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/huggingface-color.png" height="14"> | Smolagents | openinference-instrumentation-smolagents |  |
| Agno | openinference-instrumentation-agno |  | |
| <picture><source media="(prefers-color-scheme: dark)" srcset="https://unpkg.com/@lobehub/icons-static-png@latest/dark/mcp.png"><img height="14" src="https://unpkg.com/@lobehub/icons-static-png@latest/light/mcp.png"></picture> | MCP | openinference-instrumentation-mcp |  |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/pydanticai-color.png" height="14"> | Pydantic AI | openinference-instrumentation-pydantic-ai |  |
| Autogen AgentChat | openinference-instrumentation-autogen-agentchat |  | |
| Portkey | openinference-instrumentation-portkey |  | |
| Agent Spec | openinference-instrumentation-agentspec |  | |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/claude-color.png" height="14"> | Claude Agent SDK | openinference-instrumentation-claude-agent-sdk |  |
Span Processors
Normalize and convert data across other instrumentation libraries by adding span processors that unify data.
| Package | Description | Version |
|---|---|---|
openinference-instrumentation-openlit | OpenInference Span Processor for OpenLIT traces. |  |
openinference-instrumentation-openllmetry | OpenInference Span Processor for OpenLLMetry (Traceloop) traces. |  |
JavaScript Integrations
| Integration | Package | Version | |
|---|---|---|---|
| <picture><source media="(prefers-color-scheme: dark)" srcset="https://unpkg.com/@lobehub/icons-static-png@latest/dark/openai.png"><img height="14" src="https://unpkg.com/@lobehub/icons-static-png@latest/light/openai.png"></picture> | OpenAI | @arizeai/openinference-instrumentation-openai |  |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/langchain-color.png" height="14"> | LangChain.js | @arizeai/openinference-instrumentation-langchain |  |
| <picture><source media="(prefers-color-scheme: dark)" srcset="https://unpkg.com/@lobehub/icons-static-png@latest/dark/vercel.png"><img height="14" src="https://unpkg.com/@lobehub/icons-static-png@latest/light/vercel.png"></picture> | Vercel AI SDK | @arizeai/openinference-vercel |  |
| BeeAI | @arizeai/openinference-instrumentation-beeai | | |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/claude-color.png" height="14"> | Claude Agent SDK | @arizeai/openinference-instrumentation-claude-agent-sdk |  |
| <picture><source media="(prefers-color-scheme: dark)" srcset="https://unpkg.com/@lobehub/icons-static-png@latest/dark/mastra.png"><img height="14" src="https://unpkg.com/@lobehub/icons-static-png@latest/light/mastra.png"></picture> | Mastra | @mastra/arize |  |
| <picture><source media="(prefers-color-scheme: dark)" srcset="https://unpkg.com/@lobehub/icons-static-png@latest/dark/mcp.png"><img height="14" src="https://unpkg.com/@lobehub/icons-static-png@latest/light/mcp.png"></picture> | MCP | @arizeai/openinference-instrumentation-mcp |  |
Java Integrations
| Integration | Package | Version | |
|---|---|---|---|
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/langchain-color.png" height="14"> | LangChain4j | openinference-instrumentation-langchain4j |  |
| SpringAI | openinference-instrumentation-springAI |  | |
| Arconia | openinference-instrumentation-springAI | |
Platforms
| Platform | Description | Docs | |
|---|---|---|---|
| BeeAI | AI agent framework with built-in observability | Integration Guide | |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/dify-color.png" height="14"> | Dify | Open-source LLM app development platform | Integration Guide |
| Envoy AI Gateway | AI Gateway built on Envoy Proxy for AI workloads | Integration Guide | |
| LangFlow | Visual framework for building multi-agent and RAG applications | Integration Guide | |
| LiteLLM Proxy | Proxy server for LLMs | Integration Guide | |
| Flowise | Visual framework for building LLM applications | Integration Guide | |
| Prompt Flow | Microsoft's prompt flow orchestration tool | Integration Guide | |
| <img src="https://unpkg.com/@lobehub/icons-static-png@latest/dark/nvidia-color.png" height="14"> | NVIDIA NeMo | NVIDIA NeMo Agent Toolkit for enterprise agents | Integration Guide |
| Graphite | Multi-agent LLM workflow framework with visual builder | Integration Guide |
Security & Privacy
We take data security and privacy very seriously. For more details, see our Security and Privacy documentation.
Telemetry
By default, Phoenix collects basic web analytics (e.g., page views, UI interactions) to help us understand how Phoenix is used and improve the product. None of your trace data, evaluation results, or any sensitive information is ever collected.
You can opt-out of telemetry by setting the environment variable: PHOENIX_TELEMETRY_ENABLED=false
Community
Join our community to connect with thousands of AI builders.
- π Join our Slack community.
- π Read our documentation.
- π‘ Ask questions and provide feedback in the #phoenix-support channel.
- π Leave a star on our GitHub.
- π Report bugs with GitHub Issues.
- π Follow us on π.
- πΊοΈ Check out our roadmap to see where we're heading next.
- π§βπ« Deep dive into everything Agents and LLM Evaluations on Arize's Learning Hubs.
Breaking Changes
See the migration guide for a list of breaking changes.
Copyright, Patent, and License
Copyright 2025 Arize AI, Inc. All Rights Reserved.
Portions of this code are patent protected by one or more U.S. Patents. See the IP_NOTICE.
This software is licensed under the terms of the Elastic License 2.0 (ELv2). See LICENSE.