AI observability and evaluation tool for tracing and evaluating LLM applications.
🇺🇸 English • 🇨🇳 中文 • 🇹🇼 繁體中文 • 🇯🇵 日本語 • 🇵🇹 Português • • • • • • • • • • • • • • • • • • • • • • • • • • • •
Arize Phoenix is Arize's open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. For managed production workflows, Arize also offers Arize AX. Phoenix provides:
/mcp endpoint to query traces, datasets, experiments, and more.
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 containerized deployment, or in the cloud. See Self-Hosting for a walkthrough of each option, or jump straight into the Tracing Quickstart.
[!NOTE]
Phoenix is open-source and self-hosted. For a managed platform, Arize offers Arize AX — the same OpenTelemetry/OpenInference instrumentation works with both. See the full comparison.
Install Phoenix via pip or conda and have a fully functional Phoenix. For all installation and hosting options, see the install guide.
pip install arize-phoenix
phoenix serve
Or run it with no install using uvx:
uvx arize-phoenix serve
The fastest way to send traces is to let your coding agent (Claude Code, Codex, Cursor, and others) instrument your app. From your project directory, run:
npx @arizeai/phoenix-cli setup
## or, with Phoenix installed: px setup
Setup detects your framework and LLM provider, installs the right OpenInference instrumentation, and wires up trace export. Prefer to wire it up in code? See the tracing documentation.
Phoenix container images are available via Docker Hub and can be deployed using Docker or Kubernetes via the Helm chart.
For Docker Compose, Kubernetes/Helm, and other deployment options, see the self-hosting documentation.
[!NOTE]
The Google Cloud button builds Phoenix from source in Cloud Shell rather than deploying the prebuilt Docker Hub image. The Azure template serves plain HTTP (Azure Container Instances does not terminate TLS) — front it with a TLS proxy such as an Application Gateway before production use.
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.
| 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 |
| 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-cli |  | CLI for fetching traces, datasets, and experiments for use with Claude Code, Cursor, and other coding agents |
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 and the integrations documentation.
Python Integrations
| Integration | Package | Version | |
|---|---|---|---|
 | OpenAI | openinference-instrumentation-openai |  |
| OpenAI Agents | openinference-instrumentation-openai-agents |  |
 | LlamaIndex | openinference-instrumentation-llama-index |  |
| DSPy | openinference-instrumentation-dspy |  | |
 | AWS Bedrock | openinference-instrumentation-bedrock |  |
 | LangChain | openinference-instrumentation-langchain |  |
| LangGraph | openinference-instrumentation-langchain | |
 | MistralAI | openinference-instrumentation-mistralai |  |
 | Cohere | openinference-instrumentation-cohere |  |
 | Together AI | openinference-instrumentation-together |  |
 | Ollama | openinference-instrumentation-ollama |  |
 | Google GenAI | openinference-instrumentation-google-genai |  |
| Google ADK | openinference-instrumentation-google-adk |  |
| Guardrails | openinference-instrumentation-guardrails |  | |
 | VertexAI | openinference-instrumentation-vertexai |  |
 | CrewAI | openinference-instrumentation-crewai |  |
| Haystack | openinference-instrumentation-haystack |  | |
| LiteLLM | openinference-instrumentation-litellm |  | |
| OpenRouter | openinference-instrumentation-openai | | |
| OrcaRouter | openinference-instrumentation-openai | | |
 | Groq | openinference-instrumentation-groq |  |
| Instructor | openinference-instrumentation-instructor |  | |
 | Anthropic | openinference-instrumentation-anthropic |  |
 | Smolagents | openinference-instrumentation-smolagents |  |
| Agno | openinference-instrumentation-agno |  | |
| BeeAI | openinference-instrumentation-beeai |  | |
| Strands Agents | openinference-instrumentation-strands-agents |  | |
| Restate | openinference-instrumentation-openai-agents | | |
 | MCP | openinference-instrumentation-mcp |  |
| Microsoft Agent Framework | openinference-instrumentation-agent-framework |  | |
 | Pydantic AI | openinference-instrumentation-pydantic-ai |  |
| Pipecat | openinference-instrumentation-pipecat |  | |
| AG2 | openinference-instrumentation-ag2 |  | |
| Autogen AgentChat | openinference-instrumentation-autogen-agentchat |  | |
| Portkey | openinference-instrumentation-portkey |  | |
| Agent Spec | openinference-instrumentation-agentspec |  | |
 | Claude Agent SDK | openinference-instrumentation-claude-agent-sdk |  |
| TypeSafe AI | openinference-instrumentation-typesafe |  | |
| Atomic Agents | atomic-agents[observability] |  |
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. |  |
| Integration | Package | Version | |
|---|---|---|---|
| OpenAI | @arizeai/openinference-instrumentation-openai |  |
| OpenAI Agents | @arizeai/openinference-instrumentation-openai-agents |  |
| LangChain.js | @arizeai/openinference-instrumentation-langchain |  |
| TanStack AI | @arizeai/openinference-tanstack-ai |  | |
 | Vercel AI SDK | @arizeai/openinference-vercel |  |
| BeeAI | @arizeai/openinference-instrumentation-beeai |  | |
| Claude Agent SDK | @arizeai/openinference-instrumentation-claude-agent-sdk |  |
 | Mastra | @mastra/arize |  |
| MCP | @arizeai/openinference-instrumentation-mcp |  |
| TypeSafe AI | @arizeai/openinference-instrumentation-typesafe |  |
| Integration | Package | Version | |
|---|---|---|---|
| LangChain4j | openinference-instrumentation-langchain4j |  |
| SpringAI | openinference-instrumentation-springAI |  | |
 | Arconia for Spring AI | io.arconia:arconia-openinference-semantic-conventions |  |
| Google ADK | openinference-instrumentation-adk-java |  |
| Platform | Description | Docs | |
|---|---|---|---|
| BeeAI | AI agent framework with built-in observability | Integration Guide | |
 | 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 | |
 | NVIDIA NeMo | NVIDIA NeMo Agent Toolkit for enterprise agents | Integration Guide |
| Graphite | Multi-agent LLM workflow framework with visual builder | Integration Guide |
| Integration | Description | Docs |
|---|---|---|
| Qdrant | Staged hybrid search tracing with dense, sparse, RRF | Integration Guide |
Run Phoenix code evaluators in hosted sandbox providers for kernel-level isolation and runtime dependency installation.
| Integration | Description | Docs |
|---|---|---|
| E2B | Hosted micro-VM sandboxes for AI-generated code | Integration Guide |
| Daytona | Managed development sandboxes with snapshot startup | Integration Guide |
| Vercel Sandbox | Ephemeral compute on Vercel's infrastructure | Integration Guide |
| Modal | Serverless, Python-first container platform | Integration Guide |
| Docker Sandboxes | Cloud sandboxes hosted by Docker | Integration Guide |
People and coding agents such as Claude Code, Codex, and Cursor can both work with Phoenix. To give an agent access to your traces, datasets, and experiments, connect it in one of these ways:
/mcp endpoint. It serves your Phoenix data and the Phoenix skills, which match your server version.npx @arizeai/phoenix-cli, runs Phoenix commands in a terminal, and px setup instruments your app through your coding agent.See Connect Your Coding Agent for setup steps.
| Skill | Description |
|---|---|
| phoenix-cli | Debug LLM applications with the Phoenix CLI. Fetch traces, analyze errors, review experiments, and query the GraphQL API |
| phoenix-error-analysis | Read sampled traces, write notes, and group them into failure categories that pick eval targets and fix priorities |
| phoenix-evals | Build, run, and validate evaluators for AI/LLM applications using Phoenix |
| phoenix-harbor | Configure and interpret the Phoenix plugin for Harbor agent evaluations |
| phoenix-tracing | OpenInference semantic conventions and instrumentation for tracing LLM applications |
We take data security and privacy very seriously. For more details, see our Security and Privacy documentation.
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
Join our community to connect with thousands of AI builders.
See the migration guide for a list of breaking changes.
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.
Phoenix is fully open source and built in the open. If it helps you, please ⭐ star the repo to support the project.
What is Arize Phoenix? Arize Phoenix is a coding tool listed on Scriptiii AI Tools. AI observability and evaluation tool for tracing and evaluating LLM applications. Pricing: Free. Free to use. Best for: ai-agents, tool, observability-evals.
Everything you need to know about Arize Phoenix
Similar tools in Coding