phoenix

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:

• 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.
• PXI (Phoenix Intelligence) - An AI engineering agent built into Phoenix for debugging traces, iterating on prompts, and navigating the product.
• Remote MCP Server - Connect Claude Code, Cursor, and other MCP clients directly to your Phoenix instance's /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.

Table of Contents

• Run Locally
• Trace Your Application
• Deploy
• Packages
• Tracing Integrations
• Sandboxes
• For Humans and Coding Agents
• Security & Privacy
• Community

Run Locally

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

Trace Your Application

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.

Deploy

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.

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-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 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]

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
	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

Java Integrations

	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

Go Integrations

	Integration	Package	Version
	OpenAI	github.com/Arize-ai/openinference/go/openinference-instrumentation-openai-go
	Anthropic	github.com/Arize-ai/openinference/go/openinference-instrumentation-anthropic-sdk-go

Platforms

	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

Vector Databases

Integration	Description	Docs
Qdrant	Staged hybrid search tracing with dense, sparse, RRF	Integration Guide

Sandboxes

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

For Humans and Coding Agents

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:

• Claude Code or Codex. Install the Arize Phoenix plugin. It registers the Phoenix MCP server and installs the Phoenix skills.
• Any other agent. Add the Remote MCP Server at your instance's /mcp endpoint. It serves your Phoenix data and the Phoenix skills, which match your server version.
• Optional CLI. The Phoenix CLI, 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.

The skills live in skills/ and teach agents how to trace, evaluate, and debug with Phoenix:

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

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 p