Phoenix integrates with the leading AI frameworks, LLM providers, and tools to provide seamless observability, evaluation, and debugging for your AI applications. Whether you’re building with Python, TypeScript, or Java, Phoenix has you covered.
Don’t see an integration you need? We’d love to hear from you!
Integration Types
Phoenix offers several types of integrations to support your AI development workflow:
Developer Tools
Debug with Phoenix from Claude Code, Cursor and other coding assistants.
Eval Model Integrations
Run Phoenix evals with any LLM provider.
Evaluation Integrations
Record results from Harbor, Ragas, Cleanlab and MLflow.
Sandboxes
Run code evaluators in isolated, hosted sandboxes.
Span Processors
Convert traces from other libraries to OpenInference.
Tracing Integrations
Capture traces from popular frameworks and LLM providers.
Developer Tools
Integrate Phoenix with AI coding assistants to debug and analyze your LLM applications directly from your development environment.
Coding Agents
Install Phoenix debugging skills and CLI for Claude Code, Cursor, and other AI coding assistants.
MCP Server
Connect AI assistants to your Phoenix data and docs via the Model Context Protocol.
Tracing Integrations
Phoenix captures detailed traces from your AI applications, giving you visibility into every step of your LLM pipeline.By Language
- Python
- TypeScript
- Java
- .NET
- Go
AG2
Agent Spec
Agno
Atomic Agents
AutoGen
Bedrock AgentCore
BeeAI
CrewAI
DSPy
Google ADK
Graphite
Guardrails AI
Haystack
Instructor
LangChain
LangGraph
LiveKit Agents
LlamaIndex
MCP
Microsoft Agent Framework
NVIDIA
OpenAI Agents SDK
Pipecat
Portkey
Pydantic AI
Semantic Kernel
smolagents
Temporal
LLM Providers
Phoenix provides native tracing support for all major LLM providers:
Amazon Bedrock
Anthropic
Baseten
Cerebras
Cloudflare AI Gateway
Cohere
DeepSeek
Doubleword
Fireworks AI
Gravitee
Groq
Hugging Face Inference Providers
LiteLLM
MistralAI
Novita AI
Ollama
OpenAI
OpenRouter
OrcaRouter
PrismML
Qwen
Together AI
TrueFoundry
TypeSafe AI
VertexAI
vLLM
xAI Grok
Z.ai
Platforms
Integrate Phoenix with AI development platforms and infrastructure:
Claude Managed Agents
Dify
Envoy AI Gateway
Flowise
LangFlow
LiteLLM Proxy
n8n
Open WebUI
OpenRouter Broadcast
Prompt Flow
Scalekit
TrueFoundry AI Gateway
Vector Databases
Trace retrieval from vector databases to see which stage of a search to fix:
Qdrant
Coding Agents
Trace your sessions with a coding agent — turns, tool calls, and token costs — in Phoenix, no application code changes required. Install the coding-harness-tracing toolkit and pick your agent:
Antigravity
Claude Code
Codex
Cursor
Devin
Gemini CLI
GitHub Copilot
Kiro
Oh My Pi
OpenCode
Eval Model Integrations
Phoenix’s evaluation library (phoenix-evals) can use any LLM provider to power evaluations. These models score, classify, and analyze your traces.
Amazon Bedrock
Anthropic
Google Gemini
LiteLLM
MistralAI
OpenAI
VertexAI
Evaluation Integrations
Connect external evaluation frameworks and libraries to Phoenix:
Cleanlab
Harbor
Microsoft Azure AI Evaluation
MLflow
NVIDIA RAG Metrics via Ragas
Pydantic Evals
Ragas
Span Processors
Normalize and convert data from other instrumentation libraries by adding span processors that unify traces to the OpenInference format:
OpenLIT
OpenLLMetry (Traceloop)
Sandboxes
Run Phoenix code evaluators in hosted sandbox providers for kernel-level isolation, runtime dependency installation, and opt-in outbound network access. Configure providers from Settings → Sandboxes.
Daytona
Docker Sandboxes
E2B
Modal
