Integrations hook into agent frameworks to automatically trace the full agent lifecycle: LLM calls, tool invocations, sub-agent handoffs, guardrails, and related steps. Use the table below to choose the right package extra, then open the integration guide for framework-specific setup.Documentation Index
Fetch the complete documentation index at: https://docs.pandaprobe.com/llms.txt
Use this file to discover all available pages before exploring further.
| Integration | Install Extra | Class | Mechanism |
|---|---|---|---|
| LangGraph | "pandaprobe[langgraph]" | LangGraphCallbackHandler | LangChain callback handler |
| Google ADK | "pandaprobe[google-adk]" | GoogleADKAdapter | wrapt monkey-patching |
| Claude Agent SDK | "pandaprobe[claude-agent-sdk]" | ClaudeAgentSDKAdapter | wrapt monkey-patching + hook injection |
| CrewAI | "pandaprobe[crewai]" | CrewAIAdapter | wrapt monkey-patching |
| OpenAI Agents SDK | "pandaprobe[openai-agents]" | OpenAIAgentsAdapter | First-class TracingProcessor callback |
session_id— optional session identifieruser_id— optional user identifiertags— optional list of string tagsmetadata— optional dict of key-value pairs
All integrations automatically produce properly nested span hierarchies. You do not need to create traces or spans manually.
LangGraph
Callback handler for LangGraph / LangChain
Google ADK
Monkey-patch instrumentation for ADK runners and tools
Claude Agent SDK
Hooks and patches for Claude Agent SDK clients
CrewAI
Crew kickoff, agents, LLM, and tool spans
OpenAI Agents SDK
First-class TracingProcessor integration