Python SDK for AI agent monitoring, LLM cost tracking, benchmarking, and more. Integrates with most LLMs and agent frameworks including CrewAI, Agno, OpenAI Agents SDK, Langchain, Autogen, AG2, and CamelAI
Python agentagentopsagents-sdkaianthropicautogencost-estimationcrewaievalsevaluation-metricsgroqlangchainllmmistralollamaopenaiopenai-agents
API server test
This is a manual test with two files. It checks to make sure that the SDK works in an API environment.
Running the FastAPI Server
You can run FastAPI with:
uvicorn main:app --reload- To test, run
curl http://localhost:8000/completionin a different terminal.
Validate
Check in your AgentOps Dashboard
- two sessions are created with the
api-server-testtag. - Each session should have one
LLMEventand oneActionEvent. - Both sessions should have an end state of
Success - Neither session should have multiple agents