AgentOps and OpenAI Agents SDK integration for powerful multi-agent workflow monitoring.
Install the AgentOps SDK
Install OpenAI Agents SDK
Add 2 lines of code
agentops.init
before calling any openai
, cohere
, crew
, etc models..env
variable for easy access.Run your agents
Clickable link to session
Runner.run()
, the SDK runs a loop until it gets a final output:
max_turns
parameter to limit the number of loop executions.
output_type
on the agent, the final output is when the LLM returns something of that type using structured outputs.output_type
(i.e., plain text responses), then the first LLM response without any tool calls or handoffs is considered the final output.