Trace and debug agent runs with AgentOps

Trace and debug agent runs with AgentOps

Instrument agent sessions so operators can replay runs, track model costs, inspect tool calls, and compare behavior across frameworks.

Prerequisites

AgentOps Python SDK or supported framework integration, AgentOps API key or self-hosted deployment, agent runtime using OpenAI Agents SDK, CrewAI, Agno, LangChain, AutoGen/AG2, CamelAI, or another supported integration

Installation

Use the upstream install or setup path that matches your environment:

• pip install agentops
• pip install openai-agents
• npm install agentops @openai/agents
• pip install 'crewai[agentops]'

Requirements and caveats from upstream:

• python
• Build multi-agent systems with tools, handoffs, and guardrails. AgentOps natively integrates with the OpenAI Agents SDKs for both Python and TypeScript.
• Python integration guide

Basic usage or getting-started notes:

• | ⚒️ Self-Host | Want to run AgentOps on your own cloud? You're covered |

• Initialize the AgentOps client and automatically get analytics on all your LLM calls.

• Get an API key

• Source: https://github.com/AgentOps-AI/agentops

• Extracted from upstream docs: https://raw.githubusercontent.com/AgentOps-AI/agentops/HEAD/README.md

Documentation

• https://docs.agentops.ai

Source

• Agent Skill Exchange