⚙️AgentOps
AgentOps-AI/agentops · homepage ↗
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
⭐ Popular: 6k stars, gaining about 18 a week
View on GitHub ↗repo profile
momentum
durability
since we covered it
why it's a big deal
- Gives developers building AI agents a way to see step by step what an agent did, track LLM costs, and replay sessions to debug failures.
- Helps teams running multi-agent systems on frameworks like CrewAI, LangChain, and the OpenAI Agents SDK monitor behaviour from prototype through production.
- Is MIT licensed and self-hostable, so the dashboard, API, and backend can be run in-house rather than only as a hosted service.
under the hood
- Primary SDK is Python, with a TypeScript codebase alongside it, and integration is done through decorators such as session, agent, operation, and task.
- Setup is two lines, calling init with an API key and end_session, with support for async, generators, and custom attributes.
- Ships native integrations for OpenAI, Anthropic, Mistral, Cohere, and LiteLLM, plus agent frameworks including CrewAI, AG2, LangChain, LlamaIndex, and Camel AI.
Radar summary, generated from the project's public sources
star history
- PR#5 4k 2025-04-02
- now 6k + 2k since first covered
curve is sampled from GitHub's star history, plus our own daily readings since we covered it; the dashed stretch is before we first covered it, the solid line since. figures at coverage are the numbers we printed then (approx.), current count is live.
understory
Better known than its recent output, coasting a little on attention.
- output, commits & releases
- clout, star velocity
output = commits & releases; clout = star velocity, both 0 to 100 monthly indices; the gap where output runs above clout is the understory. The understory →
covered in
-
AI Agent Monitoring and Management
similar projects
compare these →- 🗜️ headroom
12× the stars
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
66k ACTIVE - ☤ hermes-agent
40× the stars
The agent that grows with you
231k ACTIVE - 🦌 DeerFlow
14× the stars
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.
80k ACTIVE
comments
Sign in with GitHub to add your blip on AgentOps.