#3838th of 42 in Gateways and observability
agentops
Tracing, session replay and LLM cost tracking for AI agents
- Stars
- 5.9k
- License
- MIT
- Last commit
- Jun 2026
- Last release
- Aug 2025
- Language
- Python
5,362 on 3 Apr 20265,934 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
AgentOps is a Python SDK plus a dashboard and API backend that records agent runs as spans, with session replay, execution graphs and per-provider LLM spend. Decorators (@session, @agent, @operation, @task, @workflow) and integrations for OpenAI Agents SDK, CrewAI, AG2, LangChain, Anthropic, Mistral, Cohere and LiteLLM feed the traces. The app is MIT-licensed and can be self-hosted using app/README.md.
Who it is for: Developers who need tracing and cost visibility for agents in production
Strengths
- Two-line init plus span decorators; supports async functions and generators
- Integrations for OpenAI Agents SDK, CrewAI, AG2, LangChain, Anthropic, Mistral, Cohere
- Session replay, execution graphs and LLM cost tracking in one dashboard
- Dashboard and API backend are MIT-licensed and self-hostable
Weaknesses
- No Docker or compose files detected; self-hosting steps live in a separate app/README.md
- Quick start points to the hosted dashboard and an API key
- Last release 2025-08-29, well behind recent commits
- README mixes v1 and v2 APIs (end_session vs decorators), which is confusing
What it needs
- no GPU
- Needs AgentOps API key (hosted dashboard)
- Models: OpenAI, Anthropic, Mistral, Cohere, LiteLLM
Quick answers
Is agentops open source?
Yes. Its code is on GitHub under the MIT license.
Does agentops need a GPU?
No, it runs without one.
Also in Gateways and observability
See all 42| Rank | Project | Score |
|---|---|---|
| 1 | OmniRouteLLM gateway routing one OpenAI-compatible endpoint across 372 providers | 96 out of 100 |
| 2 | new-apiGateway that unifies LLM providers behind OpenAI, Anthropic and Gemini APIs | 90 out of 100 |
| 3 | MLflowTracing, evals, prompt registry and AI gateway plus classic ML tracking | 89 out of 100 |
| #4 | LiteLLMOpenAI-format gateway and Python SDK for calling 100+ LLM providers | 87 out of 100 |
| #5 | freellmapiOpenAI-compatible gateway pooling free-tier LLM providers with automatic failover | 86 out of 100 |