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
AgentOps is a Python SDK and observability platform for monitoring, debugging, and cost-tracking AI agents built with Anthropic's Claude and other LLM providers. Developers initialize it with two lines of code, after which it automatically captures session replays, step-by-step execution graphs, and per-call spend data across supported frameworks including CrewAI, LangChain, AG2/AutoGen, Agno, LlamaIndex, and the OpenAI Agents SDK. It connects to Claude via the Anthropic API and also ships an MCP server published on Smithery, making it accessible from Claude Desktop environments. A standout detail is that the entire application layer, including the dashboard and API backend, is open source under the MIT license and can be self-hosted on a private cloud. The tool targets AI engineers who need production-grade visibility into multi-agent pipelines, LLM token costs, and replay debugging without relying on a third-party hosted service.
- ✓Open-source license (MIT)
- ✓Recently active
- ✓Healthy fork ratio
- ✓Clear description
- ✓Topics declared
- ✓Mature repo (>1y old)
git clone https://github.com/AgentOps-AI/agentops && cp agentops/*.md ~/.claude/agents/Subagents overview
What people ask about agentops
What is AgentOps-AI/agentops?
+
AgentOps-AI/agentops is subagents for the Claude AI ecosystem. 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 It has 5.7k GitHub stars and was last updated 1mo ago.
How do I install agentops?
+
You can install agentops by cloning the repository (https://github.com/AgentOps-AI/agentops) or following the README instructions on GitHub. ClaudeWave also provides quick install blocks on this page.
Is AgentOps-AI/agentops safe to use?
+
Our security agent has analyzed AgentOps-AI/agentops and assigned a Trust Score of 100/100 (tier: Verified). See the full breakdown of passed checks and flags on this page.
Who maintains AgentOps-AI/agentops?
+
AgentOps-AI/agentops is maintained by AgentOps-AI. The last recorded GitHub activity is from 1mo ago, with 179 open issues.
Are there alternatives to agentops?
+
Yes. On ClaudeWave you can browse similar subagents at /categories/agents, sorted by popularity or recent activity.
Deploy agentops to your cloud
Ship this repo to production in minutes. Each platform spins up its own environment with editable env vars.
Maintain this repo? Add a badge to your README
Drop the badge into your GitHub README to show it's tracked on ClaudeWave. Each badge links back to this page and reflects the live Trust Score.
[](https://claudewave.com/repo/agentops-ai-agentops)<a href="https://claudewave.com/repo/agentops-ai-agentops"><img src="https://claudewave.com/api/badge/agentops-ai-agentops" alt="Featured on ClaudeWave: AgentOps-AI/agentops" width="320" height="64" /></a>More Subagents
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
The agent that grows with you
Java 面试 & 后端通用面试指南，覆盖计算机基础、数据库、分布式、高并发、系统设计与 AI 应用开发
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
The agent engineering platform.
Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Cursor, Codex, and Gemini CLI: local deterministic AST parsing, every edge explained, no vector store.