Comet builds open tools and infrastructure to help teams ship better models. From ML experiment tracking to LLM tracing and context-aware agents, we support developers across the entire AI lifecycle.
Getting Started
🔬 Explore Opik: Debug, trace, evaluate and monitor LLM apps and RAG pipelines
📈 Use Comet ML: Track experiments, datasets, models, and monitor production ML
🧪 Try real-world Examples: Notebooks, integrations, and how-tos
⚙️ Extend with opik-mcp: Opik + MCP integration for structured LLM evaluation
comet-examples – Tutorials, notebooks, and example pipelines
opik-mcp – MCP-powered context and eval framework for Opik
Contributing
We welcome contributions of all kinds – code, docs, feedback, and examples.
Start with any repo’s README and check out the open issues.
See our CONTRIBUTING.md for more information and guidelines.
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
Model Context Protocol (MCP) server for Opik, the open-source LLM observability and evaluation platform, built by Comet. Read traces, log scores, and manage prompts from Claude Code, Cursor, or VS …
Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
Model Context Protocol (MCP) server for Opik, the open-source LLM observability and evaluation platform, built by Comet. Read traces, log scores, and manage prompts from Claude Code, Cursor, or VS Code.
You are visitor 01402503 — GeezerVison does not store the pages you look up. Best viewed with Netscape Navigator 4.7 or Internet Explorer 6 at 800×600. No cookies required.