comet-ml/opik

Project overview

Opik provides tracing, automated evaluation, and monitoring for generative AI applications, RAG systems, and agentic workflows. It supports local self-hosting via Docker Compose or a managed hosted service, and is built to handle up to 40 million traces per day.

Project type

Evaluation & Observability

Deployment

Refer to project documentation

License

Apache-2.0

Best for

• AI engineers and developers building, testing, and optimizing generative AI applications, RAG systems, and agentic workflows who require evaluation and observability.

Key capabilities

• Tracks all LLM calls and traces with detailed context during development and in production.
• Includes pre-built LLM-as-a-judge metrics like hallucination detection, moderation, and RAG assessment.
• Experiment with prompts and models in the Prompt Playground.
• Monitor feedback scores, trace counts, and token usage over time in the Opik Dashboard.
• Dedicated SDK and set of optimizers to enhance prompts and agents.
• Features to help you implement safe and responsible AI practices.

Limitations and risks

• GPU requirements, minimum hardware specifications, and telemetry configurations are not documented.

Getting started

• Clone the Opik repository, navigate to the repository directory, and start the Opik platform using the ./opik.sh command. This installation method uses a single command script for Docker Compose.

Evidence and sources

• GitHub project description: Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.
• README: Opik (built by Comet) is an open-source platform designed to streamline the entire lifecycle of LLM applications. It empowers developers to evaluate, test, monitor, and optimize t…
• README: Log high volumes of production traces: Opik is designed for scale (40M+ traces/day).
• README: The Python Opik SDK includes a number of LLM as a judge metrics to help you evaluate your LLM application. Learn more about it in the metrics documentation.
• README: ./opik.sh --guardrails # Guardrails with full Opik suite

Reviewed at: 2026-07-17T11:48:56Z