Find tools › Open-source projects › Test & monitor AI apps

opik
Open-source project · by comet-ml
An open-source dashboard for tracking, testing and grading what your AI app or agent does.
For developersPopular2,961,610 installs a month
What it costs
Free and open source; you may pay for the AI model it uses.
Use it to
- Record every step an AI agent takes in production
- Run automatic quality checks on chatbot answers
- Compare prompt versions and keep the best one
How to start
Install Python, then in a terminal run
pip install opik.Connect it to the hosted Opik service or your own self-hosted server.
Add Opik tracking to your AI app's code, following the docs.
Before you install
- Checked by a personWe read what it does before listing it.
- License: Apache-2.0You are allowed to use it under these terms.
- Last updated 2026-11-18
More detail
Debug, evaluate, and monitor LLM applications, RAG systems, and agentic workflows with comprehensive tracing and automated evaluations.
The project solves the need to track, evaluate, and optimize complex multi-step AI agent interactions and LLM calls in production without relying on closed-source SaaS platforms.
Similar tools
Descriptions are written in plain English from each project's own documentation and refreshed by our agent; this one was last checked 2026-09-29. Spotted a mistake? · Open in Find tools · © 2026 Which AI Map