AI and models · Independent · 19 Oct 2026

comet-ml/opik

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards.

← AI and models
Opik: LLM Observability & Evaluation. Trace, evaluate, and monitor your AI agents.

In simple English

This tool records every step your artificial intelligence program makes. It helps you find where your prompts fail or hallucinate wrong answers. You can run it on your own server for free under an open-source licence. It works with Python, JavaScript, and many popular agent frameworks. Setting up the full server takes some time and requires Docker.

What it is

Opik is an open-source platform for tracking, evaluating, and monitoring language model applications and multi-step agents. It provides a Python client library, a web dashboard, and a self-hosted backend.

What it is good for

Solo builders who want to debug complex AI agents, measure hallucination rates, and track token costs across different models without paying for a commercial cloud service.

Stars23k
LicenceApache-2.0
Latest2.2.105 (2026-10-19)checked 19 Oct 2026
Last code change2026-10-19
Written inPython
Setup effort
3 / 5
Payoff
5 / 5
Good
  • Full platform is open-source under the Apache-2.0 licence and free to self-host.
  • Integrates natively with dozens of agent frameworks like LangChain, LlamaIndex, and CrewAI.
  • Includes pre-built evaluation metrics to test for hallucinations and answer relevance.
Watch for
  • Running the full server locally requires Docker (a way to run a program inside its own sealed box, so it cannot break anything else on your server) and consumes significant RAM (random-access memory, the fast working memory your computer uses to hold open programs).
  • Non-programmers will find the server setup and SDK integration challenging.
  • Heavy production usage generates millions of traces that require careful database maintenance.
Replaces

Checking console logs manually or paying for commercial AI monitoring tools

Works well with

LangChain

Similar repositories
  • langfuse/langfuse36k stars

    An open-source language model engineering platform with tracing, prompts, and evaluations.

  • BerriAI/litellm62k stars

    A proxy and routing tool that standardises calls to hundreds of language models and logs usage.

Also reviewed on Repo Radar
  • ggml-org/llama.cpp132k stars

    A C and C++ library and command-line tool for running language models locally.

  • EleutherAI/lm-evaluation-harness14k stars

    Runs standard question sets against a language model and reports the scores.

  • mudler/LocalAI50k stars

    Serves text, vision, speech, image and video models from one self-hosted service that imitates the paid interfaces.

Install
pip install opik
opik configure

Independent: reviewed for Repo Radar outside the daily editions. Every independent repository

On Stack Radar: AI & Automation › AI Development & Evaluation › AI Observability.

Get the next edition in your inbox

A dozen repositories, opened and checked. The licence read, the last release dated, and the ones that did not make it named with the reason. It is the half most lists leave out.

No tracking pixels. One click to leave. The archive stays free either way.

We use your address to send the edition and nothing else. Confirm by email, leave in one click. How we handle it.