BigHugger
GH Repository · comet-ml

opik

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

stars
22,090
30-day movement
starts with the next reading
Related entries
60
Connections
3
makePythonopen-sourceopenaihacktoberfest2025playgroundagent-frameworkprompt-engineeringhacktoberfestllama-indexllm-observabilityllmlangchainllm-evaluationllmopsevaluation

Opik is an open-source Python tool from Comet for debugging, evaluating, and monitoring LLM applications, RAG systems, and agentic workflows. It provides tracing, automated evaluations, and production dashboards, with integration points for LangChain, OpenAI, and Llama-Index.

You need observability and evaluation in one place when building or running LLM and agent applications.

Use it to

  • Trace LLM and agent executions
  • Run automated LLM evaluations
  • Monitor RAG systems in production
  • Experiment with prompts in a playground
  • Track LLM ops metrics on dashboards

For Developers building and operating LLM and agent applications

Role
agent-framework
Language
Python
Licence
Apache-2.0
Forks
1,800
Open issues
119
Last push
2026-09-17
Latest release
0.1.0 · 2024-09-02
topicsllm-observabilityllm-evaluationllmopstracingagentsopen-source