# comet-ml/opik

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

Repository: https://github.com/comet-ml/opik
Canonical: https://ross.abutalabs.com/products/opik
Homepage: https://www.comet.com/docs/opik/
Language: Python
License: Apache-2.0
License Family: permissive
Topics: open-source, langchain, openai, playground, prompt-engineering, llama-index, llm, llm-evaluation, llm-observability, llmops, hacktoberfest, hacktoberfest2025, evaluation
Last push: 2026-08-26T19:30:24+00:00

## Health v2 (maintenance only)
Score: 92/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 99, release rhythm 87, longevity 86
- inputs: {"age_days": 1211, "days_push": 7, "days_rel": 7, "gap_med": 0.0, "n_releases_24m": 527}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 21624, forks 1732 (observed 2026-08-28T04:11:31.877446+00:00)

## What it is
Opik is an open-source LLM observability and evaluation platform by Comet for tracing, evaluating, and monitoring LLM applications, RAG pipelines, and agentic workflows. It offers Python/TypeScript SDKs, broad framework integrations, prompt management, guardrails, an MCP server, and can be self-hosted via Docker or Kubernetes or used as a managed cloud.

## Use cases
- trace and debug LLM agent workflows in production
- evaluate LLM outputs with automated metrics and datasets
- manage and version prompts for a RAG pipeline
- monitor LLM app costs and latency with dashboards
- self-host an LLM observability platform on Kubernetes
- add guardrails against prompt injection
- integrate LangChain or OpenAI tracing into an evaluation workflow

## When to choose
- you need end-to-end tracing and evaluation for LLM apps, RAG systems, or agents
- you want an open-source, self-hostable alternative to LangSmith or Langfuse
- you use LangChain, LlamaIndex, OpenAI, or similar frameworks and want drop-in instrumentation
- you need prompt management, guardrails, and production monitoring in one platform

## When to avoid
- you only need simple application metrics without LLM-specific tracing
- you need full user management features in a self-hosted deployment (limited there)
- your stack has no LLM components to observe or evaluate

## Facets
- artifact type: service
- maturity: active
- function: monitoring, tracing, llm-inference, rag, agent-framework, prompt-engineering, analytics, mcp, self-hosted, sdk
- domain: large-language-models, monitoring, developer-tools, machine-learning, chatbots
- platform: python, self-hosted, cross-platform
- tags: llm-observability, llm-evaluation, llmops, agent-tracing, prompt-management, guardrails, opentelemetry, langchain-integration, ai-agents, retrieval-augmented-generation, docker, kubernetes, web-server

## Member repositories
- comet-ml/opik (main) score 92

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:31.877446+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:57:51.371476+00:00, confidence not recorded.
  - readme: https://github.com/comet-ml/opik (fetched 2026-08-28T04:11:31.877446+00:00, sha 426b4a14ce16)
  - homepage: https://www.comet.com/docs/opik/ (fetched 2026-08-29T07:56:48.962010+00:00, sha b72977ac9bca)
  - site_page: https://www.comet.com/docs/opik/integrations/overview (fetched 2026-08-29T07:56:48.974205+00:00, sha a292ade434e4)
  - site_page: https://www.comet.com/docs/opik/cost-intelligence/overview (fetched 2026-08-29T07:56:48.976217+00:00, sha 2b9f0530dbb5)
  - site_page: https://www.comet.com/docs/opik/self-host/overview (fetched 2026-08-29T07:56:48.978081+00:00, sha 9a2c8455a3fe)
  - site_page: https://www.comet.com/docs/opik/reference/overview (fetched 2026-08-29T07:56:48.979828+00:00, sha eb1437a39a8a)
  - site_page: https://www.comet.com/docs/opik/quickstart (fetched 2026-08-29T07:56:48.981314+00:00, sha c3da8b07fcce)
  - site_page: https://www.comet.com/docs/opik/mcp-server (fetched 2026-08-29T07:56:48.982935+00:00, sha 863058c31d76)
  - site_page: https://www.comet.com/docs/opik/ollie (fetched 2026-08-29T07:56:48.985404+00:00, sha 1b074e170fad)
- Data as of 2026-08-30T08:39:29.467469+00:00.