Ross ROSS = Recommend OSS · open-source software intelligence for agents

comet-ml/opik

Debug, evaluate, and monitor your LLM applications, RAG systems, and agentic workflows with comprehensive tracing, automated evaluations, and production-ready dashboards. observed · 2026-08-28

github.com/comet-ml/opik · homepage · Python · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

92/100

  • Activity 99
  • Release rhythm 87
  • Longevity 86
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 0.0
  • age_days: 1211
  • days_rel: 7
  • days_push: 7
  • n_releases_24m: 527

Full methodology

Adoption not part of the score

21624 stars · 1732 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

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

service · maturity active

monitoring tracing llm-inference rag agent-framework prompt-engineering analytics mcp self-hosted sdk large-language-models monitoring developer-tools machine-learning chatbots python self-hosted cross-platform llm-observability llm-evaluation llmops agent-tracing prompt-management guardrails opentelemetry langchain-integration ai-agents retrieval-augmented-generation docker kubernetes web-server

9 sources

Member repositories

RepositoryRoleHealth v2
comet-ml/opikmain92

For agents

markdown · JSON · MCP: product_card(name="comet-ml/opik")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem