Opik

Open-source LLM tracing, evaluation and prompt optimization platform from Comet, self-hosted with Docker or Kubernetes, or on Comet's cloud.

Visit comet.com ↗Pricing & calculator Alternatives

Works with AI agents:llms.txt MCP

Ask your AI about this, with this page as the source:ChatGPT ↗Claude ↗Perplexity ↗

Where it fits

LLM Observability & Evals · Open-source platformTracing, evaluations and prompt optimization in an Apache-licensed platform you self-host with Docker or Kubernetes, or use on Comet's cloud.Trade-off: Self-hosting means running several services; smaller community than Langfuse.

How Opik itself is built

1 tools, from its own code, website and Product Hunt page.

SendGrid

Who uses it

No maker's live product on record yet, and 6 open-source projects that declare it in their code.

Declared in code 6How evidence is collected →

We haven't found a maker's live product that uses Opik yet — only the open-source projects below, which declare it in their code.

Sort

pipeshub-ai PipesHub is an open-source platform for securely connecting enterprise knowledge to AI.…LLM Observability & EvalsIn its code · source ↗

ApeRAG ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and…LLM Observability & EvalsIn its code · source ↗

AI-Bank-Statement-Document-Automation-By-LLM-And-Personal-Finanical-Analysis-Prediction AI Bank Statement Document Automation By LLM model and Personal Finanical AnalysisLLM Observability & EvalsIn its code · source ↗

homelab LLM Observability & EvalsIn its code · source ↗

chat-gun 🤖 A full-stack Agent Chat Runtime for pre-production validation, built with act, TypeSc…LLM Observability & EvalsIn its code · source ↗

philoagents-course When Philosophy meets AILLM Observability & EvalsIn its code · source ↗

Open source: a project that declares Opik as a dependency in its public code — verifiable, but not necessarily a live product.

Reliability and open issues

Incidents on its status page0 in the last 90 days · 0 in the last yearFrom its own status page, 2026-10-02. Vendors decide what they post; one page can cover several products.

Alternatives to Opik

All alternatives by situation →

LangfuseTracing, prompt management and evals in one tool you can run on your own server for free.Open sourceFree tier33 makers · LLM observability & evals

Arize PhoenixOpenTelemetry-based tracing and evals you can start locally in a notebook, then self-host or move to its cloud.Self-hostableFree tier

HeliconeGetting request logs, costs and latency by changing one base URL, with no SDK instrumentation.Open sourceFree tier13 makers · LLM observability & evals

LangSmithApps built on LangChain or LangGraph, where tracing works with almost no setup.Free tier11 makers · LLM observability & evals

BraintrustEval-driven work — scoring outputs and comparing prompts and models side by side in experiments.Free tier5 makers · LLM observability & evals

PromptfooRunning prompts and models against test cases from the command line or CI, including red-team tests for prompt injection and data leaks.Open sourceFree tier

DeepEvalWriting LLM evals as pytest-style tests in Python, with ready-made metrics for hallucination, faithfulness and answer relevancy.Open sourceFree tier

RagasScoring RAG pipelines — how faithful answers are to the retrieved context and how relevant that context is — and generating test questions from your documents.Open sourceFree tier

Questions makers ask about Opik

Is Opik free?

Yes — there is a free tier a small product can run on; paid use starts at $19/mo. source ↗

Is Opik open source or self-hostable?

Open source, and you can self-host it. source ↗

Can AI coding agents work with Opik?

It serves an llms.txt docs index; it has an official MCP server (io.github.comet-ml/opik-mcp).

Who uses Opik?

No maker's live product we track yet; 6 open-source projects declare it in their code. source ↗