Opik

Opik is an open source AI observability and evaluation platform from Comet. It logs each step an agent takes, from user interactions to context retrieval and tool calls, and adds evaluation workflows to find and fix errors across development, testing and production. Tracing covers execution graphs, multi turn sessions, token and cost tracking, and user feedback, with integrations for more than 40 frameworks and model providers and native OpenTelemetry support. Evaluation uses LLM as a judge scoring with more than 30 metrics, including answer relevance, context precision, task completion and hallucination, and supports test suites and an agent playground. In production, it can evaluate live traces, alert on failures, and apply guardrails against policy violations and PII exposure. A debugging assistant helps root cause problems in traces. A Cost Intelligence feature tracks Claude Code and Codex usage and spend across engineering teams. It is aimed at developers and organizations building agentic systems who need to understand where an agent fails and measure whether changes improve it. The open source version is free to download and run, with the same codebase as the hosted versions. Free Cloud is $0 for up to 10 team members, 25,000 spans per month and 60 day data retention. Pro Cloud is $19 per month for up to 50 team members and 100,000 spans per month, with customizable limits and retention, and additional spans at $5 per 100,000. Enterprise is custom priced and adds single sign on, flexible deployment, dedicated support and compliance certifications.