agentskillexchange Trace, evaluate, and monitor agentic workflows with Opik
Capture LLM and agent traces, run evaluations, inspect failures, and monitor RAG or multi-step agent behavior from prototype to production.
Prerequisites
Opik service or SDK, LLM application or agent workflow, evaluation datasets or production traces
Installation
Use the upstream install or setup path that matches your environment:
- git clone https://github.com/comet-ml/opik.git
- pip install opik
or install with uv
- uv pip install opik
Requirements and caveats from upstream:
- Annotate traces and spans with feedback scores via the [Python SDK](https://www.comet.com/docs/opik/v1/tracing/annotate_traces/#annotating-traces-and-spans-using-the-sdk?from=llm&utm_source=opik&utm_medium=github&utm_...
- Deploy Opik in your own environment. Choose between Docker for local setups or Kubernetes for scalability.
Basic usage or getting-started notes:
Opik helps you build, test, and optimize generative AI applications that run better, from prototype to production. From RAG chatbots to code assistants to complex agentic systems, Opik provides comprehensive tracing,...
Monitor feedback scores, trace counts, and token usage over time in the [Opik Dashboard](https://www.comet.com/docs/opik/v1/production/production_monitoring/?from=llm&utm_source=opik&utm_medium=github&utm_content=dash...
Source: https://github.com/comet-ml/opik
Extracted from upstream docs: https://raw.githubusercontent.com/comet-ml/opik/HEAD/README.md