Product / UX / Telemetry & observability

Opik

Open-source platform for debugging, evaluating, and monitoring LLM applications, RAG systems, and agentic workflows. Provides comprehensive tracing, automated evaluations, and production-ready dashboards. Built by Comet ML (established ML experiment tracking company). Fast-growing at 19.4K GitHub stars, the second most-starred open source LLM observability tool after Langfuse.

opik v2.0.57 (released 4 Jun 2026, PyPI/GitHub); confirmed live June 2026. Self-hostable OSS platform; Comet.com cloud is optional hosting.

Openness

5 high confidence

5.0

license: Apache-2.0(OSI)
source: public
commercial: Comet-cloud-hosting(not a gated core)
core-gated: ungated

Apache-2.0, full platform self-hostable; cloud is managed hosting rather than a feature-gated proprietary core.

https://pypi.org/project/opik/ recorded 2026-06-04
License: Apache 2.0; v2.0.57 (4 Jun 2026)
https://github.com/comet-ml/opik recorded 2026-06-04
Apache-2.0; self-hosted + cloud deployment

Adoption

4 high confidence

4.0

opik ~6.19M PyPI downloads/month (highest in this batch); 60-70+ framework integrations; platform reports 40M+ traces/day; ~19.4k stars corroborates only.

https://pypistats.org/packages/opik recorded 2026-06-04
~6,192,885 downloads last month
https://github.com/comet-ml/opik recorded 2026-06-04
~19.4k stars; 70+ integrations; 40M+ traces/day

Capability

4 high confidence

4.0

Covers all six feature-matrix dimensions; on par with MLflow/Langfuse anchors (C4). Not scored 5; closed Arize AX leads category capability.

https://github.com/comet-ml/opik recorded 2026-06-04
tracing, evals, LLM-as-judge, prompt management, datasets, OTel

Unchanged since 2026-07-30 (last edited, not re-checked)