# Evaluation repositories

Source: https://www.gstars.dev/c/evaluation
Tracked repositories: 13
Ranking: Total stars

1. [langfuse/langfuse](https://www.gstars.dev/repo/langfuse/langfuse) — 37267 stars
2. [Tencent/WeKnora](https://www.gstars.dev/repo/Tencent/WeKnora) — 37106 stars
3. [mlflow/mlflow](https://www.gstars.dev/repo/mlflow/mlflow) — 28707 stars
4. [promptfoo/promptfoo](https://www.gstars.dev/repo/promptfoo/promptfoo) — 26842 stars
5. [comet-ml/opik](https://www.gstars.dev/repo/comet-ml/opik) — 23101 stars
6. [vibrantlabsai/ragas](https://www.gstars.dev/repo/vibrantlabsai/ragas) — 16225 stars
7. [Helicone/helicone](https://www.gstars.dev/repo/Helicone/helicone) — 6277 stars
8. [coze-dev/coze-loop](https://www.gstars.dev/repo/coze-dev/coze-loop) — 5803 stars
9. [langwatch/langwatch](https://www.gstars.dev/repo/langwatch/langwatch) — 5004 stars
10. [open-compass/VLMEvalKit](https://www.gstars.dev/repo/open-compass/VLMEvalKit) — 4472 stars

Category/topic matches include curated categories and collected GitHub topics. Coverage is limited to tracked active, non-archived, non-fork repositories. See https://www.gstars.dev/methodology for measurement limits.