Skip to content

Ragas

Python library of LLM-judged metrics and experiment tooling for evaluating RAG and agent applications.

By Vibrant Labs · www.ragas.io

Package download activity

Each package is shown on its own; packages that can be installed together are never added up. Week 2026-W40 (2026-09-28 to 2026-10-04).

PyPIragas · headline (ranked)

279,757 downloads in the week, +9.5% vs prior week · rank 13 on PyPI

2026-W29: 377,5112026-W30: 382,2002026-W31: 361,1682026-W32: 361,3342026-W33: 361,6162026-W34: 430,1392026-W35: 251,9832026-W36: 229,4152026-W37: 218,8432026-W38: 237,8362026-W39: 255,6022026-W40: 279,757
2026-W29 to 2026-W40, 12 weeks; min 218,843, max 430,139

Reproduce this number (ClickHouse SQL) · registry metadata (mapping checked 2026-10-07)

GitHub stars

vibrantlabsai/ragas: 15,952 stars (rank 8). Stars are a point-in-time count of a repository's bookmarks, not people using the tool.

Series starts 2026-W40 (15,952).

Reproduce (GitHub API) · repository link source

Facts

Facts for Ragas
CategoriesEvaluation
StatusGenerally available
LicenceApache-2.0source, checked 2026-10-07
Self-hostYessource, checked 2026-10-07
OpenTelemetryUnknownsource, checked 2026-10-07
Pricing modelfree
Entry priceFree; Open-source library; no paid plan or pricing page found (docs offer office-hours sign-up only)source, checked 2026-10-07
Free tierYes
MeasurabilityMeasured (mapped SDK packages)

Facts last verified 2026-10-07 on first-party pages. Prices as published, taxes excluded; non-USD prices are not converted.

Compare

Spotted an outdated fact? The methodology page explains how facts are checked; corrections are applied at the next weekly build.