#
ENJA

RAGHub

Andrew-Jang/RAGHub

RAGHub is a curated community directory of frameworks, engines, tools, and resources for Retrieval-Augmented Generation (RAG). It provides developers with an organized overview of options ranging from vector databases and evaluation tools to end-to-end RAG platforms.

2k 182MITUpdated 2026-07-28

Overview

This repository functions as a comprehensive resource hub for engineers and researchers building RAG systems. It categorizes contemporary frameworks, libraries, and managed services, helping developers navigate the rapidly evolving ecosystem of context enhancement, embedding management, and vector storage solutions.

Capabilities

  • Categorized listing of RAG frameworks and engines
  • Overview of evaluation and optimization toolsets
  • Guidance on selecting appropriate vector databases and local inference methods

Best for

Discovering new frameworks and engines for building RAG applications, Comparing evaluation and optimization tools for LLM retrieval pipelines, Identifying suitable vector databases and local model deployment options

Evoa Score breakdown= Σ (score × weight)
66
Task usefulness20%65 → +13.0

実タスクにどれだけ役立つか(機能の豊富さ・用途の明確さ)。 AIによるcapabilities/use-cases解析

Code quality15%50 → +7.5

実装・指示の品質。 AIによるSKILL.md/README解析

Maintenance15%100 → +15.0

リポジトリがどれだけ活発に保守されているか。 GitHub 最終push日時の新しさ

Documentation12%43 → +5.2

ドキュメントの充実度・分かりやすさ。 README/独自要約の情報量

Security15%100 → +15.0

危険・不審な挙動が無いか。 AIによるセキュリティレビュー

Originality10%35 → +3.5

ありふれたラッパーではない独自性。 AIによる独自性判定

Popularity8%84 → +6.7

コミュニティの採用度。 GitHub Stars/Forks(対数スケール)

Compatibility5%0 → +0.0

対応AIエージェントの広さ。 AIによる対応エージェント判定

Weighted total65.9 / 100

ライセンス不明/制限あり(Red)のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →

Security considerations

This skill acts purely as an information directory and contains no executable scripts or system control mechanisms.

Categories

Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.