RAG hub
A practical hub for embedding models, retrieval systems, vector search, reranking, document agents, and grounded answer evaluation.
Built for: Knowledge product teams, search teams, support automation teams
5
Ranked entries
7
Verified repos
6
Decision pages
92
Top score
Does retrieval find the right passage before the answer model writes?
Can the system preserve permissions, freshness, and citation quality?
How expensive is reindexing if the embedding model changes later?
Ranking
These entries come from the current SkillRank dataset. Scores help discovery; final decisions should use your own workflow tests.
Embedding / RAG
OpenAI
92
Score
OpenAI’s latest large embedding model tuned for retrieval, deduping, and RAG backends.
Embedding / RAG
90
Score
Shipping Gemini-class embedding endpoint for Vertex AI and Gemini API retrieval stacks.
Embedding / RAG
Cohere
88
Score
Latest multilingual Cohere embed family for retrieval, rerank, and search stacks.
Embedding / RAG
BAAI
84
Score
Flagship multilingual BGE checkpoints for dense, sparse, and hybrid retrieval setups.
Embedding / RAG
Jina AI
82
Score
Late-interaction friendly embeddings and small specialized models.
Daily signals
Signals are generated from recorded snapshots and verified source metadata. They keep the hub connected to the daily crawler.
text-embedding-4-large remained stable across recorded snapshots this week.
Gemini embedding 004 remained stable across recorded snapshots this week.
Cohere Embed v4 remained stable across recorded snapshots this week.
BGE M3 remained stable across recorded snapshots this week.
Jina Embeddings remained stable across recorded snapshots this week.
Shubhamsaboo/awesome-llm-apps is verified on GitHub with 114,017 stars, 16,918 forks, and last push date 2026-06-03.
Verified repositories
GitHub metadata is useful for discovery, but production fit still depends on license, docs, security posture, and local maintainability.
🌊 The leading agent meta-harness for Claude. Deploy intelligent multi-agent swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning swarm intelligence, RAG integration, and native Claude Code / Codex Integration
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.
AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of code, SQL schemas, R scripts, shell scripts, docs, papers, images, or videos into a queryable knowledge graph. App code + database schema + infrastructure in one graph.
Open-source super AI assistant & Agent Harness. Plans tasks, runs tools and skills, self-evolves with memory and knowledge. Multi-model, multi-channel. Lightweight, extensible, one-line install. (formerly chatgpt-on-wechat)
Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
Pre-indexed code knowledge graph for Claude Code, Codex, Gemini, Cursor, OpenCode, AntiGravity, Kiro, and Hermes Agent — fewer tokens, fewer tool calls, 100% local
Guides
A practical framework for choosing chat, reasoning, multimodal, coding, and retrieval models without relying on launch hype.
A grounded checklist for choosing embedding models, retrieval pipelines, rerankers, and document-agent workflows.
A practical guide to routing prompts across fast, cheap, specialist, and frontier models without creating brittle AI infrastructure.
How to protect retrieval systems from malicious documents, stale knowledge, permission leaks, and unsupported answers.
Compare
A practical comparison of embedding model choices for RAG systems, semantic search, hybrid retrieval, and enterprise knowledge bases.
Compare n8n, AutoGen, CrewAI, Flowise, LlamaIndex, and other open-source agent frameworks by workflow fit and operational risk.
Source boundaries
