awesome-llm-rag
github.com/jxzhangjhu/awesome-llm-rag ↗Awesome-LLM-RAG: a curated list of advanced retrieval augmented generation (RAG) in Large Language Models
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me rag long-text and memory resources from awesome-llm-rag"
Installation instructions →What's inside
RAG Long-text and Memory
- Agent Brain
7-layer cognitive memory system for AI agents with perception gate, dream cycle, and predictive capabilities. Built with FastAPI, PostgreSQL/pgvector. Self-hostable.
- Cortex
Persistent AI memory for coding assistants. Auto-captures decisions, patterns, and context. VSCode extension + CLI + MCP server. Free.
- Statewave
Open-source memory runtime for AI agents. Compiles events into deterministic, provenance-tagged context bundles instead of query-time retrieval. Apache-2.0, self-hostable on Postgres + pgvector.
Workshops and Tutorials
- Agent Shadow Brain
Self-evolving AI coding intelligence with infinite memory (TurboQuant), genetic algorithm self-evolution, predictive bug detection, PageRank knowledge graphs, swarm intelligence, and adversarial defense.
- Omni Skills Forge
50,000+ curated AI agent skills for Claude Code, Cursor, Copilot, Windsurf, Cline. Visual dashboard, one-click install, skill doctor, auto-update.
- RAG Techniques
35+ runnable Jupyter-notebook tutorials covering advanced RAG techniques: chunking, query transformation/HyDE, reranking, self-RAG, graph RAG, and evaluation.
Resources
- Bernstein
Multi-agent orchestrator with RAG-enhanced task planning. Decomposes goals using context from codebase analysis.
- CCHub
A desktop control panel for the Claude Code / Codex / Gemini CLI ecosystem. Manage MCP servers, config profiles, agent skills, CLAUDE.md, hooks, and workflow templates from a single Tauri app (Windows / macOS / Linux).
- ChunkTuner
Open-source Python/CLI/MCP tooling to benchmark chunking strategies for RAG and recommend configurations using retrieval metrics (optional RAGAS).
- CocoIndex
Open-source ETL framework to build and continuously update RAG indexes (embeddings and knowledge graphs) from your data sources, with incremental processing that recomputes only what changed. Apache-2.0.
- guardian-agent-prompts
49 production-tested AI agent system prompts for Claude Code multi-agent orchestration with retrieval-augmented generation patterns. MIT licensed.
- LLMSlim
Open-source Python library that compresses retrieved documents to a token budget before generation, keeping the passages that answer the query; the default mode runs no model, and it ships compressors for LangChain, LlamaIndex and Haystack. MIT licensed.
RAG Search
- Not Human Search
Search engine and MCP server for discovering AI-native tools. 8,600+ sites indexed with agentic capability scoring. Useful for RAG pipelines that need to discover and integrate AI tools.
- RAG World
Open registry of 69 named RAG technologies, each mapped onto a 28-dimension configuration schema with compatibility constraints, and each carrying a maturity level derived from collected evidence by a deterministic rule. Published as JSON under CC BY 4.0, updated weekly, DOI 10.5281/zenodo.21943978.
- Stipple
Hosted MCP document-trust gate for RAG pipelines: forensic authenticity signals on ingested documents (risk bands + per-signal tamper evidence), grounded field extraction (missing values abstain as
- Superhighway
Web search API for RAG pipelines and AI agents — live web search, news, images, scrape, and one-call deep research (search + read top pages). Pay per call via x402/USDC (no signup) or free API key. MCP-compatible:
- Zoom Search
Open-source MCP search and evidence toolkit for RAG pipelines and AI agents, with query rewriting, multi-provider retrieval, cited answers, and quality, latency, and cost evaluation.
Showing a sample of 17 resources. View the full list on GitHub →