Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Retrieval-augmented generation, document Q&A, knowledge graphs and memory systems.
Signals: rag, retrieval-augmented-generation, llamaindex, knowledge-graph, question-answering, chat-with-documents, graphrag, memory
501 results
AI 应用开发、AI 编程实战与面试指南，涵盖 LLM、Agent、RAG、MCP、Claude Code、Codex 等核心技术与工程实践。
WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.
Buddhist Digital Text Platform — 10,500+ texts, 613 sources, trilingual cross-canon, AI Q&A (RAG), knowledge graph, full-text search
Ingest files for retrieval augmented generation (RAG) with open-source Large Language Models (LLMs), all without 3rd parties or sensitive data leaving your network.
Excel-to-Neo4j knowledge graph examples: legacy py2neo v3 plus modern Neo4j GraphRAG/vector search.
自然语言处理、知识图谱、对话系统，大模型等技术研究与应用。
SimpleMem: Efficient Lifelong Memory for LLM Agents — Text & Multimodal
Private, local RAGs. Supercharge LLMs with your own knowledge base.
Fast, streaming indexing, query, and agentic LLM applications in Rust
Repository for "MultiHop-RAG: A Dataset for Evaluating Retrieval-Augmented Generation Across Documents" (COLM 2024)
基于 Karpathy llm-wiki 方法论的个人知识库构建 Skill，支持多平台！
Ask questions across your Markdown notes using a fully local Graph RAG engine. Built for Obsidian vaults, works with any folder of Markdown files. Extracts entity-relation triples from wikilinks & YAML frontmatter, retrieves answers via hybrid search (vector + BM25 + temporal). Multilingual. No cloud. Runs on Ollama.
医学中文RAG项目，使用langchain+milvus，支持快速一键式部署，支持无缝领域迁移
Karpathy-style LLM knowledge base for Obsidian. Clone, run Claude Code, start building your second brain.
qKnow is an open-source agent platform for enterprise knowledge intelligence and industry AI. It provides knowledge graphs, RAG, and bot building, encapsulating industry AI into standardized modules for rapid deployment. Supporting unified integration of documents and data, it helps enterprises quickly build knowledge hubs and AI solutions.
VeritasGraph — open-source Knowledge Graph & GraphRAG framework on GitHub. Build multi-hop reasoning, ontology-aware retrieval, and verifiable attribution over your own data. Nodes, edges, RDF, linked-data — runs locally or in the cloud.
Minimalist web-searching platform with an AI assistant that runs directly from your browser. Demo: https://felladrin-minisearch.hf.space
MimiClaw: Harness on a $5 chip. No OS(Linux). No Node.js. No Mac mini. No Raspberry Pi. No VPS. Hardware agents OS.
ApeRAG: Production-ready GraphRAG with multi-modal indexing, AI agents, MCP support, and scalable K8s deployment
CookHero是一个基于 LLM + RAG + Agent + 多模态的智能饮食与烹饪管理平台，支持智能菜谱查询、个性化饮食计划、AI 饮食记录、营养分析、Web 搜索增强，以及可扩展的 ReAct Agent / Subagent 工具体系，帮助厨房新手轻松成为“烹饪英雄”。
Logic Language for World Models 🌱🐋🌍
Vision infrastructure to turn complex documents into RAG/LLM-ready data
The local-first LLM Wiki: open-source knowledge graph builder, RAG knowledge base, and agent memory store. Built on Andrej Karpathy's pattern. An Obsidian alternative for personal knowledge management, AI second brain, and durable Claude Code / Codex / OpenClaw memory.
Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.
24,538 repositories in the index in total.
