local-rag 开源项目推荐（82 个）

shibing624 /ChatPDF

RAG for Local LLM, chat with PDF/doc/txt files, ChatPDF. 纯原生实现RAG功能，基于本地LLM、embedding模型、reranker模型实现，支持GraphRAG，无须安装任何第三方agent库。

shinpr /mcp-local-rag

Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP or CLI. Fully private, zero setup.

omar-haris /smart-coding-mcp

一个可扩展的模型上下文协议（MCP-Local-MRL-RAG-AST）服务器，为AI助手提供智能语义代码搜索。采用本地AI模型构建，灵感来自Cursor的语义搜索。

tobocop2 /lilbee

整个本地人工智能堆栈集中在一个可执行文件中：它在每个图形处理器上运行和管理本地人工智能模型，它是一个您可以对话的搜索引擎，并引用来自您的文件、代码和网络的答案。用于编码代理、网络爬虫、TUI、CLI、REST API、Python库的LCP服务器。不需要Ollama或LM Studio，可与两者配合使用。

AetherAI3 /Unlimited-Context-LLM

Give any local LLM a billion-token memory. Open-source, local-first context + memory engine for Ollama and AI agents — runs on your own machine, free. 🧠⚡

EllisMorrow /Caelune

Caelune (凯露恩) — Local-first retrieval for private Markdown, PDF, and Tika documents, with a Windows desktop app and read-only MCP server.｜本地优先的私人知识检索工具。

ragmate /ragmate-lagacy

Local RAG server for code editors. Scans your codebase, builds a local context index, and connects to any external LLM for context-aware completions and assistance.

nonatofabio /local_faiss_mcp

Local FAISS vector store as an MCP server – Agent Memory, drop-in local semantic search for Claude / Copilot / Agents.

vahidkowsari /pi-local-rag

local RAG extension for pi coding agent

HarinezumIgel /RAG-LCC

本地实验性 RAG 试验场，用于探索检索质量、语料构建、置信度与过滤链设计。可配置的检索编排、排序、过滤流水线、可视化文档依据、网络搜索、Open WebUI 集成，以及丰富的调试洞察。支持 Ollama 和 vLLM，可通过 Dev Containers 或直接在 Win 和 Linux 上原生运行。

aifabrice /jev-rag

Jev RAG (Jev-RAG / JevRAG): open-source local knowledge search with BM25 + Jev reranking, agentic and hybrid retrieval, cited answers, and reproducible benchmarks.

akashicode /kash

Kash is a Go CLI that turns your raw documents (PDFs, Markdown, text files) into a self-contained AI agent packaged in a lightweight Docker container.

Gayatri-Education /Gayatri-Demo

Institutional-grade offline adaptive learning platform featuring course-independent Socratic tutoring and strictly scoped air-gapped RAG.

stefanbinder /myindependent-ai

A fully local, privacy-first personal AI assistant. Ask questions about your own data — emails, documents, chats — without anything leaving your machine.

pooyaphoenix /RA3G-Agent

Local RAG system with a built-in governance agent that filters sensitive or restricted information with separated agent logging systems to keep privacy and security

lorenzo-cambiaghi /LynxMCP

LynxMCP: local MCP server for the code questions grep can't answer. Call graph and blast radius, hybrid semantic + lexical code search on ONNX Runtime, library docs and PDFs as sources. No cloud, no PyTorch.

ramchaik /nous

Nous: A privacy-focused personal knowledge assistant using local LLMs to securely interact with your documents and enhance information retrieval.

ptai-eng /GoldPan

Privacy-first Multimodal Data Refinery, Repo Context Firewall (Prompt Injection & Trojan Source Defense), Offline Vietnamese OCR, Multilingual E5 ONNX + SQLite FTS5 RAG & 9-Tool MCP Server.

sachink1729 /Financial-RAG-GPU-less-Mistral-Langchain

All CPU efficient GPU-less Financial Analysis RAG Model with Qdrant, Langchain and GPT4All x Mistral-7B, run RAG without any GPU support!

plantacerium /Metamorphic-Resonance-Human-Language-Gamers

⊛ Consciousness Architecture. Change the word. Change the world. ⊛