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。

An extensible Model Context Protocol (MCP-Local-MRL-RAG-AST) server that provides intelligent semantic code search for AI assistants. Built with local AI models, inspired by Cursor's semantic search.

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

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.

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

Local-first RAG desktop app & official MCP Server. Let any AI instantly search your private Markdown, PDF, and 1290+ document formats. (本地优先的 RAG 桌面端与官方 MCP 服务器。让任意 AI 瞬间检索你的私有 Markdown、PDF 及 1290+ 种文档格式。)

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

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

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

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

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

A RAG-based question-answering system that processes user queries using local documents. It extracts relevant information to answer questions, falling back to a large language model when local sources are insufficient, ensuring accurate and contextual responses.

Self-contained RAG for consumer laptops (16 GB RAM): local ingestion, hybrid retrieval (FAISS + BM25), streaming processing, GDPR-aligned privacy. Runs 10 GB corpora offline with Llama 3.2.

Local-first RAG framework for maximizing the value of private and on-device LLM systems.

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.

A completely local RAG.

Automates hermetic environments (macOS/HPC) to eliminate drift. Provisions offline RAG (Gemma 2), compiles LaTeX manuscripts, and indexes local knowledge. Unifies infrastructure, writing, and inference into a single, audit-ready artifact.

RAG your Language Model convos in local. OpenAI ChatGPT support

Chat to your documents on your local device using SentenceTransformers and Ollama for Privacy or configure the way you want using cloud LLMs for faster response. 100% private or 100% faster response time, choice is yours.

LocalRAG: Evaluating local RAG pipeline [University of St. Gallen Bachelor Thesis]

Locally run RAG tool

🤖 Build your own local Retrieval-Augmented Generation system for private, offline AI memory without ongoing costs or data privacy concerns.

A fully local RAG application using Azure Local Foundry, LangChain, and ChromaDB. It runs optimized LLMs offline, enabling private semantic search and RetrievalQA workflows on your device. Designed to be simple, fast, and entirely cloud-independent.

Ask plain-English questions about your projects — source code, infrastructure configs, runbooks, documentation, anything. glean indexes your files locally using Ollama embeddings and ChromaDB, then answers with cited file and line references. No data leaves your machine.

A demonstration of Retrieval-Augmented Generation (RAG) applied to protein analysis