offline-llm 开源项目推荐（78 个）

khoj-ai /khoj

你的 AI 第二大脑。可自托管。从网络或你的文档中获取答案。构建自定义智能体，安排自动化任务，进行深度研究。将任何在线或本地 LLM 变成你的个人自主 AI（gpt、claude、gemini、llama、qwen、mistral）。免费开始。

off-grid-ai /OGAM

The Swiss Army Knife of Offline AI. Chat, see, speak, and generate images on your phone or Mac — GGUF LLMs, vision, Whisper speech-to-text, Stable Diffusion, tool calling, and local-network servers. Runs on your CPU, GPU, or NPU. No account, no API key, zero data leaves your device.

webbrain-one /webbrain

面向 Chrome 和 Firefox 的开源 AI 浏览器代理（monorepo）

ggozad /haiku.rag

面向本地与自托管文档搜索的智能体 RAG：在嵌入式 LanceDB 上实现混合检索、重排序和多模态 RAG，并配备 Docling 解析与 MCP 服务器

Onion99 /KMP-MineStableDiffusion

多平台 AI 图像生成应用，由 Stable Diffusion 驱动 • 使用 Kotlin Multiplatform 与 Compose 构建 • 支持 SDXL、FLUX、SD3 等 • 通过 C++/JNI 实现原生性能 • 支持 Android/iOS 与桌面端

HiveForensics-AI /knolo-core

Knolo 将文档转化为可验证的 Knowledge Image（.knolo）：一个可挂载、可查询并可证明的可移植文件。确定性检索、密码学根、故障关闭式验证。本地优先。无需向量数据库。

ineelhere /shiny.ollama

Chat offline with open-source LLMs like deepseek-r1, nemotron, qwen, llama and more all through a simple R package powered by Shiny and Ollama. 🚀

rogers0602 /llamaindex_rag

🚀 企业级私有化 RAG 知识库系统 | 💯 纯离线部署、无需联网 | 🔐 支持 LDAP/AD 统一认证与 RBAC 部门级权限隔离 | ⚡️ 基于 LlamaIndex + Ollama + BGE-M3/Rerank | 📝 支持多格式文档解析、上下文对话记忆及精准的 PDF 原文溯源高亮 | 📊 内置数据可视化仪表盘（🚀 Enterprise RAG Knowledge Base. 💯 Fully offline/air-gapped deployment. 🔐 Features LDAP/AD integration, RBAC & Department Isolation. ⚡️ Powered by LlamaIndex, Ollama, and Local R

demiralpdev /Caphlon-Model

A 6.87 GiB GGUF build of Qwen 3.8 27B — full 27B quality on 8 GB RAM. 96.7% HumanEval, 92.9% MMLU retention, no distillation.

umutcamliyurt /TextCloak

A tool for concealing writing style using LLM

linyeping /GemMate

Your sovereign, zero-cost AI study companion—running Gemma 4 entirely on your own hardware.

TinToSer /GPT4Docs

An Offline Document Enquiry LLM for Everyone

kpcyrd /summarize-cli

Attempt to summarize text from `stdin`, using a large language model (locally and offline), to `stdout`

Abhinivesh2729 /theepori

Thee Pori (தீப்பொறி): open-source AI coding agent to build and run a software factory from your terminal. Claude, OpenAI, and offline models via Thinai.

rogers0602 /llamaindex_rag_front

🚀 企业级私有化 RAG 知识库系统 | 💯 纯离线部署、无需联网 | 🔐 支持 LDAP/AD 统一认证与 RBAC 部门级权限隔离 | ⚡️ 基于 LlamaIndex + Ollama + BGE-M3/Rerank | 📝 支持多格式文档解析、上下文对话记忆及精准的 PDF 原文溯源高亮 | 📊 内置数据可视化仪表盘🚀 Enterprise RAG Knowledge Base. 💯 Fully offline/air-gapped deployment. 🔐 Features LDAP/AD integration, RBAC & Department Isolation. ⚡️ Powered by LlamaIndex, Ollama, and Local Re

isaccanedo /khoj

🍳 Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM into your personal, autonomous AI (gpt, claude, gemini, llama, qwen, mistral). Get started - free

JKL404 /Offline-Chat-Application

A private, free, offline-first chat application powered by Open Source AI models like DeepSeek, Llama, Mistral, etc. through Ollama.

rover-001 /pern

Private, offline-first local AI agent & developer assistant. Runs embedded llama.cpp (GGUF) entirely on-device with WhatsApp, Discord, and terminal CLI tools.

contactvaibhavi /dotfiles

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.

Vichaya-Lab /g4speak

Voice-to-text for Windows — cloud transcription with on-device AI proofreading