Run Open Source/Open Weight LLMs locally with OpenAI compatible APIs

The backend of the Atypica App, an AI educational tool for acessibility for the neurodivergent community.

The all-in-one Desktop & Docker AI application with built-in RAG, AI agents, No-code agent builder, MCP compatibility, and more.

🔍 Establish unique identities for AI agents using Solana blockchain and NFTs, enhancing security and accountability in the digital landscape.

✈️ Build an airline chatbot with Gradio and Ollama for quick ticket price answers and seamless user interaction.

🤖 Bootstrap a self-hosted AI and low code environment with Ollama, Open WebUI, and Supabase for seamless local LLM development and integration.

🚀 Extract and vectorize your Cursor chat history, enabling efficient search through a Dockerized FastAPI API with LanceDB integration.

QuietPrompt is a local-first AI tool for coding. Capture screen text, voice, or typed prompts and run them offline with your LLM; no cloud 🐙

AetherShell is an AI-driven Linux assistant that executes natural language commands offline using a local LLM. Ideal for seamless shell interaction. 🐙💻

Python application that uses local Ollama LLM models to give advice on results found from HIBP (Have I Been Pwned) API

a magical LLM desktop client that makes it easy for *anyone* to use LLMs and MCP

Edit text anywhere with AI! ✨

A Python project that deploys a Local RAG chatbot using Ollama API and vLLM API. Refines answers with internal RAG knowledge base, using both Embedding and Rerank models to improve accuracy of context provided to LLM models.

💻🔒 A local-first full-stack app to analyze medical PDFs with an AI model (Apollo2-2B), ensuring privacy & patient-friendly insights — no external APIs or cloud involved.

A fully offline NLP pipeline for extracting, chunking, embedding, querying, summarizing, and translating research documents using local LLMs. Inspired by the fictional mystery of Dr. X, the system supports multi-format files, local RAG-based Q&A, Arabic translation, and ROUGE-based summarization — all without cloud dependencies.

Python agent connecting local LLM and local SearxNG for web search

Local Deep Research achieves ~95% on SimpleQA benchmark (tested with GPT-4.1-mini). Supports local and cloud LLMs (Ollama, Google, Anthropic, ...). Searches 10+ sources - arXiv, PubMed, web, and your private documents. Everything Local.

A curated list of awesome platforms, tools, practices and resources that helps run LLMs locally

'afm' command cli: macOS server and single prompt mode that exposes Apple's Foundation Models through OpenAI-compatible API endpoints. Supports Apple Vision and single command (non-server) inference with piping as well

💻一款简洁实用轻量级的本地AI对话客户端，采用Tauri2.0和Next.js编写 A simple, practical, and lightweight local AI chat client, written in Tauri 2.0 & Next.js.