The database of free AI tools on GitHub

Desktop app for recording meetings from locally running apps and transcribing and summarizing them with a local LLM

VT.ai - multimodal AI chat app with dynamic conversation routing

A 100% local all-in-one dashboard for any screen, tablet or phone. Windows, with macOS and Linux in beta. System monitor, media and mic, a voice AI that can build dashboard pages for you, a Stream Dec

Modern desktop application (Rust + Tauri v2 + Svelte 5 + Candle (HF)) for communicating with AI models that runs completely locally on your computer. No subscriptions, no data sent to the internet — j

A complete private computer on a USB stick. PAI is a bootable Debian 12 Linux distro that runs Ollama locally on any x86_64 or ARM64 machine — full desktop, local AI, hardened networking, all in RAM.

本地运行的 DOCX/TXT 长文档改写与审阅工具，支持段内分块、多轮流式处理、Diff 审阅与 DOCX 原位回填。

Autonomous, agentic, creative story writing system that incorporates stored embeddings and Knowledge Graphs.

German-OCR is specifically trained to extract text from German documents including invoices, receipts, forms, and other business documents.

Benchmark local LLM serving by replaying real agent trajectories

InferrLM - On-device AI for iOS & Android

Integrate ChatGPT-style LLMs into Neovim: ask questions, keep multi-file context, pull diagnostics / command output, and chat without leaving your editor. Highly configurable, async, lua-only plugin.

An I/O benchmark for deep Learning applications

Self-hosted mem0 MCP server for Claude Code. Run a complete memory server against self-hosted Qdrant + Neo4j + Ollama while using Claude as the main LLM.

Full-featured IMAP & SMTP email for AI assistants: search, read, send, organize and clean up multiple mailboxes, with AES-256-encrypted credentials. Works with Claude, Cursor and any MCP client.

AI-powered character generator built with React. Create detailed TRPG/Novel characters, NPC system prompts, and visual tags using Gemini, OpenAI, or Local LLMs.支持完整角色定义的人设生成器

Free macOS-native Cluely alternative. AI chat invisible to screen sharing. Ollama, OpenAI, Claude. Swift. No Electron. No subscription.

Convert PowerPoint files into semantically rich text using vision language models

记得她说过的每一句话，也记得你答应过的每一件事。A self-hosted AI chief of staff for your chats — remembers what they said and what you promised.

Open source, local first AI medical agent for desktop and web.

Comprehensive tutorials for LangChain, LangGraph, and LangSmith using Groq LLM. Learn to build advanced AI systems, from basics to production-ready applications. Covers key concepts, real-world exampl

Go web crawler to scrape documentation sites and convert content to clean Markdown for LLM ingestion (RAG, training data)

A private Claude-Code-style coding agent for Apple Silicon — run chat, code, and local model workflows on-device. MLX-native, Ollama/OpenAI API compatible, zero API keys.

An offline coding agent for local models. One command sets up the best model your GPU can run, and on 24 GB+ RTX 30/40/50-series cards Qwen3.8-27B runs up to 1.9x faster than llama.cpp.

Python package wrapping llama.cpp for on-device LLM inference

Local Apple Notes + LLM Chat

Run your AI models at home in one binary: chat, persistent memory, web access, browser control, MCP tools, encryption at rest and end-to-end encrypted remote access. Linux, macOS, Windows. FR/EN docs.

Reproduction Package for the paper "Type-Constrained Code Generation with Language Models" [PLDI 2025]

Private recommendation rows for every Plex user: Picked for You, Because you watched, seasonal picks and more, built from each person's own watch history and hidden from everyone else. Self-hosted, on

tAI is an AI terminal assistant CLI that helps you with Linux and macOS commands.

OpenClaw Companion / OpenClaw 中文助手：中英双语、安全编排官方 OpenClaw 安装、配置、检查、升级、备份与诊断。社区项目，非官方。