The database of free AI tools on GitHub

Local-first AI character chat & roleplay for Windows/macOS/Linux — a living Realism Engine, built-in TTS & image generation, and The Stoop community character hub. Fully offline by default, open-sourc

一条命令，把微信变成任何 AI Agent 的入口 | Connect WeChat to any AI Agent with one command

Loom is an AI harness, that can be used with local or cloud LLMs, for complex tasks. It decomposes work, drives execution through a verification harness, and keeps models on track with structured stat

WPS Office 全家桶（文字/表格/演示/PDF）AI 助手：挂 OpenAI 兼容 / Anthropic / Codex 多家模型，AI 通过工具调用直接读写文档；支持生图、MCP、中英双语，覆盖 Windows / macOS / Linux（含国产系统）。

Shadow AI: stealth AI assistant for restricted/locked-down environments, enabling cross-device interaction over LAN, screen & audio capture, real-time AI inference, and low-friction automation. Suppor

🌿 StoryMoss (草苔) — AI导演式小说创作系统。Tauri+Rust驱动的桌面写作软件，集成知识图谱、伏笔追踪、StyleDNA风格引擎、协同编辑、7阶段全自动创作工作流。让AI成为你的创作搭档，越写越懂你。

Local-first media asset manager with AI semantic search — reads pro-camera metadata (Sony XAVC sidecar, FX-series) and 360 footage (Insta360/GoPro Max) that consumer DAMs drop. FFmpeg + ChromaDB + loc

绿群日报——绿群保研信息提炼：帮你每日快速跟进

LLMDog is a command-line tool that helps developers share code with Large Language Models like Claude and ChatGPT.

A decision cache for TypeSafe Jev-class models — memoize decisions so repeats are free, deterministic, and shareable. One 2 MB binary.

MCP to explore websites with llms.txt files

Structured output generation in Swift

KiraAI, a modular, multi-platform AI digital lifeform that connects Large Language Models (LLMs) and various chat adapters (QQ, Telegram...)

Train your own ChatGPT on Apple Silicon — MLX port of nanochat

AI-powered tool to organize photos into Instagram-ready posts with smart captions and hashtags. Supports both Ollama (local) and Gemini (cloud) AI providers.

Open-source AI desktop assistant — run local or remote LLMs with privacy-first design and zero setup required.

Jev-style parallel constrained decisions for any MLX model on Apple Silicon. Typed, schema-valid JSON in one forward pass.

An integration that allows LLMs to interact with Raindrop.io bookmarks using the Model Context Protocol (MCP).

OllamaFX is a native, lightweight, and professional JavaFX desktop client for Ollama. Run Llama 3, Mistral, and Phi-3 locally with maximum privacy, low RAM overhead, and a powerful interface designed

Use google sheets as a gui for crewAI

Thematic Generalization Benchmark: measures how effectively various LLMs can infer a narrow or specific "theme" (category/rule) from a small set of examples and anti-examples, then detect which item t

🧠 Self-hosted, privacy-first MCP server for long-term AI memory — save, search & summarize Claude/ChatGPT chat history locally. No cloud, no database.

GGUF Loader with its Agentic Mode, and floating button, ai Models | Open Source & Offline. Mistral, Deepseek, llama, gemma, qwen

Turn documents into structured JSON with local-first document AI. Run 100% locally by default, with API, CLI, and Web UI.

Cross-Platform High-Level LLM Library

日本語辞書 by Rust, support Telegram bot, Cloudflare Workers. Support LLM and search RAG.

Less harness. More model. A lightweight local AI assistant. / 极简 harness 的本地全能 AI 助手。

PortableLM — Zero-dependency, air-gapped local AI that runs entirely from a USB drive. Chat, generate images, and synthesize speech offline on Windows, macOS, or Linux. No installs, no internet, just

Powerful CLI and MCP server for WorkFlowy: reports, search/replace, backup support, and AI integration (Claude, LLMs)

Moved to EKKOLearnAI/hermes-web-ui; this repo is kept for historical releases.