The database of free AI tools on GitHub

Local-first task manager with a visual weekly timeline. Works offline, syncs across devices, and self-hosts with one Docker command. Uses SQLite by default, so no external database is needed.

A simple to use Ollama autocompletion engine with options exposed and streaming functionality

Feel how fast a local LLM runs before you buy the hardware

Free, open-source Grammarly alternative for Chrome & Safari — AI grammar checker and text rewriter for any website, powered by your own free Google Gemini API key. No account, no tracking, no subscrip

A lightweight vLLM-style inference engine in Rust

SmarterRouter: An intelligent LLM gateway and VRAM-aware router for Ollama, llama.cpp, and OpenAI. Features semantic caching, model profiling, and automatic failover for local AI labs.

This is the corresponding code for the book Transformers in Action

A ternary, zero-heap tiny language model that runs inside a $2 microcontroller — bit-exact Python <-> C99 <-> Cortex-M3 (QEMU) parity. Apache-2.0.

Open-source desktop SSH client with an AI assistant and end-to-end encrypted sync through your own Cloudflare account

First-class Linux packaging for DeepSeek Harness desktop — AppImage, .deb, .tar.gz for x64/arm64, built by native CI.

DeepSeek-V4-Flash-0731 284B inference in ~25 GB of RAM / Qwen3.8-Next-Flash inference in ~15 GB of RAM on any M-series MacBook

Your AI mate into your favourite terminal

Integrate LLM's into your OS. For any issues or ideas, message us in the discord server below!

Opinionated macOS setup

The first block-based adaptive learning workspace that runs locally. Upload any material → get AI-generated notes, quizzes, flashcards, and an adaptive tutor. Open source, self-hosted, 10+ LLM provide

🦀 Personal Multi-agent AI assistant platform, written in Rust — multi-agent, self-learning skills, RAG, MCP, and agentskills.io compatible

🤖 Discover how to apply your LLM app skills on Kubernetes!

TiyGate is a lightweight gateway for highly available LLM services. 一款致力于提供高可用 LLM 服务的轻量级网关。

Privacy-first AI roleplay & BYOK (Bring Your Own Key) & roleplaying, companion and storytelling app with long-term memory, custom characters, and 20+ providers. Android, Windows, macOS, Linux. Support

Tree-based speculative decoding for Apple Silicon (MLX). ~10-15% faster than DFlash on code, ~1.5x over autoregressive. First MLX port with custom Metal kernels for hybrid model support.

CLI tool – estimates LLM tokens/costs and runs provider-aware load tests for OpenAI, Anthropic, OpenRouter, or custom endpoints.

Local, gradient-free neuro-symbolic memory engine combining Hyperdimensional Computing (HDC/VSA), Hebbian plasticity, and graph triples for offline AI.

Apple AI is a lightweight, privacy‑minded macOS menu bar app that keeps your favorite AI assistants one keystroke away. Open a compact, always‑on‑top chat window and jump between services like ChatGPT

A Python package for interacting with the MinerU Vision-Language Model.

The genuine open dictionary, grounded by Wikitionary and explained more with LLMs

Local-first desktop AI workbench for roleplay, multi-character chat, long-form writing, RAG, MCP tools, plugins, and local models.

Custom output voices for ChatGPT, Codex, and Grok Bot — local and near real time.

OpenAI API client for Delphi and Lazarus/FPC. Use ChatGPT, DALL-E and other products from Pascal language.

デジタル庁のガバメントAI「源内(GENAI)」を完全ローカル(ローカルLLM/OpenAI互換)で動かす非公式プロジェクト。SAML認証(Keycloak)・RAG(Qdrant)・文字起こし(Whisper)・画像生成(SD)・チーム単位ナレッジをローカル完結。

GenAI & agent toolkit for Apple Silicon Mac, implementing JSON schema-steered structured output (3SO) and tool-calling in Python. For more on 3SO: https://huggingface.co/blog/ucheog/llm-power-steering