Control panel for VLLM, Sglang, llama.cpp, exllamav3

Protect against malicious code installed via npm, yarn, pnpm, npx, pnpx, pip, uv and poetry with Aikido Safe Chain. Free to use, no tokens required.

The AI framework that adds the engineering to prompt engineering (Python/TS/Ruby/Java/C#/Rust/Go compatible)

Optimized fork of ish-arm64 to provide iOS developers with a working Linux userland

CADAM is the open source text-to-CAD web application

Rust implementation of Tailscale (preview, experimental)

Fast computer automation CLI for AI agents. Control any desktop with screenshots, clicks, typing, scrolling, and more.

A simple, rational music player for android

A declarative UI framework that interprets YAML configuration and Lua scripting into fully native SwiftUI and Jetpack Compose — no web views, no hybrid layers.

Annotate and review coding agent plans and code diffs visually, share with your team, send feedback to agents with one click.

A CLI for Twitter/X — feed, bookmarks, and user timeline in terminal

Self-personalizing LM

embedded-graphics backend for Ratatui

A repo of useful MLX skills.

React Native VM (Hermes Bytecode Library) in C

Nano vLLM

dLLM: Simple Diffusion Language Modeling

An interface library for RL post training with environments.

Mirage Persistent Kernel: Compiling LLMs into a MegaKernel

mouse & keyboard sharing via LAN

rl from zero pretrain, can it be done? yes.

my artificial intelligence (😸AI)

Qwen3 self-hosting on `llama.cpp`

OpenTUI is a library for building terminal user interfaces (TUIs)

explore token trajectory trees on instruct and base models