Local AI text-to-speech with voice cloning and voice design, powered by GGML. C++17 port of Qwen3-TTS (QwenLM/Qwen3-TTS). 10 languages, 24 kHz mono output, runs on CPU, CUDA, ROCm, Metal, Vulkan.

An agent-first decompiler designed to be refined by other agents. Kuna is written in Rust and was originally ported from Ghidra.

a library for background removal models

Bento, the office suite that fits in a file

A hive mind communication platform

The Juggler Code Agent

Have a lan party with iroh (iroh-lan = hamachi - account - install)

Jacobian-Brainwash : A manual alignment tool for large language models built on Anthropic's Jacobian Lens. Results are exportable.

🦊 Invisible low-latency P2P mesh VPN - silent to DPI, Reed–Solomon FEC loss-recovery, self-certifying mesh discovery, NAT hole-punching. What does the fox say? Nothing.

Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

the runtime your coding agents live on

Entirety of `rustc`, translated to C.

An all-in-one, pure C++ inference engine for audio models, powered by ggml. Supports TTS, STT, VAD, voice conversion, music generation, and more, with highly optimized performance. No Python depend…

A Pocket-Sized MLLM for Ultra-Efficient Image and Video Understanding on Your Phone

Remote control for AI coding agents. Rust + GPUI + QUIC/UDP. Available on iOS/Android

Claude Code workflow for mapping projects into clean-room behavior docs, file maps, batch reports, verification, and rebuild-ready blueprints.

Plex Unlocker

Ultima Online T2A client recreated from Origin's 2.0.7 client decompilation

super expressive prompting model based on ltx2.3

TRUST – Coding Rust like it's 1989

High-Quality Voice Cloning TTS for 600+ Languages

Ultima Online Demo from Ultima Online: The Second Age CD

Ultima Online server data files

OUO: reverse engineering of Ultima Online: The Second Age server

An efficient AI coding agent extendable by neovim like Lua plugins

TCP to QUIC Proxy for spacetimedb

cerberus-re is a local Apple-focused reverse-engineering workbench for building a repeatable three-headed static/dynamic/instrumentation loop around Ghidra, LLDB, and Frida.

llama.cpp/ik_llama.cpp launcher: loads big MoE models across mismatched multi-GPU rigs by exact VRAM math.

An agentic research orchestrator for Go that is optimized to use free search & low-cost limited context window llms.