WSL2 Manager desktop application built with Tauri, Vite, React, and TypeScript

A skill for AI agents: search the web with SearXNG, browse with Camofox, bypass protections with CloakBrowser. Anti-hallucination by design. Self-hosted, free, unlimited.

goldr - layout-driven HTMX-native Go framework for building web apps

TTT Editor - Terminal Text Tool: a terminal text editor IDE. A real alternative to VS Code, Zed, and Sublime that runs in your terminal. Single binary, zero config.

Build gsx/Templ pages with Struct-based Routing

Official code for MAMMA: Markerless Accurate Multi-person Motion Acquisition.

Open-source governed, local-first memory control plane for AI agents and teams. arXiv:2608.08253

Open research on finite observer-consistency in physics: Lean-checked theorems and lemmas, reproducible simulations, explicit countermodels, and clearly tracked open physical bridges.

Contract-driven AI coding and verification for agent workflows.

Software architecture diagramming tool. Includes a modern easy to use Frontend + Backend + CLI to enable managing diagrams from the shell or in CI.

Daemonless, ultra-lightweight (~2.1mb) speech recognition for Linux (no dependencies beyond pure C++ and the Linux toolchain)

Unified TUI and CLI to index and search your local coding agent session history across 11+ providers (Codex, Claude, Gemini, Cursor, Aider, etc.)

AI coding agent optimized for small LLMs. 87% benchmark with 4B-active model.

⚒️ The open source dark software factory for expert engineers.

pi extension that exposes agent-browser as a native tool for browser automation

DFlash: Block Diffusion for Flash Speculative Decoding

RTX 6000 Pro Wiki — Running Large LLMs (Qwen3.5-397B, Kimi-K2.5, GLM-5) on PCIe GPUs without NVLink

Build a modern LLM from scratch. Every line commented. Explained like we are five.

A TUI around llama.cpp for running, managing, and benchmarking local GGUF models and launching the pi coding agent against your local server.

LLM speculative inference server for consumer & heterogeneous hardware

llama.cpp fork with additional SOTA quants and improved performance

hardware implementation of transformers running microgpt at 50k+ tkps

🧑‍🎨 A collection of agentic skills that works

A simple, fast and robust program-aware agentic inference system.

The headless browser for AI agents and web scraping

Render markdown on the CLI, with pizzazz! 💅🏻

Open-source, low-cost 10.5 GHz PLFM phased array RADAR system

A native Rust CLI for orchestrating AI agents across projects, with persistent sessions, worktrees, and local-first control.