Language model tokenization at GB/s

CLI that turns a YouTube guitar-lesson video into a PDF of the guitar tab.

A bare-metal x86 utility to dump physical RAM directly to disk. Built and tested for Cold Boot Attack experiments on frozen memory.

Beautiful, AI-native markdown IDE and LLM wiki

A suite of plugins for legal workflows

Warp is an agentic development environment, born out of the terminal.

Open source, zero webhooks payment provider

Improve Pod scheduling by making Kuberentes aware of its network topology, reducing latency and data transfer cost

The best ChatGPT that $100 can buy.

Library of 45+ independent Lua modules improving Neovim experience with minimal effort

Direct File

Open-source implementation of the Nintendo WaveBird receiver using Silicon Labs Wireless Gecko SoCs

🔊 High-precision web player for multi-device audio playback and spatial audio.

Kete Solar System Survey tools

Command and Conquer: Red Alert

iOS and macOS Decompiler

Onit MacOS client

Simulation platform for general-purpose robotics & embodied AI learning.

the LLM vulnerability scanner

Automate browser based workflows with AI

An Open-source LTE Downlink/Uplink Eavesdropper

An step by step fuzzing tutorial. A GitHub Security Lab initiative

A conversational, AI device + software framework for companionship, entertainment, education, healthcare, IoT applications, and DIY robotics. Built with Python, NextJS, Arduino, ESP32, LLMs (GPT-4o…

Training code and resources for AMD-135M language models on AMD GPUs.

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.