Recipes for shrinking, optimizing, customizing cutting edge vision models. 💜

A lightweight sandboxing tool for enforcing filesystem and network restrictions on arbitrary processes at the OS level, without requiring a container.

The best ChatGPT that $100 can buy.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

A GPU-accelerated cross-platform terminal emulator and multiplexer written by @wez and implemented in Rust

CUDA syntax highlighting for Vim

Extended Vim syntax highlighting for C and C++ (C++11/14/17/20/23)

This repository shares end-to-end notebooks on how to use various Weaviate features and integrations!

Currently used legacy lobby for BAR, for the new lobby development see https://github.com/beyond-all-reason/bar-lobby

Main game repository for Beyond All Reason.

Tmux Plugin Manager

My dotfiles synced from localhost and remote machines

A Tmux session manager, with preview, fuzzy finding, and MORE

an opinionated approach to productive development with Claude Code

Tmux Sessionizer: A tool for opening git repositories as tmux sessions

A CLI tool for analyzing Claude Code/Codex CLI usage from local JSONL files.

Official Homebrew tap for Bun

Transform your Claude Code experience with a beautiful, informative statusline

PROJECT_INDEX system for Claude Code - provides architectural awareness for AI coding

We present StableAvatar, the first end-to-end video diffusion transformer, which synthesizes infinite-length high-quality audio-driven avatar videos without any post-processing, conditioned on a re…

Puzzles for learning Triton

Efficient LLM inference on Slurm clusters using vLLM.

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Plugin to help you stop repeating the basic movement keys

Solve Visual Understanding with Reinforced VLMs

A python tool that uses GPT-4, FFmpeg, and OpenCV to automatically analyze videos, extract the most interesting sections, and crop them for an improved viewing experience.

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

The Enterprise-Grade Production-Ready Multi-Agent Orchestration Framework. Website: https://swarms.ai

Entropy Based Sampling and Parallel CoT Decoding

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.