MCP Server connecting to Perplexity Comet browser

Multi-Platform Package Manager for Stable Diffusion

Build resilient language agents as graphs.

Official inference framework for 1-bit LLMs

High-performance QuakeSpasm fork

TACL 2020: Syntax-Guided Controlled Generation of Paraphrases

[ICLR2025 Spotlight] SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

A comprehensive collection of Agent Skills for context engineering, multi-agent architectures, and production agent systems. Use when building, optimizing, or debugging agent systems that require e…

Official Implementation of "Affordable AI Assistants with Knowledge Graph of Thoughts"

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

Public repository of the Micro QuickJS Javascript Engine

SoTA open-source TTS

A followup to the functional quadtree

RAG database of the ProleWiki Corpus for enhancing open-source AI agents with a RAG database as encyclopedia of Marxism

Train and block edit and save LoRAs directly inside ComfyUI for Z-image Turbo, SDXL, Flux, WAN 2.2, SD 1.5

GLM-TTS: Controllable & Emotion-Expressive Zero-shot TTS with Multi-Reward Reinforcement Learning

Minimal CLI coding agent by Mistral

The missing standard library for multithreading in JavaScript (Works in the browser, Node.js, Deno, Bun)

Remove Backgrounds With AI & GIMP 3

The lightweight, fault-tolerant database built on SQLite. Designed to keep your data highly available with minimal effort.

A portable terminal AI interface

Android App Live Wallpaper based on the art of Mark Ferrari and code of Ian Gilman and Joseph Huckaby

Code for the ICML 2025 Paper "Product of Experts with LLMs: Boosting Performance on ARC is a Matter of Perspective"

[CVPR 2024] Official implementation for "SVGDreamer: Text Guided SVG Generation with Diffusion Model" https://arxiv.org/abs/2312.16476

Basic interfaces for the various AI text/chat bots

Qwen-Image is a powerful image generation foundation model capable of complex text rendering and precise image editing.

Wan: Open and Advanced Large-Scale Video Generative Models

Versatile audio super resolution (any -> 48kHz) with AudioSR.

🖼️🤖 302 Vector Graphics Generation! 🚀✨