Stars
DFlash: Block Diffusion for Flash Speculative Decoding
The repo for SHINE: A Scalable In-Context Hypernetwork for Mapping Context to LoRA in a Single Pass
XpressAI on your machine. Build continuous AI agents that work autonomously, remember what they've learned and stay on budget while you sleep.
deepbeepmeep / Wan2GP
Forked from Wan-Video/Wan2.1A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.
From-scratch implementation of OpenAI's GPT-OSS model in Python. No Torch, No GPUs.
Multilingual Document Layout Parsing in a Single Vision-Language Model
👔 FunMacs - Yet Another Lightweight Emacs Configuration, Using KISS philosophy.
An opinionated production-ready PlayFramework template that makes you productive.
SQLite-Vector is a cross-platform, ultra-efficient SQLite extension that brings vector search capabilities to your embedded database.
Agent framework for the JVM. Pronounced Em-BAY-bel /ɛmˈbeɪbəl/
Prompts, workflows and more for agentic engineering
🐴 Tutorial for the Pony programming language
A reimplementation of Stable Diffusion 3.5 in pure PyTorch
Xaibo is a modular agent framework designed for building flexible AI systems with clean protocol-based interfaces.
An MIT License of YOLOv9, YOLOv7, YOLO-RD
CLI that detects fake-star campaigns, dependency hijacks, licence red-flags and other signs of repository risk. Inspired by the “4.5 million fake stars” study, StarGuard helps CTOs, security teams …
Have a natural, spoken conversation with AI!
Erlang/Elixir integration for Swift Distributed Actors
AI Pair Programming in Emacs with Aider
aider is AI pair programming in your terminal
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"
VisualRWKV is the visual-enhanced version of the RWKV language model, enabling RWKV to handle various visual tasks.
Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"