Fast and memory-efficient exact kmeans

A light-weight and powerful meta-prompting, context engineering and spec-driven development system for Claude Code by TÂCHES.

OpenClaw-RL: Train any agent simply by talking

AI agents running research on single-GPU nanochat training automatically

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

An AI SKILL that provide design intelligence for building professional UI/UX multiple platforms

Lightweight GUI Automation Agent with Grid-Based Visual Grounding

Official implementation of GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

Compose multimodal datasets 🎹

omo; the best agent harness - previously oh-my-opencode

Agili 的 AIGC 周刊 - 一个由 Agentic AI Agent 驱动的 AIGC（人工智能生成内容）精选周刊。

Official Implementation of "MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives"

LLM Transparency Tool (LLM-TT), an open-source interactive toolkit for analyzing internal workings of Transformer-based language models. *Check out demo at* https://huggingface.co/spaces/facebook/l…

[ICLR 2026] MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning

Make your JSON data collaborative and version-controlled with CRDTs

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

Python curses command line CSV and tabular data viewer

This is the official repo for the paper "LongCat-Flash-Omni Technical Report"

Contexts Optical Compression

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

「来剪」轻量级视频编辑器。网页版、桌面版等均可免费使用，功能灵感源自 CapCut 等编辑器。A Lightweight Video Editor. Free for the web, desktop, and more, with features inspired by editors like CapCut.

The best ChatGPT that $100 can buy.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Multilingual Document Layout Parsing in a Single Vision-Language Model

A curated collection of fun and creative examples generated with Nano Banana & Nano Banana Pro🍌, Gemini-2.5-flash-image based model. We also release Nano-consistent-150K openly to support the commu…

Read and write tensorboard data using Rust

Open-Source Frontier Voice AI