EvoCUA: Evolving Computer Use Agent

Edit Banana: A framework for converting statistical formats into editable.

Complete Claude Code configuration collection - agents, skills, hooks, commands, rules, MCPs. Battle-tested configs from an Anthropic hackathon winner.

Qwen-Image-Layered: Layered Decomposition for Inherent Editablity

[ICLR 2025] Autoregressive Video Generation without Vector Quantization

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

🐹 Deep clean and optimize your Mac.

SkyRL: A Modular Full-stack RL Library for LLMs

Implementation of "Hyperspherical Latents Improve Continuous-Token Autoregressive Generation"

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

verl: Volcano Engine Reinforcement Learning for LLMs

Grounded SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

Pytorch implementation for the paper titled "SimpleAR: Pushing the Frontier of Autoregressive Visual Generation"

Open-source and strong foundation image recognition models.

Reference PyTorch implementation and models for DINOv3

A reading list on LLM based Synthetic Data Generation 🔥

DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top-level planning agent to coo…

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

Model Context Protocol Servers

An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control.

Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.

Several simple examples for popular neural network toolkits calling custom CUDA operators.

🤗 smolagents: a barebones library for agents that think in code.

Implementation of the training framework proposed in Self-Rewarding Language Model, from MetaAI

Dream 7B, a large diffusion language model