HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds

A cross-platform desktop All-in-One assistant tool for Claude Code, Codex, OpenCode, openclaw & Gemini CLI.

An agent skill that converts plain-language animation ideas into runnable ManimCE scenes and export-ready render commands.

Animation engine for explanatory math videos

Install this plugin in the browser to highlight and take notes on the page, and save the highlighted content conveniently.

🤗 LeRobot: Making AI for Robotics more accessible with end-to-end learning

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

Policy-based Riichi Mahjong(立直麻将) AI, based on Mortal and Suphx, powered by Rust and deep RL.

🚀🀄️ A fast and strong AI for riichi mahjong, powered by Rust and deep reinforcement learning.

Game server for Japanese Mahjong AI.

基于Suphx的立直麻将AI

Converts Tenhou game logs into mjai format for Mortal AI training.

The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simulations to serve as environments for training intelligent agents using deep reinforcement …

用于贝叶斯神经网络的不确定性量化方法合集

四种强化学习算法在“CartPole-v1”游戏中的表现，包括DQN/DDQN/PolicyGradient/ActorCritic。

An open-source AI agent that lives in your terminal.

Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.

A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

HAZARD challenge

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Awesome machine learning for combinatorial optimization papers.

True Detective: Challenging Benchmark for Deep Abductive Reasoning in Foundation Models