Stars
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
NeuraPress 是一个现代化的 Markdown 编辑器，专注于提供优质的微信公众号排版体验。响应式设计，支持移动设备。搭配 DeepSeek和微信公众号助手使用，碎片时间也能用手机发有排版的文章了。
Easily fine-tune, evaluate and deploy Gemma 4, Qwen3.5, Qwen3.6, gpt-oss, DeepSeek-R1, or any open source LLM / VLM!
Qwen3-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.
STUMPY is a powerful and scalable Python library for modern time series analysis
Data-driven APIs for common optimization tasks
Infinite Photorealistic Worlds using Procedural Generation
Official codebase for I-JEPA, the Image-based Joint-Embedding Predictive Architecture. First outlined in the CVPR paper, "Self-supervised learning from images with a joint-embedding predictive arch…
🔥Highlighting the top ML papers every week.
Get a ChatGPT plugin up and running in under 5 minutes!
Recurrent and multi-process PyTorch implementation of deep reinforcement Actor-Critic algorithms A2C and PPO
Computationally friendly hyper-parameter search with DP-SGD
Official repo for the E3B algorithm described in the paper "Exploration via Elliptical Episodic Bonuses".
High throughput synchronous and asynchronous reinforcement learning
One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)
A simple OpenAI Gym environment for single and multi-agent reinforcement learning
A Python interface for reinforcement learning environments
A suite of test scenarios for multi-agent reinforcement learning.