[ICLR 2023] ReAct: Synergizing Reasoning and Acting in Language Models

An open-sourced implementation for "Agentic Context Engineering (ACE)" methon from *Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models* (arXiv:2510.04618).

OpenCE (Open Context Engineering): A community toolkit to implement, evaluate, and combine LLM context strategies (RAG, ACE, Compression). Evolved from the `ACE-open` reproduction.

微舆：人人可用的多Agent舆情分析助手，打破信息茧房，还原舆情原貌，预测未来走向，辅助决策！从0实现，不依赖任何框架。

OpenVLA: An open-source vision-language-action model for robotic manipulation.

PyTorch code and models for VJEPA2 self-supervised learning from video.

[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming Large Language Models"

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

《一人企业方法论》第二版，也适合做其他副业（比如自媒体、电商、数字商品）的非技术人群。

程序员如何优雅的挣零花钱，2.0版，升级为小书了。Most of this not work outside China , so no English translate

精益副业：程序员如何优雅地做副业

一人公司方法论

Revisiting Mid-training in the Era of Reinforcement Learning Scaling

all of the workflows of n8n i could find (also from the site itself)

A collection of MCP servers.

[EMNLP 2025 Oral] MemoryOS is designed to provide a memory operating system for personalized AI agents.

slime is an LLM post-training framework for RL Scaling.

Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning" by Zhiheng Xi et al.

Controllable Animation Video Generation with Large Models-based Multimodal Agents

Public repository for Skills

Accompanying code for "Discovering State-of-the-art Reinforcement Algorithms" Nature publication

Open-source framework for building human-intervenable deep research agents with real-time collaboration between humans and AI. Features multi-agent architecture, comprehensive tool suite, and web-b…

Open-source implementation of AlphaEvolve

DeepEvolve is a research and coding agent for new algorithm discovery in different science domains with Deep Research and AlphaEvolve.

Contexts Optical Compression

A scalable asynchronous reinforcement learning implementation with in-flight weight updates.

Democratizing AI scientists with ToolUniverse

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

An Open-source RL System from ByteDance Seed and Tsinghua AIR

Co-create PowerPoint slide decks with AI