Powered by BoxLite - embeddable sandbox with hardware-level isolation and no daemon. The SQLite of sandbox, coming soon as open source.

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

Embedded micro-VM sandbox for running AI agents.

The paper list of "Memory in the Age of AI Agents: A Survey"

A Minecraft default-look resourcepack with 3D models.

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

MiroThinker is an open source deep research agent optimized for research and prediction. It achieves a 60.2% Avg@8 score on the challenging GAIA benchmark.

HTML Agent based on NexAU

Nex General Agentic Data Pipeline, an end-to-end pipeline for generating high-quality agentic training data.

Nex Agent for Agent is a meta-agent system that automatically creates specialized AI agents based on natural language requirements.

NexDR (Nex Deep Research), a leading deep research agent that autonomously investigates complex topics and generates rich, structured reports.

Nex Venus Communication Library

NexRL is an ultra-loosely-coupled LLM post-training framework.

The absolute trainer to light up AI agents.

Codes for the paper "BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping" by Zhiheng Xi et al.

This is a notification microservice.

Backend System of Open Tree Hole

Hyper-fast code cloc tool for remote repositories. Serverless optimized.

Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.

🥢像老乡鸡🐔那样做饭。主要部分于2024年完工，非老乡鸡官方仓库。文字来自《老乡鸡菜品溯源报告》，并做归纳、编辑与整理。CookLikeHOC.

Analysis and Summary of Papers on Agent Memory Read by Dongdong

kube.io website

Best liquid-glass project, build with shader/webgl

Democratizing Reinforcement Learning for LLMs

Tongyi Deep Research, the Leading Open-source Deep Research Agent

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

MCPMark is a comprehensive, stress-testing MCP benchmark designed to evaluate model and agent capabilities in real-world MCP use.

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models