Agentic RL on Any Harness at Scale

AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI

The 100 line AI agent that solves GitHub issues or helps you in your command line. Radically simple, no huge configs, no giant monorepo—but scores >74% on SWE-bench verified!

Secure, Fast, and Extensible Sandbox runtime for AI agents.

AgentOpt automatically finds the best LLM model combination for each step of your agent — optimizing for accuracy, cost, and latency.

🚀 Efficient implementations for emerging model architectures

Bilibili Ad Jumper Package

Physics of Language Models: Part 4.2, Canon Layers at Scale where Synthetic Pretraining Resonates in Reality

Blueprint for the PNT+ Project

A curated list of papers of interesting empirical study and insight on deep learning. Continually updating...

Low-code framework for building custom LLMs, neural networks, and other AI models

Sandbox implemented in GO including containers (namespace, cgroup), ptrace, seccomp

Offline test system for THUOOP

JXOJ——基于UOJ的信息学在线评测系统

一个有很多新增 feature 的 UOJ

将各种各样格式的数据转换为 UOJ 的格式 🎉 文件名转换 | subtask 设置| 添加样例 | 生成 problem.conf 🚀

一个船新版本的 UOJ 评测机程序，可以完美兼容原有 UOJ 的协议。

Sandbox service built on Linux container technologies with simple REST and gRPC API

Sandbox for securely executing untrusted programs

Contest Management System

Models and examples built with TensorFlow

Code repository for the paper "Hyperparameter Optimization: A Spectral Approach" by Elad Hazan, Adam Klivans, Yang Yuan.

Universal Online Judge