Remote-mode adapter that lets the Codex desktop app talk to Claude Code through the native Codex app-server protocol

你的下一次Vibe Coding，何必从终端开始？以一流的 UI 界面和智能体协作，work ALL in 飞书。

PyTorch Single Controller

Uni-Agent is a framework for training long-horizon agents.

Compact and Agent-Native MoE Training System

Democratizing Reinforcement Learning for LLMs

An asynchronous streaming data management module for efficient post-training.

Open MinT training runtime on veRL

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

From Automated Idea Factory to Realization

An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.

UCCL is an efficient communication library for GPUs, covering collectives, P2P (e.g., KV cache transfer, RL weight transfer), and EP (e.g., GPU-driven)

Claude Code SDK Demos

Collection of evals for Inspect AI

BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent (ACL 2026 Main)

Evaluating GPT-OSS on BrowseComp-Plus with Native Browsering Tools

Lightweight, clear, and fully extensible AI agent infrastructure — learn easily, customize anything 🐉

Rethinking the Trust Region in LLM Reinforcement Learning

The absolute trainer to light up AI agents.

"CLI-Anything: Making ALL Software Agent-Native" -- CLI-Hub: https://clianything.cc/

OpenClaw-RL: Train any agent simply by talking

Fast, Sharp & Reliable Agentic Intelligence

🚀 Fast and simple Node.js version manager, built in Rust

Qwen3.6 is the large language model series developed by Qwen team, Alibaba Group.

pyright fork with various type checking improvements, improved vscode support and pylance features built into the language server

Python command line wrapper for pyright, a static type checker

Implementation of GradLoc from the Tencent Hunyuan blog "Stabilizing RLVR via Token-level Gradient Diagnosis and Layerwise Clipping".

Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…

A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training

OpenSource Claude Cowork. A desktop AI assistant that helps you with programming, file management, and any task you can describe.