8000 tongyx361 (Shawn/Yuxuan Tong) / Starred · GitHub
[go: up one dir, main page]

Skip to content
View tongyx361's full-sized avatar

Block or report tongyx361

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results
JavaScript 21 5 Updated Aug 20, 2026< 8000 /relative-time>

A set of examples based on verl for end-to-end RL training recipes.

Python 349 177 Updated Nov 16, 2026

The agent flow system for token maxxing.

Python 407 40 Updated Nov 16, 2026
Shell 6 Updated Sep 9, 2026

简明技术中文 / Simplified Technical Chinese: a controlled language for Chinese technical writing, modelled on ASD-STE100. 40 rules, a one-meaning-one-word vocabulary, a zero-dependency checker, and an ag…

Python 83 4 Updated Oct 5, 2026

高性价比人生指南: 长寿防病、急救、省钱理财、法律红线、失业与工伤、医保社保、恋爱婚育、怀孕育儿、创业与做平台合规、出国与技能。每条写明成本、收益、证据等级和原始出处,只引期刊论文与官方文件。

HTML 75,998 6,746 Updated Nov 12, 2026

Provide performance insight capabilities for RL frameworks.

Python 103 42 Updated Nov 16, 2026

A simple, fast and robust program-aware agentic inference system.

Python 480 52 Updated Jul 5, 2026

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

TypeScript 110 25 Updated Nov 15, 2026

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。

TypeScript 33 3 Updated Nov 16, 2026

PyTorch Single Controller

Rust 1,085 189 Updated Nov 16, 2026

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

Python 728 157 Updated Nov 12, 2026

Compact and Agent-Native MoE Training System

Python 360 39 Updated Nov 16, 2026

Democratizing Reinforcement Learning for LLMs

Python 5,920 642 Updated Oct 16, 2026

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

Python 175 58 Updated Nov 13, 2026

Open MinT training runtime on veRL

Python 69 9 Updated May 18, 2026

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

Python 676 208 Updated Nov 16, 2026

From Automated Idea Factory to Realization

Shell 1,616 137 Updated Aug 28, 2026

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

Rust 194,763 107,280 Updated Nov 10, 2026

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)

C++ 1,586 198 Updated Nov 16, 2026

Claude Code SDK Demos

TypeScript 2,813 441 Updated Aug 27, 2026

Collection of evals for Inspect AI

Python 744 487 Updated Nov 16, 2026

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

Python 392 69 Updated May 28, 2026

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

Python 20 3 Updated Oct 17, 2025

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

Rust 641 101 Updated Oct 14, 2026

Rethinking the Trust Region in LLM Reinforcement Learning

Python 76 7 Updated Mar 2, 2026

The absolute trainer to light up AI agents.

Python 18,958 1,724 Updated Nov 12, 2026

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

Python 58,773 5,294 Updated Sep 22, 2026

OpenClaw-RL: Train any agent simply by talking

Python 5,747 612 Updated May 23, 2026

Fast, Sharp & Reliable Agentic Intelligence

C++ 2,090 89 Updated Apr 3, 2026
Next
0