Reproducing and studying RL algorithms for LLM agents, including PPO, GRPO, GSPO, DAPO, OPD and beyond.

A Call of Duty-quality FPS in Three.js, built from a single prompt.

A skill family for shaping the research storyline of CCF-A papers.

Open and control a Linux server terminal through GitHub Actions from macOS, Windows, or Linux

Official implementation of Harness-G: A Graph-Structured Harness for Search Agents

🎓从0开始训练一个大模型Minimind项目的超详细解析，包括但不限于用到的架构，算法，以及大模型面试经验

Schedule search agents the way an OS schedules processes.

Map the best way into any topic. 规划任何主题的最佳学习路径。

Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

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

本地 Grok Runtime，为多种 AI 编程 Agent 提供可管理的交互式会话 | Local Grok runtime for manageable interactivesessions across AI coding agents

The roadmap of long-horizon agents

The official GitHub page for the paper "Agent Systems with Harness Engineering"

Elevate your AI research writing, no more tedious polishing ✨

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Codex skill for full academic paper lifecycle analysis and revision

Qwen-AgentWorld: Language World Models for General Agents

Use ChatGPT Developer Mode as a local coding agent for your repo through MCP.

The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

UniRL is a Framework for Unified Multimodal Model Reinforcement Learning

Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.

人味儿写作 · An AI agent skill: edit people's words without erasing the person behind them

[CVPR 2026] [Best Paper Finalist] [Oral] Official repository of Vision Test-Time Training

An open source personal productivity platform built on Markdown, turbo charged with the scripting power of Lua

🥇 Not Just Another Agent Framework, But a Bayesian Evolution Layer That Can Work Across Harnesses