Stars
🗓️ The hardest life-admin benchmark for agents — lawsuits, escrow shortfalls, apartment hunts, exams. 20 long-horizon tasks × 20–30 stages across 10 domains and 21 services, scored by 1247 atomic c…
Musicdl: A lightweight music downloader written in pure python. (轻量级无损音乐下载器，支持数十个音乐/有声读物平台，例如网易云音乐，QQ音乐，酷狗音乐，酷我音乐，咪咕音乐，千千静听，汽水音乐，Bilibili，街声，喜马拉雅，懒人听书，荔枝FM，蜻蜓FM，JOOX，TIDAL，YouTube，Apple Music，Spoti…
A terminal workspace with batteries included
Map the best way into any topic. 规划任何主题的最佳学习路径。
Muon is an optimizer for hidden layers in neural networks
Awesome GUI Agent Paper List
ACL'2025: SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs. and preprint: SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning
https://checkcc.org 是一个 Claude 运行环境检测与账号风险分析工具，面向正在注册 Claude 账号、订阅 Claude Pro、申请 Claude API、使用 Claude Code，或担心 Claude 封号、账号受限、订阅失败的用户。
Awesome Multimodal Modeling [Covers MLLM, UMM, and NMM]
OpenAI Codex 桌面端/CLI 的可视化管理工具，具有Provider/API 切换、会话同步、提示词注入、Skills/MCP 管理、TOML 配置可视化的跨平台工具。
Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…
《深入理解 AI Agent：设计原理与工程实践》（李博杰 著）开源主仓库：全书正文、编译版 PDF 与按章配套代码
Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains papers, codes, datasets, evaluations, and analyses.
The roadmap of long-horizon agents
Elevate your AI research writing, no more tedious polishing ✨
Run frontier MoE models on hardware you already own — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦
Official Repository for our paper: AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
[COLM2026] Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning
Lightweight loop engineering state kernel for long-running AI agent teams. Agent-loop agnostic across Codex, Claude Code, and other coding agents, with durable goals, quota-aware auto-wake, executa…
Scripts for agents, shared between my repositories.
PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages