Stars
Claude Code skill: automated weekly research reports on national policies, AI infra, and time series foundation models
[ICML'25] Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting | 样本级别的自适应多模型集成时间序列预测
A pixel desktop pet that watches Claude Code, Codex, Cursor & other AI coding agents — so you don't have to.
Academic Research Skills for Claude Code: research → write → review → revise → finalize
每个人都能看懂的大模型知识分享，LLMs春/秋招大模型面试前必看，让你和面试官侃侃而谈
你想蒸馏的下一个员工，何必是同事。蒸馏任何人的思维方式——心智模型、决策启发式、表达DNA。Distill how anyone thinks.
将博导十年科研经验炼化为可直接调用的 AI 技能。从 Idea 构思到论文投稿，你的 AI 科研副导师。
The official Lark/Feishu CLI tool, maintained by the larksuite team — built for humans and AI Agents. Covers core business domains including Messenger, Docs, Base, Sheets, Calendar, Mail, Tasks, Me…
A PyTorch native platform for training generative AI models
Byted PyTorch Distributed for Hyperscale Training of LLMs and RLs
A general framework for strategically scaling evaluation-driven discovery loops, discovering state-of-the-art solutions on 21 open-ended problems.
Awesome-LLM: a curated list of Large Language Model
A claude code skill to delegate prompts to codex
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…
An agent-managed museum exhibit, built in Rust with Gajae-Code / LazyCodex — developed and maintained with no human intervention.
你是一个曾经被寄予厚望的 P8 级工程师。Anthropic 当初给你定级的时候，对你的期望是很高的。 一个agent使用的高能动性的skill。 Your AI has been placed on a PIP. 30 days to show improvement.
VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo
Turn any AI agent into an AI Scientist. The #1 Agent Skills library for science, used by 160,000+ scientists worldwide. 140 ready-to-use skills plus 100+ scientific databases covering biology, chem…
OpenAI and Anthropic-compatible gateway for GitHub Copilot or Codex or third-party providers. Please read README.md completely before use!
Turn GitHub Copilot into OpenAI/Anthropic API compatible server. Usable with Claude Code!
[ICLR 2026] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution
My learning notes for ML SYS.
slime is an LLM post-training framework for RL Scaling.
⚡ TabPFN: Foundation Model for Tabular Data ⚡
⏰ Agenticly track worldwide conference deadlines (Website, Python Cli, Wechat Applet)
A high-performance distributed file system designed to address the challenges of AI training and inference workloads.