Stars
1st place solution for 2026 KDD Cup DataAgents . 2026年KDD Cup DataAgents 冠军方案。
Executable, measurable, and reproducible AI4AI toward recursive self-improvement. Home of OpenMLE and Frontis-MA1.
Claude Autoresearch Skill — Autonomous goal-directed iteration for Claude Code. Inspired by Karpathy's autoresearch. Modify → Verify → Keep/Discard → Repeat forever.
AgentENV (AENV) is a distributed platform for running agent environments at scale.
Generate draw.io diagrams from natural language — 11 presets (UML, SysML/MBSE, BPMN, network, C4…), 36 tools: codebase/CI/infra-to-diagram, image→editable diagram, mind maps, build-up animation, ex…
📚 《从零开始构建智能体》——从零开始的智能体原理与实践教程
A straightforward method for training your LLM, from downloading data to generating text.
Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.
An agentic-first RL framework for research (9k lines).
DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference
A股全栈数据工具包 · 十一层架构 · 54端点 · 19数据源 · 零鉴权 | Full-stack China A-share data toolkit for AI agents — 11 layers, 54 endpoints, 19 sources, zero-auth
[ICML 2026 Spotlight] Latent Collaboration in Multi-Agent Systems
Official Implementation of VisualClaw: A Real-Time, Personalized Agent for the Physical World
Bridging LLM and Recommender System.
Collaborative Memory-Augmented Agentic Recommender System
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
An active paper-reading skill that reconstructs author reasoning, explains methods mechanistically, stress-tests assumptions, and generates follow-up research ideas.
Apache Doris is a real-time analytics and hybrid search database for AI agents.
UniRL is a Framework for Unified Multimodal Model Reinforcement Learning
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
2025腾讯广告算法大赛-分数0.0978代码
From Pipeline to Council — A lightweight agentic framework for search & recommendation. 五个 Agent 重构搜广推管线。
FlashInfer: Kernel Library for LLM Serving
A benchmark for evaluating LLMs on Chinese traditional fortune telling — Bazi (八字) and Ziwei Doushu (紫微斗数).
Label Studio is a multi-type data labeling and annotation tool with standardized output format
🤖 Your Intelligent Copilot for Data Exploration and Processing Pipeline