Flow-driven recursive skill evolution for agentic LLM orchestration.

Claude Code Source - Buildable Research Fork. Reverse-engineered build system, runnable with Bun.

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

🔬🦞 A self-evolving AI research colleague for scientists. 285 skills, zero hallucination, persistent memory.

Turn any workflow into reusable AI agent skills that install on 17 platforms — Claude Code, Copilot, Cursor, Windsurf, Codex, Gemini, Kiro, and more. One SKILL.md, every platform.

Now, Stronger AI Pushes Frontiers, Stronger Our Shared Future.

[ICML 2026] Official resources of "Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning".

FlowSteer: agents designing agentic workflows via reinforced progressive canvas editing.

Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement Learning

Examples of my Claude Code infrastructure with skill auto-activation, hooks, and agents

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

从0开始学习英语语法

tju_elm天津大学22级软件工程综合实践仿饿了么外卖平台项目

study-cloud, notes, codes

II-Agent: a new open-source framework to build and deploy intelligent agents

yolov5 车辆检测 车牌检测 车牌识别

yolov8 车牌检测 车牌识别 中文车牌识别 检测 支持12种中文车牌 支持双层车牌

A collection of MCP servers.

基于200万条医疗数据对DeepSeek-R1-Distill-Qwen-32B进行fine tune且部署

A simple screen parsing tool towards pure vision based GUI agent

fine-tune deepseek r1

基于200万条医疗数据对deepseek-r1进行微调

基于200万条医疗数据对deepseek-r1进行微调

基于200万条医疗数据对deepseek-r1进行微调

基于200万条医疗数据对deepseek-r1进行微调

My love story with MaryNee

🔥大屏，物联网大屏，一个基于 vue、datav、Echart 框架的大数据可视化（大屏展示）模板