Songyang Gao songyang0603
-
The Hong Kong University of Science and Technology (Guangzhou)
- Guangzhou, China
- https://songyang0603.github.io/
Organizations
@Open-Source-Makers-AssociationStars
Official Code Repository for ResearchAgent (NAACL 2025)
A format specification for describing a visual identity to coding agents. DESIGN.md gives agents a persistent, structured understanding of a design system.
last30days-cn 是一个 AI Agent 技能(Skill),能够自动搜索中国互联网 8 大主流平台最近 30 天的内容,综合分析后生成有据可查的研究报告。
A configurable Deep Research agent and TypeScript framework for DeepSeek Harness, with web search, optional page and PDF reading, and cited reports.
A free, safe and open agent for everything. Alternative to Claude Cowork & Codex. Open Bridge, the AI bridge between your intention and get the job done.
Agent Skills for researching product ideas, writing build decisions, and deploying frontend projects to Vercel.
😼 优雅地使用基于 clash/mihomo 的代理环境
Portable Agent Skill for repository-native Spec programming, informed by public DeepSeek Harness engineering patterns.
A curated list of plugins for DeepSeek Harness (dsh) · DeepSeek Harness 插件精选列表
DeepSeek Harness: Everything is a Plugin.
DeepSeek Harness (DSH) ecosystem: curated plugins, tools, and infrastructure from dsh-external/hub and the public dsh-plugin topic.
把 Markdown 一键排成可直接粘进公众号编辑器的精致 HTML —— 6 套精选主题 + 主题生成器 + 双关卡校验。An AI-agent skill that turns Markdown into paste-ready WeChat article HTML.
🎨 Best DeepSeek Harness Design Plugin. The open-source Claude Design alternative. 🖥️ Local-first desktop app. 🖼️ Your coding agent becomes the design engine: prototypes, landing pages, dashboards, ...
An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of...
Biomni: a general-purpose biomedical AI agent
A desktop app to prototype agent ideas, inspect every harness step, replay failures, and evaluate performance, all in one place. Local-first, cloud-ready for managed agents.
Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
[NeurIPS 2025] 🌐 WebThinker: Empowering Large Reasoning Models with Deep Research Capability
1,324-exercise fitness dataset — animation GIFs, ×ばつ180 thumbnails, muscle-group & equipment data, and step-by-step instructions in 6 languages. The exercise data layer behind the LogPress app.
Metacognition in LLMs: Foundations, Progress, and Opportunities
The code for paper: Decoupled Planning and Execution: A Hierarchical Reasoning Framework for Deep Search [SIGIR 2026]
Tongyi Deep Research, the Leading Open-source Deep Research Agent
Over the next month, we will implement the comprehensive paper retrieval and organization system to make this AI-Scientist agent project more concrete.
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
EurekAgent: an autonomous research system for metric-driven tasks, built with Claude Code. Define the problem and metric. Get breakthrough results.