The design language that makes your AI harness better at design.

Skill and MCP server for searching and retrieving icons

A Cursor skill that gives AI agents real UI component knowledge — best practices, layout patterns, and design-system conventions for 60+ interface components — so it generates production-grade UI i…

将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

Self-hosted, open-source agent skill registry for enterprises. Publish & version skill packages, govern with RBAC and audit logs, deploy on-premise with Docker or Kubernetes.

RAG-QA-Generator 是一个用于检索增强生成（RAG）系统的自动化知识库构建与管理工具。该工具通过读取文档数据，利用大规模语言模型生成高质量的问答对（QA对），并将这些数据插入数据库中，实现RAG系统知识库的自动化构建和管理。

把一本书蒸馏成一组可执行的 Agent Skills

社媒助手开源版 - 小红书、抖音、快手等平台数据采集的浏览器插件，可通过API调用，支持Docker部署。

Installable GitHub library of 1,500+ agentic skills for Claude Code, Cursor, Codex CLI, Gemini CLI, Antigravity, and more. Includes specialized plugins, installer CLI, bundles, workflows, and offic…

Code for P-RMF (ACL 2025): Proxy-Driven Robust Multimodal Sentiment Analysis with Incomplete Data.

A simple todolist system implemented with Spring's backend and TypeScript/React's frontend. Enjoy it.

ChatGPT 中文调教指南。各种场景使用指南。学习怎么让它听你的话。

f.k.a. Awesome ChatGPT Prompts. Share, discover, and collect prompts from the community. Free and open source — self-host for your organization with complete privacy.

⏩ Source-controlled AI checks, enforceable in CI. Powered by the open-source Continue CLI

Flexpilot IDE - Open-Source AI Native IDE

Qwen3-Coder is the code version of Qwen3, the large language model series developed by Qwen team.

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

An official implementation of "Decoupled Multimodal Distilling for Emotion Recognition" in PyTorch. (CVPR 2023 highlight)

[AAAI'25] DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis

Robust Speech Recognition via Large-Scale Weak Supervision

MCP学习： 基于 YOLO 的 AI Agent 训练项目

最容易上手的0门槛 chatglm3 & agent & langchain 项目

Finetune and Inference Qwen3-0.6B.

Agent framework and applications built upon Qwen>=3.0, featuring Function Calling, MCP, Code Interpreter, RAG, Chrome extension, etc.

model parameter identification of a dynamic two-degree-of-freedom system through Runge–Kutta-integration

Differentiable Fluid Physics Parameter Identification Via Stirring

Python library for dynamic parameter estimation

TMT: Tri-Modal Translation between Speech, Image, and Text by Processing Different Modalities as Different Languages

Easy and Efficient Finetuning LLMs. (Supported LLama, LLama2, LLama3, Qwen, Baichuan, GLM , Falcon) 大模型高效量化训练+部署.