Stars
DSPlatform系统是一个集成的解决方案，基于Thinkphp8 + Vue3 + Element Plus + Uniapp 开发，系统支持多种商业模式，包括传统商城购物、外卖配送、上门服务、上门家政、短视频带货等，满足不同行业的业务需求。无论是电商平台、本地生活服务、家政服务还是内容电商，都能快速构建完整的业务体系。
Official repo for 'Large Multimodal Models Evaluation: A Survey'
🔥 DanceOPD: On-Policy Generative Field Distillation
Agent-native LLM, RAG and Agent knowledge system with traceable Markdown, MCP tools and MkDocs.
使用 Codex 开发的剧本转可拍分镜 Skill，在 Codex 中运行效果最佳，支持 Seedance、真人/混合制作与二次开发。
Repo-native shared memory for AI coding agents.
Official implementation of Paper "Conditional cost–emission envelopes for decarbonizing dense urban power systems under spatial renewable scarcity and flexibility constraints"
技术小白也能拥有的 AI 第二大脑：无需翻墙、无需订阅，跟着图文 ~20 分钟装好 Obsidian + Claudian + cc-switch + DeepSeek V4。
Pre-submission AI review stress-test for research papers. A Claude Code skill: review, verdict, revise, verify.
The memory-first, self-improving agent harness built on EverOS, with MiroThinker-powered deep research and reasoning.
Official Implementation for the ACL 2026 paper "SARA: Selective and Adaptive Retrieval-augmented Generation with Context Compression"
Pharos — local-first agentic RAG for your team's document library: multi-format ingest, hybrid retrieval, enterprise ACL, dual HTTP + MCP exits.
Focus on Australia,US and CN Stock, just analyst
A blueprint-driven AutoResearch runtime for orchestrating AI research workflows from idea generation and experiments to paper writing and peer review.
Arabic-first generative speech recognition — Audar-ASR-V1 (Flash + Turbo). #1 on the Open Universal Arabic ASR Leaderboard. Model cards, benchmarks & inference.
Cross-platform terminal grid for running Codex, Claude, Gemini, and other CLI agents side by side.
SAfactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
Open-source, channel-native agent gateway for Slack. Route team threads to Claude Code, Codex, OpenCode, Docker, HTTP agents, and custom CLIs with policy, approvals, memory, audit logs, and artifacts.
有大致的想法不知道怎么选题？只要给这个skills扔点数据，他能自动帮你延伸出多个idea，检索文献，并帮你跑初步回归验证实证可行性和理论可行性，最后打分排名，让你的科研第一步不再难堪！
Official TestSprite CLI — AI-powered automated testing from your terminal
内置知识库 · 2.4 亿文献源 · PDF 全文翻译零配置 · 无插件网页版 app.ai4paper.pro · AI 速搜文献 · AI 一键综述 · 小程序期刊订阅 · 原生支持 Zotero 7–10 | AI4Paper.pro
AgentBench is an interactive benchmarking platform for tool-using AI agents. Connect your own agent, run practical tasks, and watch every action unfold in real time. With reproducible environments,…