数据来源:github.com/trending · 抓取时间:2026-05-19 17:16 CST 按今日新增 Stars 排序,共 12 个精选项目
项目地址: https://github.com/Imbad0202/academic-research-skills 语言: Python · 总 Stars: 13,107 描述: Academic Research Skills for Claude Code: research → write → review → revise → finalize 为 Claude Code 打造的学术研究技能包,覆盖"研究→写作→评审→修改→定稿"全流程。
项目地址: https://github.com/HKUDS/CLI-Anything 语言: Python · 总 Stars: 37,157 描述: "CLI-Anything: Making ALL Software Agent-Native" — CLI-Hub: https://clianything.cc/ 让所有软件都具备 Agent 原生能力的命令行枢纽,CLI-Hub 一站式控制台。
项目地址: https://github.com/CloakHQ/CloakBrowser 语言: Python · 总 Stars: 15,814 描述: Stealth Chromium that passes every bot detection test. Drop-in Playwright replacement with source-level fingerprint patches. 30/30 tests passed. 通过全部 30 项反爬检测的隐身 Chromium,开箱即用 Playwright 替代方案,源码级指纹修复。
项目地址: https://github.com/tech-leads-club/agent-skills 语言: TypeScript · 总 Stars: 4,239 描述: The secure, validated skill registry for professional AI coding agents. Extend Antigravity, Claude Code, Cursor, Copilot and more with absolute confidence. 面向专业 AI 编程 Agent 的安全技能注册中心,支持 Claude Code / Cursor / Copilot 等多平台扩展。
项目地址: https://github.com/microsoft/ai-agents-for-beginners 语言: Jupyter Notebook · 总 Stars: 63,807 描述: 12 Lessons to Get Started Building AI Agents 微软出品,12 节课程带你从零开始构建 AI Agent,含完整 Notebook 练习。
项目地址: https://github.com/BigBodyCobain/Shadowbroker 语言: Python · 总 Stars: 7,974 描述: Open-source intelligence for the global theater. Track everything from the corporate/private jets of the wealthy, and spy satellites, to seismic events in one unified interface. Hook an AI agent up to have it parse through data and find previously unseen correlations. 开源全球情报平台:追踪私人飞机、间谍卫星、地震事件,一键接入 AI Agent 挖掘数据关联。
项目地址: https://github.com/supertone-inc/supertonic 语言: Swift · 总 Stars: 8,561 描述: Lightning-Fast, On-Device, Multilingual TTS — running natively via ONNX. 极速端侧多语言 TTS 引擎,基于 ONNX 原生运行,无云端依赖,延迟极低。
项目地址: https://github.com/humanlayer/12-factor-agents 语言: TypeScript · 总 Stars: 20,897 描述: What are the principles we can use to build LLM-powered software that is actually good enough to put in the hands of production customers? 面向生产级 LLM 软件的 12 条核心原则,打造真正可交付客户的 Agent 系统。
项目地址: https://github.com/NVlabs/Sana 语言: Python · 总 Stars: 6,812 描述: SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer NVIDIA 出品,线性扩散 Transformer 实现高效高分辨率图像生成。
项目地址: https://github.com/tinyhumansai/openhuman 语言: — · 总 Stars: 待确认 描述: Your Personal AI super intelligence. Private, Simple and extremely powerful. 你的个人 AI 超级智能助手:私密、简洁、极其强大。
项目地址: https://github.com/K-Dense-AI/scientific-agent-skills 语言: — · 总 Stars: 待确认 描述: A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing. 即用型 Agent 技能集合,覆盖科研、工程、金融、分析及写作等场景。
项目地址: https://github.com/ruvnet/RuView 语言: — · 总 Stars: 待确认 描述: π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video. 将普通 WiFi 信号转化为实时空间智能、生命体征监测与存在检测,全程无摄像头。
本日报由 Leo 自动抓取与整理 · 2026-05-19