趋势榜

掌控你的 AI。面向 AI Agent 的原生 macOS Harness——任意模型、持久记忆、自主执行、加密身份。Swift 开发，完全离线，开源。Own your AI. The native macOS harness for AI agents -- any model, persistent memory, autonomous execution, cryptographic identity. Built in Swift. Fully offline. Open source.

一套开箱即用的 Claude Code 学术模板，基于 LaTeX/Beamer + R，支持多 Agent 评审、质量门禁、对抗式 QA 与复现协议。A ready-to-fork Claude Code template for academics using LaTeX/Beamer + R. Multi-agent review, quality gates, adversarial QA, and replication protocols.

统一管理 Mac 上所有 coding-agent 会话——浏览、搜索、恢复。Rust + GPUI。Every coding-agent session on your Mac in one place — browse, search, resume. Rust + GPUI.

你的主动式个人 AI 助手与日常生产力伙伴 🌎Your proactive personal AI assistant & companion for daily productivity 🌎

Emotion Ball 是一套面向 AI 助手的表情引擎:32 种状态表情全部由纯 SVG 与原生 JavaScript 实时驱动,零框架、零图片资源。AI 侧只需输出一个 emotionId,小球即可切换到对应表情,可直接用作聊天机器人、桌面宠物、悬浮助手的情绪表达层。

Chrome 扩展：固定一个屏幕区域后，可用快捷键翻阅分页文档。OCR 通过内置 Tesseract 100% 离线运行。Chrome extension: pin a screen region once, then hotkey your way through a paginated document. OCR runs 100% offline via bundled Tesseract.

DeepSeek v4 Flash EXL3 运行于单台 DGX SparkDeepSeek v4 Flash EXL3 on one DGX Spark

coding agents 的 GUI。A GUI for your coding agents

修改版的Rikkahub，增加和优化了部分功能，将会持续更新

Mimir — 一站式科研工作台插件：LaTeX 论文边写边编译、arXiv 文献管理、实验追踪、指标图表、GPU 服务器 SSH 任务编排，管理科研全周期。An open-source research workbench plugin for the whole research cycle.

轻量级跨平台 RF 电路仿真器——DC、S-parameters、harmonic balance、loadpull/sourcepull，非 SPICE 仿真器。Lightweight cross-platform RF circuit simulator — DC, S-parameters, harmonic balance, loadpull/sourcepull. Not a SPICE simulator.

开源 FDE Agent 与企业 AI 约束层：24 条规则的 git-diff 审计、自动快照回滚、规则注入、自我进化。以 9 个 DeepSeek Harness 插件 + MCP server（66 个工具）形式交付。MIT 许可。Open-source FDE Agent & constraint layer for enterprise AI: 24-rule git-diff audit, auto snapshot rollback, rule injection, self-evolution. Ships as 9 DeepSeek Harness plugins + MCP server (66 tools). MIT.

面向 systematic review 和 evidence synthesis 的 AI 驱动全文筛选与数据提取。AI-Driven Full-Text Screening and Data Extraction for Systematic Reviews and Evidence Synthesis

一套不断壮大的 Agent Skill 家族，面向严谨、上下文感知的学术写作、同行评审与学术出版工作流。A growing family of agent skills for rigorous, context-aware academic writing, peer review, and scholarly publishing workflows.

Paper Workbench — 论文写作审查全流程工作台 / End-to-end academic writing & review workbench

巴西 UFC（联邦大学）社区化、现代化的学术 LaTeX 模板。Template LaTeX comunitário e modernizado para trabalhos acadêmicos da Universidade Federal do Ceará (UFC).

面向全国大学生数学建模竞赛（CUMCM）的 Claude Code 全流程自动化 Skills：赛题分析→建模→编程绘图→论文撰写（LaTeX/Typst）→验证验收。内置国赛论文写作模板、LaTeX 模板、模型选择库、方法知识库与 Python 实现。

dMIC60 线粒体–核 Crosstalk 论文中图表与 Table S1 的代码及源数据。Code and source data for figures and Table S1 from the dMIC60 mitochondrial–nuclear crosstalk manuscript.

复现研究结果所需的数据与代码Data and code required for reproducing the research results

一个 TypeScript LangGraph agent，通过搜索、摘要和 human approval 回答 research questions，使用 LangSmith 完整 trace 并可直接用于评估。A TypeScript LangGraph agent that answers research questions with search, summarization, and human approval – fully traced with LangSmith and ready for evaluation

文献综述 AI 工作台Literature Review AI Workbench

关于可复现 pipelines 的 capstone workshop：项目结构、环境、Make、containers 与多步 SLURM workflows。Capstone workshop on reproducible pipelines: project structure, environments, Make, containers and multi-step SLURM workflows.

与 VM 医学院联合开发的开源生物统计与临床研究工具包，为研究者提供免费的 SPSS 替代方案，支持统计分析及自动化报告生成。Open-source biostatistics and clinical research toolkit being developed with VM Medical College to provide researchers with a free SPSS alternative for statistical analysis and automated report generation.

仓库包含文章与 Excel 文件，收录系统综述《人工智能方法在实体瘤疗效评价标准中的应用》中的 CLAIM 与 FUTURE-AI 评估。Repository containing articles and Excel files with CLAIM and FUTURE-AI assessments for the systematic review Artificial intelligence approaches to the Response Evaluation Criteria in Solid Tumors: a systematic review.

基于你的 Zotero library 的个人论文推荐器。Personal paper recommender based on your Zotero library

免费开源的零代码桌面应用，用于系统综述与 Meta 分析（PRISMA 2020）。Tauri + React + C# 引擎，支持 Windows、macOS、Linux。Free, open-source, no-code desktop app for Systematic Reviews & Meta-Analyses (PRISMA 2020). Tauri + React + C# engine — Windows, macOS, Linux.

为更好的 AI 研究问题梳理清晰的来源、主张、变更与权衡路径Calm source, claim, change, and tradeoff paths for better AI research questions

research questions、evidence maps、implementations 及可复现的工程 case studies。Research questions, evidence maps, implementations, and reproducible engineering case studies.