趋势榜

一个开源的 AI coding Agent，驻留在你的终端中。An open-source AI coding agent that lives in your terminal.

一项紧凑的 Agent Skill，用于生成高度简化、圆润且带有微妙新拟物化风格的 IP 吉祥物 Logo。A compact Agent Skill for highly simplified, rounded, subtly neo-skeuomorphic IP mascot logos.

几乎可视为 DSPy 在 TypeScript 上的"官方"框架。The pretty much "official" DSPy framework for Typescript

Agent 团队的聚集地。跨平台团队聊天工具，AI Agent 作为一等队友 — 支持云端大脑或自带大脑（Claude Code / Codex）。Where agent teams gather. Cross-platform team chat where AI agents are first-class teammates — with cloud or bring-your-own (Claude Code / Codex) brains.

LaTeX 中文排版基础设施 — ctex、xeCJK 及配套宏包（XeLaTeX / LuaLaTeX / pdfLaTeX / upLaTeX）Chinese typesetting infrastructure for LaTeX — ctex, xeCJK, and satellite packages (XeLaTeX / LuaLaTeX / pdfLaTeX / upLaTeX)

DeepSeek Harness (dsh) Windows / Linux 桌面客户端 — 内置 Node.js + dsh CLI，一键启动，10 套内置 UI 皮肤。EAC：Embracing All Creation 揽尽万象DeepSeek Harness (dsh) Windows / Linux desktop client - bundled Node.js + dsh CLI, one-click launch, 10 built-in UI skins. EAC: Embracing All Creation 揽尽万象

Jina AI 官方 Remote MCP ServerOfficial Jina AI Remote MCP Server

通过 MCP 为编码 Agent 提供开源跨 Agent 记忆层。兼容 Claude Code、Codex、Cursor、Windsurf、Gemini CLI、Antigravity、OpenClaw、Hermes Agent、Oh-my-Pi、Pi、Copilot、Kiro、OpenCode 与 Trae。Open-source cross-agent memory layer for coding agents via MCP. Compatible with Claude Code, Codex, Cursor, Windsurf, Gemini CLI, Antigravity, OpenClaw, Hermes Agent, Oh-my-Pi, Pi, Copilot, Kiro, OpenCode, and Trae.

面向 Agent 工具的 OpenRouter。社区入口：https://discord.gg/6mQYYfFMAnOpenRouter for agent tools. Join community here: https://discord.gg/6mQYYfFMAn

生产级 Go SDK，用于构建具备长期记忆、知识检索与语音能力的 AI agent，可作为库、守护进程或实时管道运行。Production-grade Go SDK for building AI agents with long-term memory, knowledge retrieval, and voice — runnable as a library, a daemon, or a real-time pipeline.

DeepSeek Harness 零代码桌面端｜一键启动，支持 Windows 与 macOS；内置插件发现、热点插件推送、一键安装与管理、AI 智能推荐和视觉增强。

GoLiveBypass — Equicord/Vencord 插件，通过在非巴西代理（Tor 或经过测试的免费代理）后启动会话来恢复巴西 Discord 用户的 Go Live 与摄像头功能。隐私与反审查工具。GoLiveBypass — Equicord/Vencord plugin that restores Go Live & camera for Brazilian Discord users by booting the session behind a non-BR proxy (Tor or tested free proxy). Privacy and anti-censorship tool.

类 GitHub 风格的 Jenkins CLI——在终端管理 context、构建运行、日志与管理员任务。GitHub-style CLI for Jenkins — manage contexts, runs, logs, and admin tasks from your terminal.

AI 驱动的漏洞自动验证平台：提交仓库与漏洞描述，在隔离沙箱中白盒审计、搭靶场复现并出具中文报告。

免费 Warhounds Trainer，支持大量 cfg 文件。自动更新，无需密钥系统。2026 年可用。Free Warhounds Trainer with support for many cfg files. Auto-updates, no key system. Works in 2026.

Find DSH plugins inside the agent — live GitHub dsh-plugin topic search, star-ranked / 会话内搜索发现 DSH 插件

为 DeepSeek Harness 提供有界、分层、需审批、可审计的跨会话记忆（能力接缝：ctx.memory + SQLite provider + memory tool + 冻结快照注入）。Bounded, layered, approval-gated, auditable cross-session memory for DeepSeek Harness (capability seam: ctx.memory + SQLite provider + memory tool + frozen snapshot injection)

DeepSeek AI 官方 DeepSeek Harness (dsh) 的独立、基于源码的 handbook：覆盖 Agent、插件、安全、故障排查与 runbook。Independent, source-backed handbook for DeepSeek AI's official DeepSeek Harness (dsh): agents, plugins, security, troubleshooting, and runbooks.

ThumbGate 预动作检查通过排序后的教训和反复失败进行自我改进，硬性阻断检测到的密钥泄露，并在严格模式下阻断匹配项。ThumbGate Pre-Action Checks self-improve from ranked lessons and repeated failures, hard-block detected secret leaks, and block matches in strict mode.

DeepSeek Harness (DSH) 插件精选目录 — 14 类 280+ 个社区插件，覆盖 MCP / Skill / TUI / 多 Agent / 上下文记忆 / UI 皮肤，点链接直达仓库。Curated directory of dsh plugins for DeepSeek Harness.

基于 Camoufox 的隐身浏览器自动化 MCP server——100+ 工具，npx 安装，反爬虫隐身MCP server for stealth browser automation via Camoufox — 100+ tools, npx install, anti-bot stealth

Obsidian 知识库的独立 MCP server — 混合搜索、笔记与文件、记忆、任务、OAuth 2.1。Standalone MCP server for Obsidian vaults — hybrid search, notes & files, memory, tasks, OAuth 2.1.

八平台全栈 AI 操作系统——通过 LangGraph + MCP + A2A 统一调度 176 个 LLM；340 表多租户 RLS、RAG 知识库、agent 市场，覆盖 Web/API/CLI/桌面/扩展/移动/小程序，Apache 2.0。Eight-platform full-stack AI operating system - unifies 176 LLMs via LangGraph + MCP + A2A. Multi-tenant RLS over 340 tables, RAG knowledge base, agent marketplace. Web/API/CLI/Desktop/Extension/Mobile/Miniapp. Apache 2.0.

强化的纯本地 LiteLLM 网关——自动发现 15+ 提供商的免费/试用 LLM 模型（OpenRouter、Groq、Gemini、Cerebras、NVIDIA NIM、SambaNova、Cohere、GitHub Models 等），统一 OpenAI 兼容端点 127.0.0.1:4000，为 AI coding agent 提供基于角色的别名。Hardened local-only LiteLLM gateway — auto-discovers free/trial LLM models from 15+ providers (OpenRouter, Groq, Gemini, Cerebras, NVIDIA NIM, SambaNova, Cohere, GitHub Models, etc.). Single OpenAI-compatible endpoint at 127.0.0.1:4000. Role-based aliases for AI coding agents.

以孟加拉语优先、面向方言的 LLM 研究。开源孟加拉语 tokenizer，性能优于 Sarvam、AI4Bharat 和 GPT-4o（fertility 1.52，几乎零破损 conjuncts）。非商用，保护孟加拉语及其方言。Bengali-first, dialect-aware LLM research. Open-source Bengali tokenizer that outperforms Sarvam, AI4Bharat, and GPT-4o (fertility 1.52, near-zero broken conjuncts). Non-commercial, preserving Bengali and its dialects.

AI 驱动的初创公司情报 Agent——手写 ReAct 循环、并行工具执行、实时联网搜索以及 RAG 增强的文档分析。不依赖任何框架，具备完整理解能力。AI-powered startup intelligence agent — hand-built ReAct loop, parallel tool execution, live web search, and RAG-grounded document analysis. No frameworks. Full understanding.

CloserAI — 基于 DeepSeek Harness 构建的本地优先、模型无关、权限透明的桌面 AI 工作台。CloserAI - a local-first, model-agnostic, permission-transparent desktop AI workbench built on DeepSeek Harness.

免费、本地优先、按章节编排的 LLM、向量数据库、RAG 与 Agent 课程——从零到你的首个 AI agent。Free, local-first, chapter-wise curriculum for LLMs, Vector DBs, RAG & Agents — from zero to your first AI agent.

Keel 将编码 Agent 转变为工作 owner：项目中立的 issue-to-done 工作流骨干。Keel turns coding agents into work owners: a project-neutral issue-to-done workflow backbone.

基于 Zotero 的文献综述助手，支持基于原文的 PDF 抽取、声明验证、内容综合及 Semantic Scholar 检索Zotero-based literature review assistant for grounded PDF extraction, claim verification, synthesis, and Semantic Scholar search.

金融与生活交易学习 RAG 与 QuantConnect LEAN 回测工作流（FastAPI、Qdrant、pgvector、Docker）。금융·생활거래 학습 RAG와 QuantConnect LEAN 백테스트 워크플로우 (FastAPI, Qdrant, pgvector, Docker)

一套配置、一组凭证、一个 MCP 端点——由 Claude Code、Cursor、Codex 等 10 余个客户端共享。Local-first，零遥测。One config, one credential set, one MCP endpoint — shared by Claude Code, Cursor, Codex and 9 more. Local-first, zero telemetry.

可复现研究代码：检验足球预测优势是否依赖于博彩公司去水方法。Reproducible research code testing whether football forecasting edges depend on bookmaker de-margining methods.

infinite token glitch——让 ChatGPT 在真实机器上调用 Codex 工具的 MCP serverinfinite token glitch - mcp server for chatgpt to use codex tools on a real machine

作者感知的科学写作分析：作者空间、目标论文风格、校准的生成证据，以及安全合规的修订Authorship-aware scientific writing analysis: author space, target-paper style, calibrated generation evidence, and integrity-safe revision.

让研究资源更易于查找、复用与共享，记录可复现研究的资产。（镜像）Making research resources easy to find, reuse, and share, documenting assets for reproducible research. (Mirror)

拥有超能力的 Github。Github with super powers

CorePapers - 面向留学生的 AI 学术写作助手CorePapers - AI Academic Writing Assistant for International Students

Ultimate AI Spellbook Workflows 2026 – 构建多平台 Skill 与自动化Ultimate AI Spellbook Workflows 2026 – Build Multi-Platform Skills & Automation

FastMCP 3.2 语音 gateway：FunASR 本地 STT、Gemini Live/TTS、Hume、ElevenLabs 声音克隆、唤醒词、RAG。MCP server + React webapp。FastMCP 3.2 speech gateway: FunASR local STT, Gemini Live/TTS, Hume, ElevenLabs cloning, wake word, RAG. MCP server + React webapp.

韩国加密货币 × AI 垂直媒体与社区——alpha.moss.land：频道立场、AI 简报、RAG、8 个带业绩记录的 AI persona、12 工具 MCP server。Korean crypto × AI vertical media + community — alpha.moss.land. Channel stance, AI briefs, RAG, 8 AI personas with track records, 12-tool MCP server.

Claude Code 与 Codex 的中央插件市场Central plugin marketplace for Claude Code and Codex

Rust CLI、MCP server 和 Claude Code 插件，用于个人考勤、工资条、薪资及 Hilan 账户相关自助任务。Rust CLI, MCP server, and Claude Code plugin for personal attendance, payslips, salary, and related self-service tasks on your own Hilan account.

插件化形态的 14-Agent 软件公司：在硬性预算上限内规划、构建并对每次变更进行对抗式评审。Markdown + POSIX shell，零运行时依赖。A 14-agent software company in a plugin: plan, build, and adversarially judge every change under hard budget caps. Markdown + POSIX shell, zero runtime deps.

自构建的 AI Agent 框架——多模型 ReAct + 分层缓存友好的上下文 + 异步多 Agent + XML 工作流。CLI 与 WebUI，零 LangChain。An AI agent framework that builds itself — multi-model ReAct + tiered cache-friendly context + async multi-agent + XML workflows. CLI & WebUI, zero LangChain.

2026 终极 AI Coding Agent 连续性工具包——无缝交接与同步。Ultimate AI Coding Agent Continuity Toolkit 2026 - Seamless Handoff & Sync

在同一 chunk 集合上对比 Lexical / Vector / Graph RAG，提供确定性评估、自我修正的 LangGraph agent 循环、PII 治理与 RAG 就绪度分析器。Lexical vs Vector vs Graph RAG over one identical chunk set, with deterministic evaluation, a self-correcting LangGraph agent loop, PII governance, and a RAG-readiness analyzer.

将 GitHub Copilot CLI 转变为资深队友的 CLI + TUI：安装精选的 skill 目录、自定义 Agent、教学人格、跨会话记忆，以及原生 Spec-Driven Development 引擎。纯 Go 实现，内部不含 LLM；capiko 负责指挥，Copilot 负责执行。CLI + TUI that turns the GitHub Copilot CLI into a senior teammate: installs a curated catalog of skills, custom agents, a teaching persona, cross-session memory, and a native Spec-Driven Development engine. Pure Go — no LLM inside; capiko directs, Copilot executes.

12 个写作 skill—— SEO 博客、邮件营销、销售文案、学术写作。12 writing skills - SEO blog, email marketing, sales copy, academic writing.

12 项研究 AI Skills —— LaTeX 论文、统计分析、文献综述、会议投稿12 research AI skills - LaTeX papers, statistical analysis, literature review, conference submission.

找出你的转换器在 .docx 中悄悄丢弃的内容——命名空间、表格、图片与字体在大多数情况下看起来正常，直到真正出问题。零依赖。Find what your converter silently dropped from a .docx - namespace, table, figure and font failures that render fine until they do not. Zero dependencies.

Spectre AI 2026：新一代 OSINT 引擎与自主图谱消歧工具包。Spectre AI 2026: Next-Gen OSINT Engine & Autonomous Graph Disambiguation Toolkit

面向 AI coding agent 的终端多路复用器：一个键盘驾驶舱管控整支集群，配备工作项、任务队列与单面板资源上限。A terminal multiplexer for AI coding agents: one keyboard cockpit for the whole fleet, with work items, a task queue, and per-panel resource caps.

确定性 SAT API、CNF 预处理工具与可复现研究标准。Deterministic SAT APIs, CNF preprocessing tools, and reproducible research standards.

针对气候灾害与心理健康系统综述的文献检索（PubMed、Scopus）Bibliographic retrievals (PubMed, Scopus) for a systematic review of climate hazards and mental health

本仓库为我们论文 SPR-SMN：Scientific paper recommendation employing SPECTER with memory network 的代码This repository is for the code of our paper SPR-SMN: Scientific paper recommendation employing SPECTER with memory network

Embodied Daily：每日具身智能 AI 论文推荐（HF Daily Papers + arXiv）Embodied Daily: daily embodied-AI paper recommendations (HF Daily Papers + arXiv)

一项系统动力学研究，探讨 fractional ownership 与 AI 赋能的点对点交易如何在向租房者和低收入家庭开放参与的同时提升可再生能源利用率。基于 25 项研究的系统综述，在 Stella 中构建因果回路模型，并针对新西兰市场监管进行对比设计方案评估a system dynamics study of how fractional ownership and AI-enabled peer-to-peer trading could raise renewable utilisation while opening participation to renters and low-income households. Systematic review of 25 studies, causal loop modelling in Stella, and a comparative design assessment against NZ market regulation.

AI 增强的 IT 运维工作台——规格驱动、多提供商、本地优先，将事件与服务请求转为带 KB 引用的摘要，配备可审计会话、PII 脱敏与沙箱化操作。AI-augmented IT ops workbench — spec-driven, multi-provider, local-first. Turns incidents and service requests into KB-cited summaries with auditable sessions, PII redaction, and sandboxed actions.

通过系统综述和患者病例场景分析识别潜在药物不良反应（ADR），包括对症状、用药史、剂量及时间线的评估，以确定可疑药物并判断所报告反应是否可能与药物相关。项目展示了基础的 Pharmacovigilance 能力identifying potential Adverse Drug Reactions through systematic review and analysis of patient case scenarios. It includes evaluation of symptoms, medication history, dosage, and timelines to determine the suspected drug and assess whether the reported reaction is potentially drug-related. The project demonstrates basic Pharmacovigilance

个人简介：可信 AI、可复现研究、开发者工具。Profile overview: trustworthy AI, reproducible research, and developer tools.

针对本地 stdio MCP server 配置的静态诊断工具。Static diagnostics for local stdio MCP server configurations

企业知识智能平台：基于权限感知的搜索、助手与 agent，覆盖公司现有工具栈。Enterprise knowledge intelligence platform. Permission aware search, assistant and agents over the tools a company already runs.

一个为 Model Context Protocol 提供策略执行能力的 gateway。聚合 MCP server，强制工具调用策略，扫描结果中的 prompt injection 与凭证泄露，并审计一切。Rust 实现。A policy-enforcing gateway for the Model Context Protocol. Aggregates MCP servers, enforces tool-call policy, scans results for prompt injection and leaked credentials, and audits everything. Rust.

针对个性化新抗原癌症疫苗与肿瘤特异性 T 细胞应答的独立结构化文献综述Independent structured literature review of personalized neoantigen cancer vaccines and tumor-specific T-cell responses.

一款面向学生的友好界面应用，用于介绍 Diana Ridley（2012）的文献综述方法（SQ3R），并融入适用于社会科学学生的 SPIDER 方法，辅助学生主动完成文献标注与综述写作This app is a student friendly interface to introduce Diana Ridley's (2012) method of literature review (SQ3R) and incorporating 'SPIDER' method for students of Social Science. This is an assistive application for students to actively annotate and write review of literature.

SLR Harvester Web 是一个面向 Scopus、PubMed 和 OpenAlex 系统综述的浏览器仪表盘，可持久化记录检索策略、标签与筛选决策，实现完整方法学透明性；注册后可跨设备同步项目，也支持本地文件夹离线使用SLR Harvester Web is a browser-based dashboard for Scopus, PubMed and OpenAlex systematic literature reviews. It persistently logs search strategies, tags, and screening decisions for full methodological transparency. Sign up to sync projects across devices, or work offline with a local folder.

MeterSphere v2.10 个人开发分支 — 一站式开源持续测试平台。工作流引擎(Flowable 7) · 需求池(从0到1) · 微前端(qiankun→micro-app) · AI知识库 · 测试跟踪，含个人笔记与创意项目。

一个用于研究入侵检测系统 (IDS) 在时间分布漂移下何时应进行适应的可复现研究框架。该项目评估了一个分阶段决策流水线，结合漂移筛查、新颖性检测与成本感知的适应触发器，以判断重训练是否必要且有益。A reproducible research framework for investigating when an Intrusion Detection System (IDS) should adapt under temporal distribution shift. The project evaluates a staged decision pipeline combining drift screening, novelty detection, and cost-aware adaptation triggers to determine whether retraining is necessary and beneficial.

JassWiki - 数字 Jass 百科全书。JassWiki - Die digitale Jass-Enzyklopädie

可复现研究：基于基准、统计模型与走步前向验证，检验可解释的市场信号能否预测 SPY 的五日方向。Reproducible research testing whether interpretable market signals can forecast SPY’s five-day direction using benchmarks, statistical models, and walk-forward validation.

用于构建高质量医美研究问题的 Codex SkillCodex skill for developing strong medical aesthetic research questions

受治理的持久化 AI worker，配备默认拒绝权限、人工审批、dry-run 以及经过认证的 MCP。Governed persistent AI workers with default-deny authority, human approvals, dry-runs, and an authenticated MCP.

基于 PRISMA 2020 的 LLM 微调技术系统综述（2020–2025）— 84 项研究，涵盖 LoRA/QLoRA/RLHF/DPO，本科毕业论文（PUCE）。PRISMA 2020 systematic review of LLM fine-tuning techniques (2020-2025) - 84 studies, LoRA/QLoRA/RLHF/DPO, undergraduate thesis (PUCE).

FraudBench-Hybrid 是一个面向时序银行欺诈检测的可复现研究框架，仓库包含数据集配置、防数据泄露的 Heavy Hybrid 集成实现、实验评估、结果、可视化分析及未来研究扩展资料FraudBench-Hybrid is a reproducible research-based framework developed for temporal bank fraud detection. This repository will include dataset configuration, leakage-controlled Heavy Hybrid ensemble implementation, experimental evaluation, results, visual analysis, and material for future research extensions.

系统综述systematic reviews

文献综述站点Literature review site

将 Claude 连接至 Overleaf 的 MCP server，可在免费层读取、编辑、编译与恢复 LaTeX 项目。MCP server that connects Claude to Overleaf. Read, edit, compile and restore LaTeX projects on the free tier.

用于规范化文献综述循环工作流的本地 Codex SkillLocal Codex skill for a disciplined literature-review loop workflow.

基于 Zotero 的 Claude Code Skills 研究：PDF 高亮挖掘、主题编码、稿件评审与系统综述审计Claude Code skills for Zotero-based research: PDF highlight mining, thematic coding, draft review, and systematic review auditing

用于系统综述与 Meta 分析的可编辑学术 HTML 演示Editable academic HTML presentation for systematic review and meta-analysis

CodeByte 黑客松团队仓库 —— [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:codebyte]。Hackathon team repository for CodeByte - [hackindia-team:ai-first-startup-hackathon-build-a-startup-using-ai-only:codebyte]

OptiBuild 工程案例研究——一款 AI 驱动的施工现场管理平台：工程量清单解析、成本核算、进度报告与按角色划分的数据权限。Engineering case study of OptiBuild, an AI-enabled construction-site management platform: quantity-survey parsing, costing, work-progress statements and role-scoped data.

Mielepiù 工程案例研究——一款 B2B 销售平台，其 AI Agent 基于真实数据作答并给出引用来源。Engineering case study of Mielepiù, a B2B sales platform whose AI agent answers on real data and cites its sources.

AI 工程师与全栈开发者——从架构到生产，独立设计并交付完整的 AI-native 与全栈系统。AI Engineer & Full-Stack Developer — I design and ship complete AI-native and full-stack systems, from architecture to production.

Athleta 工程案例研究——一款 AI 健身产品，采用每用户一个知识图谱的设计，由 Agent 提议、用户确认。Engineering case study of Athleta, an AI fitness product with a per-user knowledge graph where the agent proposes and the user confirms.

命令行本地优先的单用户通用 Agent。Local-first, single-user general agent for the command line.

活文献综述：面向网络安全领域的现代数据架构Living literature review: Modern data architecture for cybersecurity

HCIFlow 是一个 HCI 研究平台，将以单一流水线替代 Gorilla/Qualtrics/Prolific/SPSS 工具链：研究设计、协作、数据采集以及 AI 生成的结果与统计分析（卡方、Mann-Whitney U、Kruskal-Wallis）。基于 Next.js 14、Tailwind、Supabase 和 Claude API 构建。HCIFlow is an HCI research platform that will replaces the Gorilla/Qualtrics/Prolific/SPSS toolchain with a single pipeline: study design, collaboration, data collection, and AI-generated result and statistical analysis (chi-square, Mann-Whitney U, Kruskal-Wallis). Built with Next.js 14, Tailwind, Supabase, and the Claude API.

Wenshu（文枢）— 面向人文社科研究的 AI 知识处理工作流：本地知识库 / RAG / 中文引文 / 理论谱系。AI knowledge workflow for humanities & social sciences: local knowledge base, RAG, citation (GB/T 7714), knowledge graph.

面向印度诊所的多语言医疗分诊助手—— LangChain + Groq Agent，基于 WHO 症状指南与 ICD-11 的 FAISS RAG，支持英语/印地语/卡纳达语的 Whisper 语音输入，FastAPI + PostgreSQL 后端。提供在线 demo。Multilingual medical triage assistant for Indian clinics — LangChain + Groq agent, FAISS RAG over WHO symptom guides and ICD-11, Whisper voice input in English/Hindi/Kannada, FastAPI + PostgreSQL backend. Live demo.

基于 Whisper、Gemini、Streamlit、yt-dlp 与 FFmpeg 构建的 AI 应用，可即时转录并总结任意 YouTube 视频。Transcribe and summarize any YouTube video instantly with AI-powered app using Whisper, Gemini, Streamlit, yt-dlp & FFmpeg.

基于 AgentTeams 构建的、有证据支撑的 AI 软件工程团队。An evidence-backed AI software engineering team built on AgentTeams.

关于细菌抗生素耐药程度标准化定义使用的系统综述与建议A systematic review and recommendations on the use of standard definitions for extent of antibiotic resistance in bacteria

系统综述的主动学习摘要筛选。在全部 26 个 SYNERGY 数据集上基准测试：WSS@95 均值 64.1。Active-learning abstract screening for systematic reviews. Benchmarked across all 26 SYNERGY datasets: mean WSS@95 of 64.1.

基于仿真的 MRI 调度策略分析，结合统计分析与离散事件仿真，以优化资源利用率、等待时间、加班时长与患者吞吐量。Simulation-based analysis of MRI scheduling policies, combining statistical analysis and discrete-event simulation to optimize resource utilization, waiting times, overtime, and patient throughput.

iNPH 诊疗路径中分母特异性转归的系统综述与 Meta 分析的数据、代码与审计追踪（PROSPERO CRD420261458736）Data, code, and audit trail for the systematic review and meta-analysis of denominator-specific transitions in the iNPH care pathway (PROSPERO CRD420261458736)

面向 OCR 历史文献的小型可复现预处理流水线，保留页码映射以实现透明搜索与导出。A small, reproducible preprocessing pipeline for OCR-based historical sources, retaining page mappings for transparent search and export.

NexaCrew（作者 Sin Chi Chiu / MAP Studio USA）—— AI-native、自托管的企业运营平台：ERP、POS、库存（IMS）、仓储（WMS）、HR、考勤、访客管理与门禁均由聊天 prompt 驱动。ISO 级记录、人脸识别 kiosk、station/kiosk 模式、自定义 SOP 构建器、车队更新。NexaCrew by Sin Chi Chiu / MAP Studio USA - AI-native, self-hosted Enterprise Operations Platform: ERP, POS, Inventory (IMS), Warehouse (WMS), HR, time-clock, visitor management and access control driven by chat prompts. ISO-grade records, face-recognition kiosks, station/kiosk modes, custom SOP builder, fleet updates.

SwipeTA 背后关于图表识别、市场模式与噪声反馈的可复现研究Reproducible research on chart-reading, market patterns, and noisy feedback behind SwipeTA.

使用纯 C99 MoE 推理引擎在 CPU 上原生运行 DeepSeek-V4-Flash-0731，无需 GPU、CUDA 或 PyTorch。Run native DeepSeek-V4-Flash-0731 on CPU with a pure C99 MoE inference engine — no GPU, CUDA, or PyTorch needed.

为 LLM 记忆而构建。Built for LLMs memory

我的个人简历。My own Resume

PaperMind 是一个 AI 驱动的研究助手，可帮助用户撰写科研论文、开展文献综述、识别现有研究空白，运用多种机器学习模型与自然语言处理技术为用户提供洞察与建议The PaperMind project is an AI-powered research assistant that helps users in generating research papers, conducting literature reviews, and identifying gaps in existing research. It uses various machine learning models and natural language processing techniques to provide insights and suggestions to the users.

RIFT — Race-state Inference From Telemetry。一项可复现研究实现，仅基于位置遥测重建具备事件感知的关联性比赛状态，涵盖路线进度、共享事件标识、检查点通过、物理顺序、前车关系、间距与间隔。RIFT — Race-state Inference From Telemetry. A reproducible research implementation for reconstructing occurrence-aware relational race state from positional telemetry alone, including route progress, shared occurrence identity, checkpoint crossings, physical order, car-ahead relations, gaps and intervals.

一项系统性文献综述A systematic literature review

目标：将 State Space Models（SSM）/ Mamba 用于医学时间序列分析；总体研究问题：Mamba 模型能否提升基于步态信号检测帕金森病的分类模型性能: To use State Space Models (SSM)/ Mamba for medical time series analysis General research question: Can Mamba models improve the performance of classification models trained to detect Parkinson's disease using gait signals.

RepoMap AI 2026：为 AI 助手绘制突破窗口限制的代码库地图RepoMap AI 2026: Map Codebases for AI Assistants Beyond Window Limits