仓库/Skill 库

为仿制药临床法规事务团队打造的法规准备加速器。A regulatory prep accelerator for a generic-drug Clinical Regulatory Affairs team.

证据优先的科研桌面工具，支持论文发现、PDF 证据抽取、论点分析、对比与文献综述综合Evidence-first research desk for paper discovery, PDF evidence extraction, claim analysis, comparison, and literature review synthesis.

自托管共享记忆，面向 AI Agent 团队。支持房间（Rooms）、L0-L3 层级深度与 MCP；读取路径不调用任何语言模型。基于 vectorize-io/hindsight（MIT）的 fork。Self-hosted shared memory for a team of AI agents. Rooms, hierarchical L0-L3 depth, MCP. The read path never invokes a language model. Fork of vectorize-io/hindsight (MIT).

Conversational academic writing Copilot: LangGraph ReAct agent with citation tracing, faithfulness reviewer, RAG & Reflexion LaTeX self-repair ｜ 对话式学术写作 Copilot：LangGraph ReAct 智能体，引用溯源 + 忠实度审校 + RAG 检索 + Reflexion 编译自修复，端到端产出真实 PDF

LLM 的知识截止会使文献综述过时或不完整；RAG 与时序感知检索可提升时效性，但无法完全解决引用、来源选择与时间推理问题。LLM knowledge cutoffs can make literature reviews outdated or incomplete, while RAG and time-aware retrieval can improve freshness but do not fully solve citation, source-selection, and temporal reasoning problems.

面向发表的 Skill，面向务实型工程研究实验与学术写作。A publication-oriented skill for pragmatic engineering research experiments and academic writing.

保留图表的转换器 —— DOCX/XLSX 转 Markdown，采用原生 OOXML 图表数据提取（无需光栅化/OCR/VLM），并提供零损耗的复合图表标记。Converters where figures survive — DOCX/XLSX to Markdown with native OOXML chart-data extraction (no rasterize/OCR/VLM) and zero-loss composite-figure markers

集成 RAG、知识图谱、语义搜索、论文推荐与本地 LLMs 的 AI 研究助手AI Research Assistant with RAG, knowledge graphs, semantic search, paper recommendations, and local LLMs.

基于 Next.js、FastAPI 和 Supabase 的 AI 辅导应用。上传 PDF 与 URL，即可生成结构化摘要、多轮对话和自定义测验。自定义主题通过 Wikipedia、ArXiv 和 DuckDuckGo 进行联网搜索，以生成测验并围绕主题展开对话。Next.js AI tutor with FastAPI and Supabase. Upload PDFs and URLs to generate structured summaries, multi-session chat, and custom quizzes. Custom topics use web search through Wikipedia, ArXiv, and DuckDuckGo to generate quizzes and chat about the topic.

面向 LLM agent 的 MCP server，用于加拿大调整后成本基础（ACB）与资本利得：支持平均成本法与 superficial-loss 检测。MCP server for Canadian adjusted cost base (ACB) and capital gains: average-cost, superficial-loss detection, for LLM agents.

面向多源检索、证据抽取与带引用研究摘要的自主 AI 研究助手。Autonomous AI research assistant for multi-source retrieval, evidence extraction, and cited research summaries.

本地优先的研究论文工作空间与可视化 AI Agent 工作流构建器Local-first research paper workspace and visual AI agent workflow builder

🍀 OpsRAG 是基于 RAG 的技术事故调查助手，帮助 DevOps 工程师、SRE、云工程师与平台工程师排查基础设施、应用与分布式服务问题🍀 OpsRAG is a technical incident investigation assistant based on Retrieval-Augmented Generation, designed to help DevOps engineers, SREs, Cloud Engineers, and Platform Engineers investigate problems in infrastructure, applications, and distributed services.

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.

开源数字全息显微镜（DHM）工作站：离轴全息重建、定量相位成像、自动对焦，以及基于经典 + CNN 混合管线的无参考相位检索。PySide6 GUI，可选 Apple Silicon MLX 加速，并提供面向 AI Agent 的 MCP server。Open-source digital holographic microscopy (DHM) workstation: off-axis hologram reconstruction, quantitative phase imaging, autofocus, and reference-free phase retrieval via a hybrid classical + CNN pipeline. PySide6 GUI, optional Apple Silicon MLX acceleration, and an MCP server for AI agents.

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.

The Triplicate：数据驱动的大幅面报纸排版引擎 —— docxology/template 可复现研究范式的公开范例（测试覆盖率 ≥90%，无 mock，GitHub 与 Zenodo 10.5281/zenodo.20533675 双重发布）。The Triplicate: a data-driven large-format newspaper layout engine — public exemplar of the docxology/template reproducible-research paradigm (≥90% test coverage, no mocks, double-published GitHub + Zenodo 10.5281/zenodo.20533675).

Python 包，作为可复现的科学刺激生成视觉、听觉和视听错觉 —— 17 个已编目错觉导出为 PNG、WAV、GIF、MP4 和 NPZ，附带 SHA-256 清单与确定性随机种子，含 15 个附带源数据边车的发表级图表，测试覆盖率 90% 以上Python package that generates optical, auditory and audio-visual illusions as reproducible scientific stimuli — 17 catalogued illusions exported to PNG, WAV, GIF, MP4 and NPZ with SHA-256 manifests, deterministic seeds, 15 publication figures with source-data sidecars, and 90%+ test coverage.

语言 case 的范畴论处理，集成 Active Inference 与 CEREBRUM 架构：DisCoPy 弦图横跨类型学、范畴语法、拓扑斯理论及量子扩展，生成 30 个发表级图表与一篇 24 节的手稿。1,207 个测试，覆盖率 95.96%，零 mockCategory-theoretic treatment of linguistic case integrated with Active Inference and the CEREBRUM architecture: DisCoPy string diagrams spanning typology, categorial grammar, topos theory, and quantum extensions, generating 30 publication figures and a 24-section manuscript. 1,207 tests, 95.96% coverage, zero mocks.

面向 Text-to-Motion、Physics RL 与 Pose Estimation 文献综述的自动化多 Agent 研究框架，抓取 ArXiv 论文并去重，通过 LLM 子 Agent 抽取结构化指标，自动下载 PDF 以供 RAG/NotebookLM 摄取。Automated multi-agent research framework for academic literature reviews on Text-to-Motion, Physics RL, and Pose Estimation. Fetches ArXiv papers, deduplicates, extracts structured metrics via LLM sub-agents, and auto-downloads PDFs for RAG/NotebookLM ingestion.

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.

纯 Go 实现的分布式列式 SQL 分析引擎——对 S3 上 Parquet 进行向量化执行，无需 JVM、无需 CGo。以 Trino 级别的能力提供相当性能，却只需极小资源占用。原生支持 IPv4/CIDR/MAC 等网络类型，适用于遥测和安全场景。Distributed columnar SQL analytics engine in pure Go — vectorized execution over Parquet on S3, no JVM, no CGo. Trino-class performance on a fraction of the footprint. Network-native IPv4/CIDR/MAC types for telemetry and security workloads.

Agentic RAG：回答前对每条引用与原文进行核对，证据不足时弃答。具备自纠正检索循环、确定性引用锚定以及 prompt injection 防御能力。Agentic RAG that verifies every citation against source text before answering, and abstains when the evidence does not hold. Self-correcting retrieval loop, deterministic citation grounding, prompt-injection defence.

FinVet v1 —— 用于金融虚假信息检测的 RAG 与外部事实核查（IEEE BigData 2025 workshop）。已被 danielberhane/finvet 取代。FinVet v1 — RAG and external fact-checking for financial misinformation detection (IEEE BigData 2025 workshop). Superseded by danielberhane/finvet

RAMR —— 检索增强记忆可靠性：面向 Agentic-RAG / 记忆系统的抗污染合成基准（附方法与发现）。RAMR — Retrieval-Augmented Memory Reliability: a contamination-resistant synthetic benchmark for agentic-RAG / memory systems (findings + method)

将学术论文（JATS、Grobid TEI、arXiv HTML、出版商 HTML、PDF）解析为统一的文档模型与 Markdown。Parse scholarly papers — JATS, Grobid TEI, arXiv HTML, publisher HTML, PDF — into one document model and Markdown.

面向 20–30 岁高血压与糖尿病高风险人群的 AI 医疗 — 教练关联的饮食与运动指导平台AI healthcare for 20–30s at risk of hypertension & diabetes — Trainer-Linked Diet & Exercise Coaching Platform

将研究压缩包转化为可搜索、可引用的素材。拆分为论文、代码与数据集，索引后即可提出 Deep Research 问题，并引用页码与源行。Self-hosted（Postgres、MinIO、Qdrant）。Turn research zips into searchable, citable materials. Split papers, code, and datasets; index them; ask Deep Research questions that cite pages and source lines. Self-hosted (Postgres, MinIO, Qdrant).

全球研究者的终极 AI 驱动发现平台。统一搜索 8+ 专业数据库（NCBI、arXiv、OpenAlex），结合 Llama 3.1 驱动的综合分析、RAG 问答与自动化文献综述。The ultimate AI-powered discovery hub for global researchers. Unified search across 8+ specialized portals (NCBI, arXiv, OpenAlex) with Llama 3.1-driven synthesis, RAG chat, and automated literature reviews.

Syx 是一个面向长周期项目与编码 Agent 的实验性本地 AI 记忆系统，探索主动上下文、日记忆滚动回收、睡眠式记忆整合、长期 RAG 检索、类梦境综合以及 markdown 记忆制品Syx is an experimental local AI memory system for long-running projects and coding agents. It explores active context, daily memory rolloff, sleep consolidation, long-term RAG retrieval, dream-like synthesis, and markdown memory artifacts.

钥石复盘：面向魔兽世界大秘境玩家的 AI 复盘教练（战术意图理解 + 社区知识库 RAG）

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 LangGraph、Ollama 与 RAG 的可追溯多智能体医疗辅助分诊系统