仓库/Skill 库

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

面向 AI Agent 调试 Android React Native/Expo 应用的本地运行时可观测性桥接层——以证据为先：截图、UI 树、逐请求网络数据、FPS、React 渲染、CDP console/heap/profile、确定性诊断、前后对比。Local runtime observability bridge for AI agents debugging React Native/Expo apps on Android — evidence-first: screenshots, UI trees, per-request network, FPS, React renders, CDP console/heap/profile, deterministic diagnosis, before/after compare.

跨机器运行的 AI Agent 邮件系统。mail for AI agents across machines

探索用于测试 ML、LLM 和 Agentic AI 系统的 AI 安全工具、论文与框架Explore AI security tools, papers, and frameworks for testing ML, LLM, and agentic AI systems

🚀 使用强化学习优化半精度通用矩阵乘法（HGEMM）CUDA kernel，性能超越 cuBLAS 及其他基准。🚀 Optimize Half-precision General Matrix Multiply (HGEMM) CUDA kernels using reinforcement learning, surpassing cuBLAS and other benchmarks with superior performance.

🍀 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.

为 AI agent 搭建团队知识仓库——集中领域知识、工作流与规范，供 agent 消费、基于其开发，并通过 PR 循环持续保鲜。Scaffold team knowledge repos for AI agents — centralize domain knowledge, workflows, and specs that agents can consume, develop with, and keep fresh via PR loops.

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.

基于 Hermes 的原生 AI 工作台，通过专业 Agent 与 Skill 完成经人工审核的精炼工作。A Hermes-native AI workshop for crafted, human-approved work through specialist agents and skills.

PostgreSQL MCP 2026：面向开发者的最佳 AI 数据库访问工具PostgreSQL MCP 2026 Best AI Database Access Tool for Developers

Islam West Africa Collection 的 RDF 词汇表：面向 Omeka S 的 AI 处理溯源与按模型键控的情感标注属性RDF vocabulary for the Islam West Africa Collection: AI processing provenance and model-keyed sentiment annotation properties for Omeka S

对伊斯兰西非文献集（IWAC）语料库情感分析的交互式可视化，对比 ChatGPT、Gemini 与 Mistral，支持多语言与高级筛选。Interactive visualization of sentiment analysis on the Islam West Africa Collection (IWAC) corpus, comparing ChatGPT, Gemini, and Mistral with multilingual support and advanced filtering.

自主规约驱动的开发，通过确定性工程循环编排隔离的 Oh My Pi 编程 Agent。Autonomous spec-driven development, orchestrating isolated Oh My Pi coding agents through deterministic engineering loops.

IntentCoding 官方实现：放大代码生成中的用户意图（ACL 2026）Official implementation of IntentCoding: Amplifying User Intent in Code Generation (ACL 2026)

使用 vision-language model 处理视觉与文本数据，执行多模态推理与图像理解任务。Process visual and textual data with this vision-language model for multimodal reasoning and image understanding tasks.

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.

通过硬件 IP 核在硅层级抑制 LLM 幻觉，强制 LLM 输出的语义完整性Enforce semantic integrity in LLM outputs with a hardware IP core that suppresses hallucinations at the silicon level

截至 2026-08-10 的投机解码研究知识库：66 篇核心论文全文精读、方法谱系、系统比较与研究空白

MCU 串行调试桥：过滤视图、图表、标记、Web UI，以及面向 AI Agent 的 CLI。Serial debug bridge for MCUs: filtered views, graphs, markers, web UI, and a CLI for AI agents

在 Oracle Cloud Infrastructure (OCI) 上部署 Odoo，并集成 Agentic AI 工作流与自动化Odoo deployment on Oracle Cloud Infrastructure (OCI) integrated with Agentic AI workflows and automation.

Agent 优先、安全优先的工具包，用于开发和定制 reMarkable Paper Pure 平板。Agent-first, security-conscious toolkit for developing and customizing reMarkable Paper Pure tablets

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.

面向可靠 AI 辅助工作的、人主导、模型无关的操作系统契约与 Markdown 模板。Human-controlled, model-agnostic operating contracts and Markdown templates for reliable AI-assisted work.

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.

即时评估课程资格，输出明确的通过/未通过结果以及定制化的入学测试。Instantly evaluate course eligibility with clear pass/fail results and tailored entry assessments.

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.

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)

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.

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

基于 git 构建的可治理 multi-agent 框架。A governed multi-agent framework built on git

AI 编程 Agent 会话知识的无损压缩——先症状分诊、持久化捕获、冷启动验证Lossless compaction of session knowledge for AI coding agents — symptom-first triage, durable capture, cold-start verification

为 coding agent 提供并行、隔离的本地环境——基于 git worktree + 容器，每个 bay 拥有独立端口、hostname 和数据库，可通过 CLI 或 MCP 驱动。Parallel, isolated local environments for coding agents — git worktree + containers + per-bay ports, hostname and database, driven by CLI or MCP.