仓库/Skill 库

通过一次 wrap() 调用为 LLM 流水线构建运行时可靠性守卫，可配置地防御常见生产故障Build runtime reliability guards for LLM pipelines with one wrap() call and configurable protection against common production failures

RAG 真的物有所值吗？ragornot 在真实 AWS Lambda + Bedrock 后端上，通过四种检索模式（Flat/BM25、Hierarchical、LLM-only、RAG）运行相同查询，并测量延迟、质量、成本和碳排放——用数据帮你决定是否使用 RAG。静态 Next.js 部署于 GitHub Pages。Does RAG actually earn its cost? ragornot runs the same query through four retrieval modes (Flat/BM25, Hierarchical, LLM-only, RAG) against a live AWS Lambda + Bedrock backend and measures latency, quality, cost, and carbon — so you can decide RAG-or-not with data. Static Next.js on GitHub Pages.

🧠 Ultimate AI Coding Agent 2026：全面提速开发流程，写出更快、更干净的代码。🧠 Ultimate AI Coding Agent 2026: Supercharge Your Dev Workflow for Faster, Cleaner Code

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.

WordPress 共享 AI 基础设施：provider 凭证、实时模型、提示词、标准化请求及 AI-Scribe 和兼容插件的使用记录。Shared AI infrastructure for WordPress: provider credentials, live models, prompts, normalised requests and usage records for AI-Scribe and compatible plugins.

📊 自动化从 LinkedIn 抓取招聘信息，通过高效批量数据收集简化研究与招聘工作。📊 Automate job listing extraction from LinkedIn to streamline your research and recruitment efforts with efficient, bulk data collection.

DeepSeek Harness 个人自研插件集：上下文罗盘 / 跨会话知识 / 子代理模型路由 / AI 生图（Personally developed plugins for DeepSeek Harness）

AI 教材数字化与互动辅导平台：PDF/扫描教材经 MinerU OCR 结构化出题，文本 + 视觉双模型审校与确定性质量门禁；学生端七种题型互动、分层提示与错题多轮陪练闭环；FastAPI + PostgreSQL JSONB + React 19

一本关于生产级 RAG 与 agentic 系统的实用第一性原理手册，支持 RU/EN/SK，基于 Docusaurus 构建。A practical, first-principles handbook on production RAG & agentic systems — RU/EN/SK, built with Docusaurus.

GenAI 职业路线图 2026 🚀 | AI 岗位路径与技能指南GenAI Career Roadmap 2026 🚀 | AI Job Paths & Skills Guide

由一名高中应届毕业生借助 AI 开发的、可定制个人知识库的 AI Agent。An AI agent that customizes your knowledge base, created by a graduated high school student using AI

自我进化的个人 AI agent，以 Telegram 为优先；多提供商自带 key；具备持久记忆、每日日记、skill 图、梦境循环。永久免费，Apache 2.0。Self-evolving personal AI agent. Telegram-first. Multi-provider BYO key. Persistent memory, daily journal, skill graph, dream cycle. Free forever. Apache 2.0.

📚 构建并评估 RAG 流水线，实现数据导入、嵌入、检索与问答，并提供准确性与相关性指标。📚 Build and evaluate RAG pipelines to ingest, embed, retrieve, and answer questions with metrics for accuracy and relevance.

织光 WeaveMind V1.0 — 看得见、会记忆、会自我进化的多智能体 AI 团队。多用户鉴权、结构化数据适配器、验收溯源、报告分享/PDF/通知，本地运行数据私有。

自托管 Docker 栈，用于跨平台 AI Agent 工作区（Claude Code + ChatGPT + 任意 LLM）。MIT 许可。Self-hosted Docker stack for cross-platform AI agent rooms (Claude Code + ChatGPT + any LLM). MIT.

🤖 DeepTutor 是一款 AI 驱动的学习助手，可根据个人需求定制教育内容，提供个性化资源与支持🤖 Enhance learning with DeepTutor, an AI-powered assistant that personalizes education to fit your needs. Discover tailored resources and support.

使用本地 LLM 与私密法律文档对话，在自有硬件上获得带引用、可验证的答案。Chat with private legal documents using local LLMs. Get cited, verifiable answers on your own hardware.

一种静态类型、编译型编程语言，带有原生 x86-64 后端 — 由 AI 编写，为 AI 服务。A statically-typed, compiled programming language with a native x86-64 backend — written by AI, for AI.

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.

面向本地优先应用与 AI Agent 的嵌入式双时态记忆引擎，采用混合检索——进程内运行，无需服务器。Embedded bitemporal memory engine with hybrid retrieval for local-first applications and AI agents — in-process, no server.

🚀 零配置将 LangChain Agent 暴露为服务；以简单包装把脚本变为 Web 服务，无需任何基础设施🚀 Expose your LangChain agents as services with zero configuration; turn scripts into web services using simple wrappers and no infrastructure setup.

市场营销 × 消费者行为研究的开源项目发现与实证分析平台

论文《Controllable molecular graph generation from natural-language chemical constraints》（基于自然语言化学约束的可控分子图生成）的代码仓库。This is repository for "Controllable molecular graph generation from natural-language chemical constraints"

🔍 在 Weaviate 混合检索中评测 embedding 模型，基于自有数据或 MTEB 数据集评估 MRR@K、Hit@K、延迟与内存占用🔍 Benchmark embedding models in hybrid search with Weaviate. Evaluate MRR@K, Hit@K, latency, and memory using your data or MTEB datasets.

🛠️ 通过 ACG 增强 RAG 系统，依托可靠的外部知识提升准确性与事实一致性，减少 LLM 响应中的幻觉。🛠️ Enhance RAG systems with ACG to reduce hallucinations in LLM responses by improving accuracy and grounding in reliable external knowledge.

提供提案撰写、医学影像文献综述与论文报告幻灯片的工具，自动化学术研究工作流。Automate academic research workflows with tools for proposal writing, medical imaging literature reviews, and paper presentation slides.

几何有限主义：语言与思维的几何学Geofinitism: The Geometry of Language and Thought

基于架构决策记录（ADR）理念的 Memory Framework，用于 AI agent（Claude Code、Codex、Antigravity……）之间的知识共享。支持 agent 安装，vector（Postgres + pgvector）+ graph（Neo4j）双骨干，通过本地 gateway 管理，支持多种本地 LLM 后端，具备完整 provenance、合并、遥测等能力。Memory Framework based on the idea of Architectural Decision Records, shared knowledge between AI agents (Claude Code, Codex, Antigravity ...). Agent installable, vector (Postgres + pgvector) + graph (Neo4j) backbone, managed through a local gateway, supporting multiple local LLM backends, with full provenance, consolidation, telemetry and more

PaperForge v2026 是一款基于浏览器的学术写作自动化系统，通过 LLM 引导的工作流完成论文生成、引用处理、迭代与校验。PaperForge v2026 is a browser-based academic writing automation system with LLM-guided workflows for paper generation, citation handling, iteration, and validation.

本地优先、由 LLM 驱动的系统文献综述 (SLRs) 平台，以人机协同方式自动完成筛选与提取Local-first, LLM-powered platform for Systematic Literature Reviews (SLRs)—automating screening and extraction with human-in-the-loop precision.

codegraph 是一个 local-first 的代码上下文引擎和面向代码仓库的 MCP server。它将源代码增量索引到轻量级 SQLite 图中，然后提供高信噪比的 tools，支持符号查找、调用图遍历、影响分析、相关测试发现和语义搜索。使用 Go 构建，单二进制工作流，专为……而设计。codegraph is a local-first code context engine and MCP server for repositories. It incrementally indexes source code into a lightweight SQLite graph, then exposes high-signal tools for symbol lookup, call graph traversal, impact analysis, related test discovery, and semantic search. Built in Go with a single-binary workflow, it is designed to work

面向私有仓库与本地模型的自托管、厂商中立编码 Agent。TUI 优先，支持 16 家提供商的 BYOK 或通过 Ollama/LM Studio 完全离线运行。每个 Agent 操作均经过沙箱隔离、日志记录与签名——构建为可验证，而非仅可信任。Self-hosted, vendor-neutral coding agent for private repos and local models. TUI-first, BYOK across 16 providers or fully offline with Ollama/LM Studio. Every agent action is sandboxed, logged, and signed — built to be verified, not just trusted.

Haven 42 是一款证据门控、本地优先的 AI 工作台，支持 Windows、Linux 和 macOS 上的编码、聊天与媒体处理。Haven 42 is an evidence-gated, local-first AI workbench for coding, chat, and media on Windows, Linux, and macOS.

UMD 行星长期记忆算法、公式、基准、SDK 与可复现研究。UMD planetary long-term memory algorithms, formulas, benchmarks, SDKs, and reproducible research

针对 LLM 集成证据筛选（系统综述标题/摘要筛选）的筛选-自验证内核。Screening-and-self-validation kernel for LLM-ensemble evidence screening (systematic review title/abstract screening).