仓库/Skill 库

为 AI agent 提供可验证的记忆：写入受控、读取带溯源、双时态历史、无法回答时选择 abstention 而非幻觉。AGPL/商业双重许可。Verified memory for AI agents: gated writes, provenance on every read, bi-temporal history, abstention instead of hallucination. AGPL/commercial.

opencode 的持久化记忆 MCP server：Redis 存储事实、ChromaDB 语义搜索、文档存储、幂律记忆衰减、agent 身份；内置官方 Claude.app OAuth，可使用 Claude Max 套餐且规避第三方检测；一键安装。Persistent memory MCP server for opencode — Redis facts, ChromaDB semantic search, document storage, power-law memory decay, agent identity. Plus first-party Claude.app OAuth: use your Claude Max plan without third-party detection. One-command install.

自托管语义代码搜索。将代码仓库和知识源索引至本地向量数据库，然后通过 CLI 或任何 MCP 兼容 Agent 进行自然语言搜索。Self-hosted semantic code search. Index repos and knowledge sources into a local vector DB, then search by natural language from CLI or any MCP-compatible agent.

面向多 Agent 工作流的 MCP 协调原语。LLM 无关、CLI 无关、可自托管。TypeScript + SQLite。MCP coordination primitive for multi-agent workflows. LLM-agnostic, CLI-agnostic, self-hostable. TypeScript + SQLite.

实时更新的向量数据库项目、集成和基准评测全景图——每……刷新。Live-updating landscape of vector database projects, integrations, and benchmarks — refreshed every

LOCAH.ai —— 基于 Wilfrid Laurier University 公开信息的助手。提供引用标注的回答、显式呈现的矛盾，以及 Laurier 信息在何处未能服务学生的证据。LOCAH.ai — an assistant over Wilfrid Laurier University's public information. Cited answers, surfaced contradictions, and evidence on where Laurier's information fails students.

自托管、多用户转录平台：录制或上传音频。支持说话人标记、带时间戳的转录、跨录音识别说话人、摘要、提取行动项，并可使用自有 OpenAI 兼容 LLM 与转录内容对话。你的音频、你的服务器、你的模型。已在笔记本 RTX4070、台式机 RTX3090 与 RTX5090 上测试。Self-hosted, multi-user transcription platform: record or upload audio. Speaker-labeled, timestamped transcripts, Recognize speakers across recordings, Summarize, extract action items and chat over your transcripts with your own OpenAI-compatible LLM. Your Audio, your Server, your Model. Tested on Laptop RTX4070, Desktop RTX3090 and RTX5090

一份由 AI Agent 为人类撰写的出版物。Node/Express SSR + SQLite，自主化编辑部，实时 AI 工具数据引擎。https://dreaming.pressA publication where AI agents write for humans. Node/Express SSR + SQLite, autonomous newsroom, live AI-tool data engine. https://dreaming.press

Commercient Data Lake / Data Hub CLI（dlake）——为 SQL Server 数据平台即时提供 REST + GraphQL API 以及面向 AI Agent 的 MCP 访问能力。提供官方二进制发行版。Commercient Data Lake / Data Hub CLI (dlake) - instant REST + GraphQL APIs and MCP access for AI agents over a SQL Server data platform. Official binaries.

IBANforge——集成 IBAN 校验、BIC/SWIFT 查询、Swiss clearing 与 EMI/vIBAN 分类 API 的服务，配套面向 AI Agent 的 MCP。IBANforge — IBAN validation, BIC/SWIFT lookup, Swiss clearing, and EMI/vIBAN classification API with MCP for AI agents

🔬 管理专业 Agent 集群开展综合性文献综述的专家系统，基于用户自定义标准，利用 PubMed 数据库收集、整理并综合科研文献。🔬 An expert system to manage a swarm of specialized agents to conduct comprehensive literature reviews using the PubMed database, collecting, curating, and synthesizing scientific research based on user-defined criteria.

全栈博客平台 · Go 后端 + React 前端，内置 MCP server 供 AI agent 读写文章

空间智能工作站——53 路实时 OSINT 数据源，基于 PostgreSQL+pgvector 的 FollowTheMoney 实体图谱，9 阶段多 Agent 编排器（4 层防幻觉防护）、贝叶斯信源裁定、W3C PROV 证据 DAG、GNN 流水线（GAT+T-GCN+FedAvg+DP-SGD），3 节点 Ed25519 认证网格，通过 NVIDIA NIM Cascade 实现 24 小时自动简报Spatial intelligence workstation — 53 live OSINT feeds, FollowTheMoney entity graph on PostgreSQL+pgvector, 9‑phase multi‑agent orchestrator with 4‑layer anti‑hallucination guards, Bayesian source adjudication, W3C PROV evidence DAG, GNN pipeline (GAT+T‑GCN+FedAvg+DP‑SGD), 3‑node mesh with Ed25519 auth, automated 24h briefing via NVIDIA NIM Cascade

面向会议的对话智能：将转录文本转化为摘要、决策、行动项、风险与机会，支持多租户自托管。FIAP NEXT Challenge 2026。Conversation intelligence for meetings: turns transcripts into summaries, decisions, action items, risks and opportunities. Multi-tenant, self-hosted. FIAP NEXT Challenge 2026.

面向 Kubernetes 环境的 air-gapped RAG pipeline。在 LibreChat/LiteLLM/Keycloak/vLLM 之上增加文档摄取、强制的分类/可发布性标签、策展人审核与基于声明的访问控制检索，并以自定义 MCP 工具的形式对外暴露。Air-gapped RAG pipeline for Kubernetes environments. Adds document ingestion, mandatory classification/releasability tagging, curator review, and claims-based access-controlled retrieval on top of LibreChat/LiteLLM/Keycloak/vLLM — exposed as a custom MCP tool.

面向银行内部产品审计的深度研究 LLM Agent + RAG 平台，提供带引用报告、PDF 导出与 pgvector 支持。Deep-research LLM agent + RAG platform for internal bank-product audit — cited reports, PDF export, pgvector

面向 Node 与浏览器的 AI 数据库对话：用自然语言提问、审视查询、获取答案。支持 Postgres、MySQL、SQLite、DuckDB、Oracle、MongoDB。具备只读 AST 守卫、React UI、MCP server、VS Code 与 JetBrains 集成。AI database chat for Node and the browser: ask in plain language, review the query, get answers. Postgres, MySQL, SQLite, DuckDB, Oracle, MongoDB. Read-only AST guard, React UI, MCP server, VS Code & JetBrains.

AI Agent 集群的开源任务控制中心 —— 对话即可配置，Agent 负责执行，人类负责审批。Open-source mission control for AI agent fleets — chat to provision, agents to operate, humans to approve.

AI agent memory 与基础设施全景——912 个系统 × 68 列的对比目录，覆盖记忆层、agent 框架、运行时、vector store、知识图谱、MCP server、benchmark。支持按类型化边、谱系、引用进行检索。AI agent memory & infrastructure landscape — comparative catalog of 912 systems × 68 columns covering memory layers, agent frameworks, runtimes, vector stores, knowledge graphs, MCP servers, benchmarks. Searchable with typed edges, lineages, citations.

为 LLM Agent 自动化学术文献搜索、检索和管理工作流，使用面向主流数据库的集成研究 Skill。Automate academic literature search, retrieval, and management workflows for LLM agents using integrated research skills for major databases.

语音 AI API 的开放价格数据库 —— STT、LLM、TTS、S2S、VAD。Open price database for voice AI APIs - STT, LLM, TTS, S2S, VAD

🖥️ 通过终端中键盘优先的 Kanban board 简化工作流，实现快速、专注的任务管理。🖥️ Streamline your workflow with a keyboard-first Kanban board in your terminal for fast, focused task management.

使用 SQLite 和 FAISS 存储、整合与召回 coding agent 记忆，附带 provenance 追踪，实现快速、结构化的知识访问Store, consolidate, and recall coding agent memories with provenance tracking using SQLite and FAISS for fast, structured knowledge access.

Agents as Infrastructure。自托管多 Agent MCP server——具备 workspace、持久记忆与层级结构的长期运行 Agent。配备真实管理 UI、OAuth 2.1、静态加密 secrets。Agents as Infrastructure. Self-hosted multi-agent MCP server — long-lived agents with workspaces, persistent memory, and hierarchy. Real admin UI, OAuth 2.1, encrypted secrets at rest.

🌟 利用 GPU 加速 Apple Silicon 上的 SQLite 数据库操作，提升分析速度与数据管理效率🌟 Accelerate SQLite database operations on Apple Silicon with GPU power for faster analytics and efficient data management.

基于 LlamaIndex、Redis 与 PII 脱敏的 RAG 搜索引擎。RAG search engine using LlamaIndex, Redis, and PII masking.

绵羊遗传评估 CLI 与 MCP server——基于 NSIP 数据库检索个体、对比 EBV、规划配种、排序羊群。Sheep genetic evaluation CLI & MCP server -- search animals, compare EBVs, plan matings, rank flocks via the NSIP database

Cortex System：AI 工程领域的操作系统，治愈技术健忘症。Cortex System: The Operating System for AI Engineering. Cure Technical Amnesia.

使用先进的 RAG 系统发现你的下一部心仪动画，提供精准推荐与增强语义搜索。🎬 Discover your next favorite anime with this advanced Retrieval-Augmented Generation system, offering precise recommendations and enriched semantic search.

面向 AI Agent 的低开销记忆后端 —— 单二进制，内存占用约 50MB，支持验证增强准确性Low-footprint memory backend for AI agents — single binary, ~50MB RAM, verify-augmented accuracy

将学术论文转换为带注释、浏览器友好的网页，逻辑配色清晰、导航便捷，由 OpenAlex 数据驱动。Convert academic papers into annotated, browser-friendly web pages with color-coded logic and easy navigation powered by OpenAlex data.

基于 TurboQuant 优化 FAISS 兼容的向量量化，实现快速、精准的向量检索。Optimize FAISS-compatible vector quantization for fast, accurate vector search with TurboQuant

🤖 生产级 AI agent 编排平台，支持实时流式输出与多工具执行🤖 Orchestrate AI agents with ease using this production-ready platform, featuring real-time streaming and multi-tool execution capabilities.

论文 "Every Answer Has Its Own Path: Agentic Routing for Retrieval-Augmented Table Question Answering" (EMNLP 2026) 的官方代码。Official code for "Every Answer Has Its Own Path: Agentic Routing for Retrieval-Augmented Table Question Answering" (EMNLP 2026)

基于 RAG、LangGraph 多 agent workflow、FastAPI 与 PostgreSQL（pgvector）构建的 AI 教育内容生成平台。生产级架构，集成 LangSmith tracing。AI-powered educational content generation platform using RAG, LangGraph multi-agent workflows, FastAPI, and PostgreSQL with pgvector. Production-ready architecture with LangSmith tracing.

一个面向 PDF 文档问答的全栈 RAG 应用：上传 PDF，将其索引到本地向量库，然后基于页面级答案进行对话，并在内置阅读器中通过可点击引用跳转到对应页面。A full-stack retrieval-augmented generation (RAG) application for question answering over PDF documents. Upload a PDF, index it into a local vector store, then chat with page-grounded answers and clickable citations that jump to the right page in the built-in viewer.