仓库/Skill 库

一个简单但有效的持久化 key-value 数据库。A simple, yet effective persistent key-value database.

Opptrix——AI 驱动的全球多市场投研工作台 | 面向中国 A 股的开源 LLM 投研助手。170+ MCP 工具、因子筛选、回测、自选股与 Electron 桌面端。TypeScript · React · Fastify monorepo。Opptrix — AI驱动的全球多市场投研工作台 | Open-source LLM research assistant for China A-shares. 170+ MCP tools, factor screening, backtest, watchlist & Electron desktop. TypeScript · React · Fastify monorepo.

经过策展的 Model Context Protocol（MCP）server 目录，用于发现和集成 AI 工具、数据源和服务。涵盖数据库、开发者工具、Web 自动化、云基础设施、生产力、AI Agent、analytics 等众多领域的 MCP server。A curated catalog of Model Context Protocol (MCP) servers for discovering and integrating AI tools, data sources, and services. Explore MCP servers across databases, developer tools, web automation, cloud infrastructure, productivity, AI agents, analytics, and more.

为 Claude Code 提供持久化记忆，支持自带数据库Persistent memory for Claude Code. Bring your own database.

AKB — Agent Knowledgebase。AI agent 的组织记忆：以 URI 图统一 vault 范围的文档 / 表格 / 文件，通过 MCP 提供服务。AKB — Agent Knowledgebase. Organizational memory for AI agents: vault-scoped docs / tables / files unified by URI graph, served over MCP.

用于多 Agent 协调的 Rust MCP server：34 个工具、Git 备份的归档、SQLite 索引、advisory 文件锁，以及交互式 TUI 控制台。Rust MCP server for multi-agent coordination: 34 tools, Git-backed archive, SQLite indexing, advisory file locks, and an interactive TUI console

Smart Promise Tracker AI 2026 —— 承诺 Memory 引擎。Smart Promise Tracker AI 2026 – Commit Memory Engine

通过迭代实现自我改进的 AgentSelf improving agents through iterations

本地代码搜索，结合 BM25、向量相似度与 cross-encoder 重排序。使用 tree-sitter 解析 60+ 种语言，完全离线运行，返回包含文件路径、行号范围与符号元数据的结构化结果。使用 Rust 构建。Local code search combining BM25, vector similarity, and cross-encoder reranking. Parses 60+ languages with tree-sitter, runs entirely offline, and returns structured results with file paths, line ranges, and symbol metadata. Built in Rust.

一款便捷的 lib，用于流畅地与大语言模型（LLM）交互及构建 AI 应用。A handy lib for smooth interaction with large language models (LLMs) and crafting AI apps.

面向 AI Agent 的代码搜索工具：32 个 MCP 工具，SQLite 索引，单一二进制文件零依赖。可解析 1С:Предприятие — Конфигуратор 与 EDT 的导出文件；8.8 万文件的配置库索引耗时 6 分钟，查询响应 10 毫秒。Code 索引 MCP server：基于 tree-sitter AST，支持 14 种语言，20 个通用工具 + 12 个 1C/BSL 专用工具。Поиск по коду для ИИ-агентов: 32 инструмента MCP, индекс на SQLite, один бинарник без зависимостей. Разбирает выгрузки 1С:Предприятие — Конфигуратор и EDT; конфигурация на 88 тыс. файлов индексируется за 6 минут, ответ на запрос — 10 мс. Code index MCP server: tree-sitter AST for 14 languages, 20 universal tools + 12 for 1C/BSL.

面向 agentic AI 与受治理分析的源代码可用的语义与上下文层、规则引擎和语义 sidecar；可将声明式 YAML 模型编译为优化的 SQL、KPI 和语义上下文，覆盖 8 种 SQL 方言Source-available semantic and context layer, rule engine, and semantic sidecar for agentic AI and governed analytics. Compiles declarative YAML models into optimized SQL, KPIs, and semantic context across 8 SQL dialects.

面向实验的 GenAI/RAG 优化器与工具包，基于 Oracle Database AI Vector Search 与 NL2SQLGenAI/RAG Optimizer and Toolkit for experimentation using Oracle Database AI Vector Search and NL2SQL

可解释、本地优先的 AI Agent 记忆引擎。约 9 MB 的单一二进制在 VelesQL 下融合向量 + 图 + 列存；why() 返回每次召回背后的证据路径。无云依赖、无胶水代码 —— 支持服务器、浏览器、移动端与桌面端运行。The explainable, local-first memory engine for AI agents. One ~9 MB binary fuses vector + graph + columnar under VelesQL; why() returns the evidence path behind every recall. No cloud, no glue code — runs on server, browser, mobile and desktop.

基于 Google ADK 构建的生产级多 Agent 编排引擎：数据库驱动的 Agent 配置、支持 50+ LLM provider、MCP 协议、持久化记忆、Web 仪表盘与 RBAC。Production-ready multi-agent orchestration engine built on Google ADK. Database-driven agent config, 50+ LLM providers, MCP protocol, persistent memory, web dashboard, RBAC.

代码智能 CLI——覆盖 34 种语言的函数级依赖图、为 AI agent 提供 34 工具的 MCP server、复杂度度量、架构边界强制、CI 质量门禁、git diff 影响分析（含 co-change 分析）、混合语义搜索。完全本地运行，无需 API key。Code intelligence CLI — function-level dependency graph across 34 languages, 34-tool MCP server for AI agents, complexity metrics, architecture boundary enforcement, CI quality gates, git diff impact with co-change analysis, hybrid semantic search. Fully local, zero API keys required.

基于 Parquet 构建的嵌入式检索库。快速、高效且可扩展。Embedded retrieval library built on Parquet. Fast, efficient, and scalable.

结合向量检索与时序知识图谱的 AI 记忆系统，内置面向 Agent 的认知引擎，支持记忆衰减、矛盾检测与 MCP 集成。AI memory system combining vector search with temporal knowledge graph. Built-in cognitive engine for agents. Supports memory decay, contradiction detection, and MCP integration.

将生产事故转化为结构化的 9 段式 LLM 响应（严重等级、根因、缓解措施、事后复盘）。附带 5 个场景的回归测试集 + LLM-as-judge 评估流水线。Turn a production incident into a structured 9-section LLM response (severity, root cause, mitigation, postmortem). Ships with a 5-scenario regression suite + LLM-as-judge eval pipeline.

Agent 记忆系统对比。Comparison of memory systems for agents

一个轻量且快速的 Rust 嵌入式键值存储。A lightweight and fast embedded key-value store for Rust.

隐私优先、自托管的加密资产记账应用，零云端数据共享。聚合交易所、钱包及多链历史，计算 FIFO/LIFO/HIFO 成本基础、已实现/未实现盈亏与资本利得，跟踪质押/空投收入，并导出可报税的 CSV/PDF/JSON 报告。加密 SQLite。Python，跨平台。Privacy-first, self-hosted crypto accounting app with zero cloud data sharing. Aggregates exchange, wallet and multi-chain history, calculates FIFO/LIFO/HIFO cost basis, realized/unrealized PnL and capital gains, tracks staking/airdrop income, and exports tax-ready CSV/PDF/JSON reports. Encrypted SQLite. Python, cross-platform.

在 Apple Silicon 上运行 Windows 游戏 —— 免费、开源，并附带开放兼容数据库，告知你哪些游戏真正可用。Run Windows games on Apple Silicon — free, open source, with an open compatibility database that tells you what actually works.

Perseus Vault — 面向 AI agent 的持久化、加密、时序感知记忆。单个 Rust 二进制、单文件、local-first、原生支持 MCP，MIT 许可。Perseus Vault — durable, encrypted, time-aware memory for AI agents. One Rust binary, one file, local-first, MCP-native, MIT.

RuvNet Brain——基于 Reuven Cohen（rUv）的 RuvNet 技术栈（RuVector/RVF、Ruflo、AgentDB、RuLake、SPARC 及 21 个构建块）为 Claude Code 提供一个可下载、源码溯源的"大脑"。通过单一 MCP 工具（search_ruvnet）让 Claude 立足真实源码，而不是脱离技术栈空想。RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet), so it builds with the stack instead of drifting off it.

通过 MCP 为 Claude Code 提供持久化长期记忆 — 跨会话捕获编码决策、Bug 修复和上下文。采用 FTS5 + TF-IDF 混合搜索与 episode 批处理。单一 SQLite 数据库，无需外部服务。作为 claude-mem 的替代方案，成本降低 600 倍。Persistent long-term memory for Claude Code via MCP — captures coding decisions, bugfixes, and context across sessions. Hybrid FTS5 + TF-IDF search with episode batching. Single SQLite DB, no external services. Alternative to claude-mem with 600x lower cost.

为 AI 编码 Agent 提供长期、跨项目的记忆。以你自己的 Obsidian 仓库为唯一信源。无守护进程、不依赖不透明数据库，记忆归你所有。Long-term, cross-project memory for AI coding agents. Your own Obsidian vault as the source of truth. Daemonless and without opaque databases, your memory belongs to you.

覆盖 100+ 操作系统上 100+ 浏览器的自动化 User-Agent 数据库。通过 GitHub Actions 每 5 分钟更新一次。按真实流行度加权，按 OS 与浏览器分组，并附带累积的 ALL/ 文件夹存放唯一 agent。Automated User-Agent database for 100+ browsers on 100+ operating systems. Updated every 5 minutes via GitHub Actions. Weighted by real-world popularity, grouped by OS and browser, with a cumulative ALL/ folder of unique agents.

开源、可自托管的 Markdown 团队 Wiki，内置 MCP server——让 AI Agent 作为"一等队友"读写并检索你的文档。支持实时多人协作、语义+全文搜索。基于 Go + PostgreSQL + React/Milkdown。Open-source, self-hostable markdown team wiki with a built-in MCP server — so AI agents read, write, and search your docs as first-class teammates. Live multiplayer, semantic + full-text search. Go + PostgreSQL + React/Milkdown.

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)

AI 编程智能体统一桌面工作台 | Desktop hub for managing Claude Code, Codex CLI, Gemini CLI & OpenCode. Tauri 2 · Rust · React · SQLite.

为开发者及其编码 Agent 提供持久化的本地记忆。将命令、输出、错误以及有效修复方案记录到 SQLite，并通过 MCP 提供服务Persistent, local memory for developers and their coding agents. Records commands, output, errors, and the fixes that worked into SQLite and serves them over MCP.

一个面向 PostgreSQL 的原生订阅同步引擎A subscription-native sync engine for PostgreSQL.

零停机 embedding 升级。Zero downtime embedding upgrades

AI 编写软件的记录系统。实体、关系、变更与来源的持久化图谱，使人类和 AI Agent 在合并前看到变更影响范围。目前与 Git 并行使用。The system of record for AI-written software. A persistent graph of entities, relationships, changes, and provenance, so humans and AI agents see what a change touches before it merges. Beside Git today.

生产级多 Agent 编排引擎。从可插拔的 Agent、LLM、工具与 retriever 目录组合 Agentic 工作流；本地使用 LangGraph 执行，或通过 Temporal 分布式执行。内置 RAG 管道用于企业知识检索，支持 A2A 与 MCP 协议，提供可视化拖拽蓝图构建器。Production-grade multi-agent orchestration engine. Compose agentic workflows from a pluggable catalog of Agents, LLMs, tools, and retrievers. Execute locally with LangGraph or distributed with Temporal. Built-in RAG pipeline for enterprise knowledge retrieval. A2A and MCP protocol support. Visual drag-and-drop blueprint builder.