Mail-Archiver is a production-grade ASP.NET Core 10 web application for archiving emails from IMAP, Microsoft 365 (Graph), and local imports (MBOX, EML). It provides a full MVC UI for searching, viewing, exporting, restoring, and managing archived emails, alongside a read-only REST API (v1) and a Model Context Protocol (MCP) server for AI agent integration. The system features background job processing for sync, batch operations, deduplication, retention policies, and audit exports, all backed by PostgreSQL with full-text search. Authentication supports local password (PBKDF2), OpenID Connect, and API keys, with two-factor authentication and role-based access control. The codebase is well-structured with clear separation of concerns: provider-specific services (IMAP, Graph, Mbox), shared utilities, and a core service layer. Extensive unit and integration tests (xUnit) cover critical paths, and Docker Compose provides a reproducible test environment. While some technical debt exists (raw SQL in core services, in-memory job tracking, German comments in places), the overall architecture is solid and the reusable components (static helpers, deduplication strategies, background job patterns) demonstrate high craftsmanship.
Vigil is a microservices status page application written in Rust. It monitors distributed infrastructure services via multiple probe modes (HTTP, TCP, SSH, ICMP, push, script, local), aggregates their health status, and serves a public status page with real-time updates. It also sends alerts through various channels (Slack, Email, Twilio, Telegram, etc.) when services go down or recover. The architecture is a single binary with separate threads for probing, aggregation, and HTTP serving, using a shared in-memory state protected by RwLock. The codebase is well-structured, with clear separation of concerns: config reader, prober, notifier, aggregator, and responder modules. It includes an MCP server for AI agent integration. The project is actively maintained with recent commits and CI/CD pipelines.
The code-index-mcp repository implements a Model Context Protocol (MCP) server that provides code indexing and analysis capabilities for Large Language Models (LLMs). It enables AI assistants to query codebases for symbol definitions, call relationships, file contents, and project metadata through a standardized MCP interface. The system features a three-layer architecture separating technical tools (file system, search, monitoring), business services (code intelligence, index management, project management), and MCP entry points. It supports shallow indexing (file discovery) and deep indexing (symbol extraction via tree-sitter AST parsers) for over 10 programming languages, with SQLite persistence for indexes and real-time file watching for automatic updates. The application is designed for integration with MCP-compatible clients like Claude Desktop and Codex CLI.
chubbyskills is a personal knowledge management CLI toolkit that ingests content from over a dozen platforms (YouTube, Bilibili, X, Xiaohongshu, WeChat, Douyin, Podcasts, etc.), transcribes audio/video locally or via cloud providers, and outputs structured Markdown notes with YAML frontmatter (schema v1). The system is architected as a collection of modular "skills" (one per platform) orchestrated by a unified CLI (`tools/chubby.py`), with shared utilities in `chubby_common/`. It includes an incremental knowledge base indexer using SQLite FTS5 and optional semantic embeddings, an MCP server exposing six tools for AI agent integration, and a deterministic evidence brief generator with integrity validation. Operation is local-first: transcription uses SenseVoice and faster-whisper, video downloading uses yt-dlp, and all processing is designed to work offline. Cloud transcription (Atlas/MuAPI) and LLM enrichment (DeepSeek) are optional extensions. The repository also provides a skill installer, platform smoke testing, output validation, and retry mechanisms with credential redaction. Despite the breadth, the codebase maintains clean separation of concerns, with the shared library standing out as a reusable zero-dependency core.
This is a VS Code extension that provides a unified interface for discovering, installing, and managing MCP (Model Context Protocol) servers and AI agent skills. It integrates with multiple sources: the Official MCP Registry, skills.sh, GitHub repositories, and CloudMCP (a hosted alternative). The extension offers a chat participant (`@mcp`) for natural-language search and install, and a sidebar webview with search and management tabs. It supports 30+ AI coding agents including GitHub Copilot, Claude Code, and Codex CLI. The architecture consists of a TypeScript extension backend (using esbuild for bundling) and a React 19 + Vite + Tailwind CSS + shadcn/ui frontend, communicating via typed RPC messages. Telemetry is collected anonymously with standardized error classification. The codebase is well-structured with clear separation of concerns, CI/CD pipelines, and unit tests.
Docfork is a documentation lookup service designed specifically for AI coding agents and developers. It provides up-to-date, version-pinned documentation through a Model Context Protocol (MCP) server with two core tools: `search_docs` for finding relevant documentation sections and `fetch_doc` for retrieving full content. The service is accessed via IDE plugins (Cursor, Claude Code, etc.), a command-line interface (dgrep), and a TypeScript SDK. The architecture features a monorepo structure with separate packages for the MCP server, CLI tool, SDK, and IDE integrations, using Turborepo for build orchestration and pnpm workspaces for package management. Key features include authentication via API keys or OAuth, team-based 'Cabinets' to scope documentation to specific project stacks, and privacy-first telemetry that collects only metadata without querying user data.
VeritasGraph is a comprehensive, governed GraphRAG and agent framework for building enterprise-grade knowledge graphs with verifiable attribution. The repository contains a core Python library (VeritasReason) for knowledge graph construction, semantic extraction, reasoning, provenance tracking, and export, along with multiple domain-specific applications: a HIPAA-safe clinical knowledge graph pipeline (clinical-kg), a floorplan extraction and validation web app (floorplan-kg), a municipality incident reporting chatbot, and a Model Context Protocol (MCP) server for IDE integration. The architecture is modular, with a plugin-based method registry pattern, unified configuration management, and a pipeline orchestration engine. While the primary character is an application framework, it also includes research-oriented components such as clinical benchmarks (MedKG-Signal) and evaluation suites, making it a hybrid project with a strong application focus.
GistPad MCP is a Model Context Protocol (MCP) server that provides a comprehensive interface for managing GitHub Gists through AI assistants like GitHub Copilot and Claude Desktop. It exposes tools for CRUD operations on gists, file management within gists, comments, daily notes, archiving, starring, and reusable prompts. The server runs over stdio and uses the GitHub REST API via a custom typed fetch client. It features a caching layer with hourly refresh, resource subscriptions, and change notifications. The codebase is written in modern TypeScript (ES2024, Node.js 22+) with strict type safety, comprehensive tests for the file editing tool, and a clean modular architecture separating concerns into tools, server, store, and utilities. It demonstrates strong engineering practices including abstract base classes for stores, automatic tool annotation derivation, and careful error handling.
Perfetto MCP is a Model Context Protocol server that provides tools for analyzing Perfetto trace files. It maintains persistent connections to trace files and exposes various analysis tools through the MCP protocol, including ANR detection, CPU profiling, jank frame detection, memory leak analysis, and more. The architecture features a modular design with separate components for connection management, tool implementations, and resource registration. Key entry points include the main server module, development entrypoint, and package initialization. The system handles connection lifecycle management with automatic reconnection and provides structured JSON responses for all tool invocations.
Jesse is a mature, full-stack algorithmic trading framework designed for cryptocurrency backtesting, live/paper trading, hyperparameter optimization, Monte Carlo simulation, and rule significance testing. It combines a Python library with a FastAPI web server and a Nuxt.js dashboard, offering a comprehensive environment for developing and validating trading strategies. The repository also includes an MCP (Model Context Protocol) server for AI-assistant integration, over 180 technical indicators (many with Rust-accelerated backends), and a research API for programmatic strategy analysis. Architecture is modular with distinct layers: CLI entrypoint → web controllers / MCP tools → service layer → simulation engine (backtest/optimize/live) → exchange adapters. State management uses global singletons for in-memory simulation state, while persistent data is stored via Peewee ORM (PostgreSQL, optional TimescaleDB). The indicator library showcases a clean pattern with sequential/non-sequential modes and Rust fallback. However, the codebase shows signs of organic growth with some tightly coupled modules (global config, store singletons) and a large static frontend bundle that is opaque to analysis. Key strengths include the breadth of supported exchanges (10+), robust backtesting with realistic fee/margin/leverage modeling, and a well-designed MCP tool layer for AI-assisted development. Weaknesses include exchange driver duplication, a complex Rust subprocess for coordination, and dependency on many external APIs that require ongoing maintenance.
This is a monorepo housing `create-uni`, a CLI scaffolding tool for quickly generating `uni-app` projects. `uni-app` is a cross-platform framework based on Vue, allowing development for iOS, Android, Web, and various mini-programs. The CLI supports interactive prompts (via `@clack/prompts`), command-line flags, a native desktop GUI (via a Rust `napi-rs` addon encapsulating `wry`), and an MCP (Model Context Protocol) server for AI-assisted project creation. The core package (`packages/core`) handles template rendering using EJS with a callback-driven data injection pattern, while `packages/config` provides the option catalogues. The GUI package combines a Rust webview with a Preact/TypeScript UI (built with shadcn/ui). The MCP package exposes two tools (`create-with-template`, `create-custom`) with Zod schemas auto-derived from config data. The project demonstrates strong architectural separation, modern tooling, and a novel integration of a native GUI into a Node.js CLI. Though tightly focused on the uni-app ecosystem, several internal patterns (template rendering, object merging, directory traversal, MCP server setup) are cleanly implemented and potentially reusable.
This repository provides a production-ready documentation template built on Nuxt 4, Nuxt UI 4, and Nuxt Content 3. The codebase implements a static site generator for technical documentation with full-text search, automatic navigation, dark mode, and optimized OG images. It includes a built-in MCP (Model Context Protocol) HTTP server that exposes two tools (`list-pages` and `get-page`) for AI assistants to discover and read documentation content programmatically. Additionally, it integrates `nuxt-llms` to pre-render `/llms.txt` and `/llms-full.txt` files for LLM consumption. The architecture follows a standard Nuxt/Nitro server-rendered app with prerendering enabled, relying on modules for search, image optimization, and content management. The repo is explicitly a template intended for forking, with clean configuration-driven customization via `app.config.ts` and a well-documented content structure.
LeanKG is a Go-based knowledge graph engine for AI-assisted development. It indexes source code from multi-language repositories into a graph of elements (functions, types, classes) and relationships (calls, imports, implements), stored in SQLite or PostgreSQL with optional vector embeddings for semantic search. The system provides a CLI, REST API, MCP (Model Context Protocol) server, and a React web UI (force-directed graph, file tree, code panel). Core capabilities include incremental indexing with three-signal change detection, a four-tier query ladder (cold/exact/fuzzy/semantic), impact analysis with blast radius, organizational knowledge management (incidents, notes, env reports), ontology matching, federation across servers, and token-budgeted compression for AI tool integration. The architecture is modular: the store backend interface supports SQLite and PostgreSQL with a shared migration ledger; indexing uses regex extractors for 40+ languages with an optional tree-sitter CGO tier; embeddings use a provider abstraction (OpenAI-compatible, llama.cpp sidecar, deterministic). The codebase is well-structured with extensive tests, hermetic test patterns, and deterministic output design. Notable reusability includes the compress package (shell output, git diff), auth token system, store abstraction pattern, and A/B benchmarking harness.
This repository implements an MCP (Model Context Protocol) server that provides semantic code search capabilities for AI assistants. It enables developers to search their codebases by meaning rather than just keywords, using local AI models to ensure privacy and avoid external API calls. The system features semantic code search using embeddings (nomic-embed-text-v1.5 with MRL), incremental indexing with file watching, efficient SQLite-based caching of embeddings, cross-platform package version checking across 20+ ecosystems, workspace switching capabilities, and resource throttling to prevent system overload during indexing. The codebase demonstrates strong engineering practices with proper error handling, modular design, and attention to user experience.
TrendRadar is a configurable news aggregation and trend analysis system that crawls hot lists from 11+ Chinese platforms (Zhihu, Weibo, Douyin, Bilibili, etc.) and RSS/Atom feeds, filters content via keyword DSL or AI-based interest matching, performs AI-powered analysis (sentiment, controversy, topic trends), generates rich HTML reports, and pushes notifications to 9+ channels (Feishu, DingTalk, Telegram, Email, ntfy, Bark, Slack, WeCom, generic webhook). It is primarily an application (with CLI entry points, scheduling via timeline.yaml, Docker/GitHub Actions deployment) but incorporates data-pipeline patterns such as multi-stage ETL (crawl → store → filter → analyze → report), SQLite storage with optional S3 remote sync, and AI batch processing. The architecture is a modular monolith: the core `trendradar` package handles all orchestration, while a separate `mcp_server` package exposes 20+ tools via Model Context Protocol (MCP) for LLM integration. The system is heavily config-driven (YAML and text files) and includes a standalone web-based config editor. External dependencies include the third-party newsnow API (for hot lists), LiteLLM (for AI model abstraction), and various notification service APIs. The codebase demonstrates good craftsmanship with clean abstractions (storage backends, notification dispatcher, AI client), though some duplication exists between the core and MCP notification logic, and the extensive configuration surface requires careful maintenance.
Supermemory is a commercial-grade AI memory and context engine that provides persistent long-term memory for AI agents. The repository implements the client-side integration SDKs, an MCP (Model Context Protocol) server, a memory graph visualization component, and supporting infrastructure. In production, it connects to an external cloud API (api.supermemory.ai) that handles document ingestion, semantic search, user profiles, and knowledge graph construction. The codebase is organized as a monorepo with distinct packages for TypeScript/Python SDKs covering multiple AI frameworks (Vercel AI SDK, OpenAI, Mastra, Claude, etc.), a Cloudflare Workers-based MCP server with OAuth and widget UI, a ship-grade memory-graph React component with force-directed canvas rendering, and a comprehensive validation schema package. The architecture demonstrates strong engineering practices: strict Zod validation, middleware injection patterns, caching and deduplication logic, and thorough testing across languages. Notable skill is evident in the memory-graph canvas engine (viewport, simulation, spatial indexing, version chain visualization) and the shared memory-context injection utilities. The main downside is significant logic duplication across four Python SDK packages and their TypeScript counterparts, which increases maintenance risk. The repo is actively developed with CI/CD pipelines publishing to npm and PyPI.
This repository implements a Model Context Protocol (MCP) server and CLI for searching, downloading, and reading academic papers across ~20 scholarly platforms (arXiv, PubMed, Semantic Scholar, CrossRef, OpenAlex, Google Scholar, etc.). It is primarily an application—a Python package distributed via PyPI—that exposes two entry points: an MCP server (stdio-based, compatible with Claude Desktop and other MCP clients) and a command-line interface. The architecture follows a clean two-layer design: a unified tool layer (search_papers, download_with_fallback) that orchestrates concurrent multi-source searches with deduplication, and a modular connector layer where each platform is implemented as a self-contained class inheriting from a common PaperSource abstract base. The system emphasizes a 'free-first' strategy, relying on open public APIs and optional API keys for enhanced access. It includes a fallback chain for PDF downloads (native source → OA repositories → Unpaywall → Sci-Hub) and supports full-text extraction via pypdf. The codebase is well-structured with consistent patterns (Paper dataclass, env config, retry/backoff), comprehensive test coverage (unit and e2e), and CI/CD publishing. However, some connectors are skeletons (IEEE, ACM) or not wired (ChemRxiv), and HTML scraping components are fragile to upstream changes. The last commit date is anomalously in the future (2026-08-17), but the repository shows active issue triage and community engagement.
This repository is a large monorepo for a multimodal AI agent platform developed by ByteDance. It includes a desktop Electron application (UI-TARS Desktop) that allows users to control their computer using natural language via vision-language models (UI-TARS, GPT-4o, Claude, etc.). Additionally, it provides a CLI tool (Agent TARS) for running agents in browser/desktop environments, a server for multi-user agent sessions, a web UI for interacting with agents, MCP servers for browser/filesystem/commands, and a comprehensive SDK for building custom agents and operators. The architecture is heavily componentized with multiple packages for agent core, tool-calling engines (native, prompt-engineering, structured-outputs), browser automation (local, remote, sandbox), desktop automation (NutJS, ADB), and UI components. While the codebase demonstrates strong engineering with clean abstractions (event streams, plugin systems, strategy patterns), it also shows signs of rapid growth with some duplication (two agent server implementations, overlapping operator packages) and ongoing migrations. The repository is actively maintained with frequent releases and comprehensive test coverage across unit, integration, and e2e tests.
This repository contains the backend API for a trading platform, specifically QuantDinger. It handles strategies, indicators, and market data, and has various tests and scripts for ensuring the quality and functionality of the code.
This repository provides a stealth browser automation MCP (Model Context Protocol) server that offers undetectable control over real browser instances (Chrome, Chromium, Edge) via the Chrome DevTools Protocol (CDP) and the `nodriver` library. It exposes 97 tools across 11 sections including navigation, DOM interaction, element extraction (styles, structure, events, animations), network interception and modification (including dynamic Python-powered hooks), CDP command execution, cookie management, tab control, and proxy forwarding with authentication. The architecture is a FastMCP-based server with singleton managers for browser instances, network interception, element cloning, and process cleanup. It supports stdio and HTTP transports, Docker deployment, and optional bearer auth. The system is designed to bypass anti-bot detection (Cloudflare, CreepJS, login walls) and is used for scraping, testing, and AI agent automation. While the codebase is well-structured and the functionality is comprehensive, there is some code duplication across multiple element cloner implementations and technical drift risk due to tight coupling with CDP APIs and the `py2js` transpiler dependency.