Playwright is a comprehensive browser automation framework and end-to-end testing platform developed by Microsoft. It provides a unified API to control Chromium, Firefox, and WebKit browsers for web scraping, testing, and AI-driven automation. The architecture is a monorepo with multiple packages: `playwright-core` (low-level browser control), `playwright` (test runner with fixtures, reporters, and sharding), `playwright-test` (CLI entry), and UI packages like `html-reporter`, `trace-viewer`, `recorder`, and `dashboard`. Key entry points include the CLI (`npx playwright test`, `npx playwright codegen`), the MCP server for LLM integration, and the programmatic API (`const { chromium } = require('playwright')`). Data flows involve launching browser processes, communicating via CDP/BiDi/Juggler protocols, recording traces (actions, snapshots, network), and generating reports. External dependencies include Node.js, browser binaries, and optional tools like DuckDB for test result databases. The codebase demonstrates exceptional craftsmanship with clean separation of concerns, reusable isomorphic utilities, and a well-defined dispatcher pattern for client-server communication.
CodeGraph is a local-first, cross-language code intelligence engine designed to give AI coding agents structured knowledge of a codebase: symbols, references, call graphs, import graphs, inheritance, routes, and framework-specific dynamic dispatch. It indexes source with tree-sitter WASM grammars (or an optional native Rust kernel for speed), stores the resulting graph in SQLite with FTS5, then resolves cross-file references and synthesizes edges for indirect patterns like web frameworks, DI containers, callbacks, and event dispatch. The primary interfaces are a CLI (codegraph), an MCP server exposing tools for agents, an embeddable programmatic API, and a Svelte web viewer.
gog is a comprehensive, production-grade CLI tool for Google Workspace automation that unifies 20+ Google services (Gmail, Calendar, Drive, Docs, Sheets, Slides, Forms, Meet, Chat, Contacts, Tasks, Classroom, YouTube, Analytics, Search Console, Admin, Groups, Keep, Photos, Maps, Apps Script) into a single binary. It excels at task-first workflows: searching and sanitizing mail, resolving calendar names, auditing Drive sharing, editing Docs, appending Sheet tables, building Slides from Markdown, managing Workspace users, and performing encrypted backups. The architecture is a modular monolith with clean internal package boundaries for each service domain. Key entry points are cmd/gog/main.go and the Kong-based command tree in internal/cmd. Primary data flows: command invocation -> account/client resolution -> authenticated Google API client creation -> API execution -> structured output (JSON, plain TSV, or human-readable tables). External dependencies include Google APIs, OAuth2, keyring backends (macOS Keychain, Windows Credential Manager, Linux Secret Service, encrypted file), MCP for agent integration, and age encryption for backups. The codebase demonstrates exceptional craftsmanship in cross-platform secret storage, Gmail push notification processing, sed-style Docs editing with UTF-16 index tracking, atomic Docs request batching, encrypted backup with Git shard checkpointing, email open tracking with versioned key rotation and bot detection, and build-time safety profile compilation to hash-based allow/deny switches. Active development with recent commits, comprehensive test coverage (unit + integration + live tests), and modern dependency versions.
GitNexus is a graph-powered code intelligence platform that indexes any codebase into a knowledge graph, then exposes it through MCP tools and a web UI. It supports 14+ languages with deep scope-based resolution (RFC #909), cross-file type inference, control-flow graphs (CFG), program dependence graphs (PDG), taint analysis, and hybrid search (BM25 + semantic + RRF). The system has two main components: a CLI/MCP server (Node.js) for AI agent integration with tools like Cursor, Claude Code, and Codex; and a web UI (React + Vite) for visual graph exploration. The architecture is a multi-phase ingestion pipeline: scan → structure → parse → scope resolution → clustering → process detection → search indexing. The codebase demonstrates strong engineering with comprehensive test coverage (1100+ tests), a shared types package (gitnexus-shared), vendored tree-sitter grammars with prebuilt binaries, Docker containerization with cosign signing, and CI/CD with security scanning. The eval harness for SWE-bench evaluation shows research-grade rigor. Key architectural decisions include the registry-primary scope resolution system, the language provider pattern with compile-time exhaustive dispatch, and the worker pool for parallel parsing with self-healing capabilities.
GBrain is a personal knowledge management system designed as an AI agent memory layer. It provides a persistent knowledge base that runs as a 24/7 daemon for continuous ingestion, enrichment, and consolidation of information from various sources. The system features a CLI-first architecture with MCP (Model Context Protocol) support for AI agent integration, a web admin interface, and extensibility through skill packs. It uses a hybrid storage approach with PGLite for local/single-user deployments and Postgres+pgvector for shared/scale deployments, incorporating vector search, full-text search, and a self-wiring knowledge graph with typed edges. The system includes evaluation frameworks (BrainBench, takes-quality assessment), an advisor system for health recommendations, and automated maintenance cycles.
Reactive Resume is a full-stack, open-source resume builder and job application tracker. It provides a rich web interface for creating, editing, and managing resumes with real-time preview, multi-format export (PDF, DOCX, Markdown, JSON), and ATS compatibility analysis. The system includes an AI-powered assistant for resume tailoring and cover letter drafting, an MCP server for LLM integration, and a semantic CSS stylesheet system for fine-grained PDF styling. The architecture is a monorepo with a React frontend (TanStack Router, Zustand, Lingui i18n), a Node.js API layer (oRPC, Drizzle ORM, PostgreSQL), and dedicated packages for PDF generation, DOCX export, authentication, and UI components. Key entry points include the resume builder interface, public resume sharing pages, an AI agent chat, and a job application board with stage tracking and CSV import/export. External dependencies include PostgreSQL, Redis, AI provider APIs (OpenAI, Anthropic, Gemini), and cloud storage (Vercel Blob or S3). The codebase is well-structured with extensive unit and integration tests, a reusable UI component library, and a modular package architecture that supports self-hosting via Docker or Vercel.
This repository is the core implementation of **coc.nvim**, a powerful Language Server Protocol (LSP) client and extension host for Neovim and Vim. It transforms these editors into full-featured IDEs by managing the lifecycle of language servers and providing rich features like intelligent code completion, diagnostics, refactoring, navigation, and snippet expansion. The architecture is a monolithic Node.js backend that communicates with the editor via RPC (`@chemzqm/neovim`), with a Lua bridge for performance-critical text operations and a sophisticated extension system that allows users to install and manage third-party plugins. The codebase demonstrates a high degree of engineering craftsmanship. It features a clean, event-driven architecture with extensive use of the Disposable and CancellationToken patterns for resource management. Notable subsystems include a highly optimized fuzzy matching engine with WASM support, a complete Model Context Protocol (MCP) server for AI agent integration, a robust configuration system with layered scoping, and a secure download/extraction utility. The project maintains an exceptionally large and well-structured test suite covering unit, integration, and handler-level scenarios. Currently, the project is in an **active** maintenance state with very low technical drift. It aggressively tracks the latest Node.js versions and LSP protocol extensions. While the sheer size of the codebase introduces some inherent complexity and a few deprecated internal APIs, the overall architecture is sound, the code is well-factored, and several components are genuinely reusable in other projects. It stands as a benchmark for how to build a complex, high-performance editor plugin.
PaddleOCR is a production-grade OCR and document parsing toolkit built on PaddlePaddle. It provides a comprehensive suite of models for text detection, text recognition, layout analysis, table extraction, formula recognition, key information extraction (KIE), and document conversion (PDF/Image to Markdown/JSON). The system is deployed as a Python CLI, a Python library, a C++ inference engine, mobile SDKs (Android, iOS), a JavaScript browser SDK, a Go SDK, a TypeScript SDK, and a Model Context Protocol (MCP) server for AI agent integration. It also includes a cloud API client for remote inference. The architecture is modular: models are configurable via YAML, pipelines orchestrate multi-stage workflows, and deployment targets range from edge devices to cloud servers. The codebase is actively maintained with extensive testing, CI/CD, and support for multiple hardware accelerators (GPU, NPU, XPU, etc.). While primarily an application toolkit, it also contains research-grade training infrastructure, custom loss functions, and data augmentation modules, making it a hybrid project with a strong application focus.
The Front-End Checklist is a comprehensive, open-source platform for front-end quality assurance, targeting both human developers and AI agents. It delivers a curated corpus of 386+ best-practice rules across 11 categories (HTML, CSS, JavaScript, Performance, Accessibility, SEO, Security, Images, Testing, Privacy, i18n) via a Next.js web application, a Model Context Protocol (MCP) server, and a standalone CLI. The architecture is a pnpm monorepo with shared packages for authentication (Better Auth + Prisma), design system (Radix UI), analytics (OpenPanel), state management (Zustand), search (FlexSearch), storage (IndexedDB), and validation. The MCP server exposes 11 tools (audit_url, review_code, search_rules, etc.) for AI-assisted code review and URL auditing, while the CLI provides offline audit capabilities. The web app offers rule browsing, user checklists with progress tracking, guides, and public profiles. The system is production-deployed on Vercel with PostgreSQL, Sentry error tracking, and Upstash rate limiting.
This is the official Python SDK for the Model Context Protocol (MCP), a protocol for integrating AI models with external tools, resources, and prompts. The SDK provides both a high-level decorator-based API (MCPServer) and a low-level handler-based API (Server) for building MCP servers, along with a full client implementation (Client) for connecting to servers. It supports multiple transports (stdio, SSE, streamable HTTP), OAuth 2.0 authentication, caching, subscriptions, progress reporting, structured output, and an extension system. The codebase is well-structured with clean separation of concerns, extensive test coverage (unit, integration, documentation-sourced), and reusable patterns for authentication, caching, path security, and URI template parsing. It is actively maintained with recent commits and a comprehensive CI pipeline.
CodeBurn is a local-first, cross-platform observability and cost management tool for AI coding assistants. It reads session logs from 40+ AI tools (Claude Code, Cursor, Copilot, Codex, Gemini, etc.) directly from the user's local disk, parses them, and attributes costs using a bundled pricing engine with fallbacks. The architecture is a modular monolith with a core TypeScript CLI engine and multiple platform-specific frontends (Electron desktop, Swift macOS menubar, Tauri Windows/Linux tray, VS Code extension, MCP server, and GNOME extension). The codebase demonstrates exceptional engineering discipline. It features a sophisticated versioned cache with cross-process locks and progressive hydration, a clean provider adapter pattern for ingesting heterogeneous data sources, and a robust quota monitoring system with strict error handling and credential safety. The test suite is extensive, covering parser edge cases, cache correctness, and cross-platform parity. The project is actively maintained with frequent releases and a large community (11k+ stars). The primary risk is the volatility of the external AI tool APIs it depends on for quota tracking and log formats, but the code is structured to handle this through its adapter pattern and comprehensive testing. It requires Node.js 22.13+.
Visual-explainer is an agent skill that transforms complex technical output into polished, self-contained HTML pages. It serves as a plugin for AI coding agents (Claude Code, Pi, Cursor, Antigravity, Codex, OpenCode, MCP hosts) to generate diagrams, diff reviews, plan reviews, slide decks, narrated videos, and data tables instead of ASCII art. The architecture is modular: a core skill definition (`SKILL.md`) provides workflow and design rules, while separate subsystems handle plan rendering (`plan/render.mjs`), quick-mode JSON-to-HTML conversion (`quick/render.mjs`), a local stdio MCP server (`mcp/server.mjs`), a best-effort PPTX exporter (`pptx/export.mjs`), and a Playwright-based video renderer (`video/render.mjs`). The Pi agent integration includes a native TypeScript extension (`extension.ts`) with `prepare`, `render`, and `render_quick` actions. The codebase demonstrates high craftsmanship with thorough input validation, security-conscious file handling (symlink rejection, atomic writes, output jail), clear error messages, and extensive documentation. The plan renderer is particularly notable as a zero-dependency HTML generator that validates plan structure, reads cited code from disk, and produces interactive pages with decision trees, comments, and keyboard navigation. The quick renderer validates JSON specs against a JSON Schema and produces complete HTML. The MCP server follows the Model Context Protocol strictly and exposes tools, prompts, and resources without calling an LLM or starting an HTTP listener. The video renderer uses Playwright to drive a virtual clock, ensuring frame-perfect timing. The repository is actively maintained with recent commits, a detailed changelog, and version consistency checks across all metadata files.
Repomix is a multi-interface tool that packs code repositories into a single AI-optimized file for consumption by large language models (LLMs) like ChatGPT, Claude, and Gemini. It operates as a CLI tool, a library, an MCP (Model Context Protocol) server, a GitHub Action, a browser extension, and a web service. The core pipeline discovers files respecting ignore patterns, reads them with binary and encoding detection, optionally compresses code via tree-sitter (removing implementation details while preserving signatures), scans for secrets with Secretlint, and generates output in XML, Markdown, JSON, or plain text formats. It also provides token counting with configurable encodings and disk-backed caching, git integration (diffs, logs, change-frequency sorting), and skill generation for Claude Agent. Architecturally, the project is modular with a clear separation between the core library (src/core/), CLI interface (src/cli/), MCP server (src/mcp/), website (website/), and browser extension (browser/). The core uses dependency injection for testability, worker threads (tinypool) for parallel file processing and metrics, and a strategy pattern for language-specific tree-sitter parsing. Configuration is loaded from JSON/JS/TS files and merged with CLI options. The codebase demonstrates strong engineering practices including comprehensive test coverage, security hardening (SSRF protection, git command sanitization, sandboxed MCP tools), and performance optimizations (token count cache, bounded concurrency, fast binary detection). The project is actively maintained with frequent releases, a large community (28k+ stars), and extensive documentation in 15 languages. While the core is well-architected, the multiple distribution channels and large dependency surface introduce maintenance overhead. Some duplication exists between the website and CLI validation logic, and the tree-sitter WASM management is fragile. Overall, it is a high-quality, production-ready tool with several reusable components.
peon-ping is a cross-platform sound and notification system for AI coding assistants, intercepting lifecycle events from tools like Claude Code, Cursor, Copilot, and Gemini to play contextual audio feedback (e.g., Warcraft Peon voice lines) and show desktop notifications. The architecture consists of a core hook script (`peon.sh` on Unix, `peon.ps1` embedded in `install.ps1` on Windows), a set of thin adapter scripts that translate each IDE's native event format into a canonical CESP JSON schema, and an MCP server (`mcp/peon-mcp.js`) enabling agents to trigger sounds programmatically. Key data flows: adapter receives an event → pipes JSON to peon.sh → parses config/state → resolves sound pack via override hierarchy → plays audio via platform-appropriate backend → shows notification via overlay or toast. External dependencies include system audio players (afplay, pw-play, ffplay, etc.), ElevenLabs/MiniMax TTS APIs, ntfy.sh/Pushover/Telegram for mobile notifications, and a remote pack registry. The project also includes a trainer mode for exercise reminders, structured debug logging (ADR-002), and an automated agent-driven project management system (gitban) for its own development. Reusable components include the MCP server (can be extracted as a standalone tool), the Windows audio playback module with fallback chain (`scripts/win-play.ps1`), and the TypeScript utilities for debounce/spam detection (`peon-ping-internals.ts`). The adapter pattern is well-documented and could be replicated for new IDEs. The project is actively maintained with frequent commits, comprehensive multi-language tests (BATS, Pester, Vitest), and clear separation of concerns despite the complexity of supporting 20+ IDE integrations.
Oh-My-ClaudeCode (OMC) is a multi-agent orchestration layer for Claude Code, Anthropic's AI coding assistant. It extends Claude Code with a plugin system, custom MCP tools, a team collaboration engine, a real-time HUD, and a rich hook system. The system is implemented in TypeScript and runs as a CLI tool (`omc`), an npm package (`oh-my-claude-sisyphus`), and a Claude Code plugin. It manages autonomous coding pipelines (autopilot, ralph), multi-worker team sessions via tmux, skill learning and injection, and provides extensive tooling including LSP integration, AST analysis, Python REPL, and git-based checkpoints. Architecturally, OMC is a modular monolith with clear separation: a CLI entry point (Commander-based), a hook registry with ~20+ lifecycle hooks (session-end, pre-tool-use, persistent-mode, etc.), a team subsystem with state machines and tmux-based worker management, a HUD rendering engine, and a standalone MCP server exposing 33+ tools. The system integrates with multiple AI providers (Claude, Codex, Gemini, Grok, Cursor) and git hosting providers (GitHub, GitLab, Azure DevOps, Bitbucket, Gitea). External dependencies include `@anthropic-ai/claude-agent-sdk`, `@modelcontextprotocol/sdk`, `better-sqlite3`, `zod`, and `commander`. Key data flows include: user input → CLI or Claude Code hook → hook dispatcher → feature modules (autopilot, team, skills) → tool execution → state persistence (filesystem, SQLite). The system maintains extensive state on disk (`.omc/state/`, session transcripts, team events, skill files) and uses file-based locking for concurrency safety. The JEV shadow judgment system provides non-blocking evaluation of heuristic decisions against an external API for quality monitoring. The codebase demonstrates strong engineering practices: extensive test coverage (~3000+ tests), modular architecture with clear interfaces, atomic file operations, and security-conscious utilities (SSRF guard, token redaction, path traversal prevention). It is actively maintained with frequent releases and responsive issue triage.
QMD (Quick Markdown Search) is a local-first, on-device hybrid search engine for markdown files, built as a CLI tool, a TypeScript SDK, and an MCP (Model Context Protocol) server. It indexes markdown documents and supports BM25 full-text search via SQLite FTS5, vector semantic search via sqlite-vec, LLM-based query expansion (using a fine-tuned Qwen3-1.7B model), and cross-encoder reranking. The architecture is a monolithic TypeScript module with clear separation of concerns: a core store layer handling indexing and retrieval, a config-driven collection system with YAML-based index definitions, a trust-gated security model for project-local configurations, and output formatters supporting JSON, CSV, Markdown, and XML. The project also includes a fine-tuning pipeline (Python-based SFT, GRPO) to train the query expansion model, with curated training data and evaluation benchmarks. The repository has a hybrid character: while its primary output is a production-ready application (CLI + MCP server), it contains a substantial data-research component in the `finetune/` directory with training scripts, dataset generation, reward functions, and model evaluation harnesses. The fine-tuning pipeline is tightly coupled to the main application's query expansion feature, making this more than a simple add-on – it is integral to the search quality. The code demonstrates strong engineering practices: content-addressable storage for deduplication, AST-aware chunking for code files, reciprocal rank fusion for multi-signal search, and a cross-runtime SQLite abstraction that runs on both Node.js and Bun. The project is actively maintained with CI/CD on GitHub Actions, Nix flake builds, and npm publishing. Key entry points include `src/cli/qmd.ts` (CLI dispatcher), `src/store.ts` (core data layer), `src/mcp/server.ts` (MCP server), and `finetune/train.py` (training pipeline). The system is designed for personal knowledge management and AI agent integration, offering a `qmd search` command for quick lookups and an MCP server exposing tools like `query`, `get`, and `multi_get` for agent consumption. Security is a first-class concern: project-local configs that declare hooks or out-of-project paths require explicit trust approval via a digest-based store, and the HTTP MCP server includes DNS-rebinding protection.
Kami is a locally installed AI-agent skill and plugin for professional document generation, aimed at Claude Code, Codex, Cursor, and MCP-capable agents. It is not a hosted service: agents invoke it through natural language, and the skill orchestrates a deterministic pipeline that validates structured content, fills self-contained HTML templates, renders PDFs via WeasyPrint, optionally exports PPTX or Marp slides, and runs a battery of quality gates before declaring a document deliverable. The repo also ships a zero-dependency MCP stdio server exposing tools such as kami_templates, kami_render, kami_check, and kami_screenshot.
This is a monorepo for managing a curated catalog of 'skills'—packaged markdown instructions that extend AI coding agents (Cursor, Claude Code, Copilot). It provides three main surfaces: a CLI (Ink/React TUI) for installing/updating/removing skills, an MCP server (Model Context Protocol) for agent-native access, and a Next.js marketplace for browsing. The core library implements a clean port/adapter pattern for filesystem, HTTP, shell, and environment operations, with a robust lockfile system, content-hash verification, and CDN-based registry distribution. The codebase is well-structured, well-tested, and actively maintained, demonstrating high craftsmanship in dependency injection, state management, and progressive disclosure patterns.
Skybridge is a production-grade, full-stack TypeScript framework for building interactive MCP (Model Context Protocol) Apps and ChatGPT Apps. It provides a unified runtime to develop server-side tools with rich React-based UI views that render inside AI chat hosts like ChatGPT, Claude, Cursor, and VSCode. The framework is structured as a monorepo with packages for the core server/client library (`skybridge`), a Vite plugin for build orchestration, a developer tools SPA for local debugging, a project scaffolding CLI (`create-skybridge`), and an eval/test harness. The architecture centers on a typed MCP server implementation that handles tool registration, per-tool OAuth 2.1 authentication, an onion-model middleware system, and view resource serving. On the client side, a bridge abstraction (HostAdaptor) normalizes communication across different host protocols (OpenAI Apps SDK vs. MCP App JSON-RPC), while React hooks provide type-safe access to tool calls, view state, user context, and display modes. The framework emphasizes a 'reason, then render' two-phase pattern: a tool call computes data, then a view displays it interactively. Extensive examples cover e-commerce, games, authentication, productivity dashboards, and generative UI, demonstrating the framework's flexibility. Skybridge is not a data research project; it is a developer toolchain for building agent-native applications.
Graphify is a CLI tool and library that extracts structural and semantic knowledge graphs from source code across 36+ programming languages. It parses files using tree-sitter grammars, builds a graph of nodes (functions, classes, modules, etc.) and edges (calls, imports, inheritance, etc.), performs community detection via Leiden/Louvain, and generates reports, wikis, and exports to formats like Obsidian, Neo4j, and FalkorDB. The system integrates with AI coding assistants through an MCP server (stdio/HTTP), skill files (SKILL.md, CLAUDE.md), and git hooks for automatic graph updates. Key entry points include `graphify extract`, `graphify query`, `graphify serve`, and `graphify install`. External dependencies include tree-sitter grammars, LLM APIs (OpenAI, Anthropic, Gemini, Ollama), and optional databases. The architecture is modular: per-language extractors in `graphify/extractors/`, graph assembly in `build.py`, clustering in `cluster.py`, and export in `export.py`. The codebase demonstrates strong engineering practices with extensive tests, atomic file writes, security validation (SSRF, path traversal), and cross-platform support.