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.
This repository implements a production-grade Model Context Protocol (MCP) server that exposes GitHub's REST and GraphQL APIs as a collection of tools, resources, and prompts for AI agents. The server runs in either stdio (local CLI) or HTTP (remote) mode, supporting multiple authentication methods: personal access tokens, OAuth 2.1 (PKCE browser flow, device flow, manual fallback), and GitHub App installation tokens. It provides over 90 fine-grained tools organized into toolsets (issues, pull requests, actions, projects, code scanning, etc.), each with metadata including required OAuth scopes, feature flags, read-only hints, and information flow control (IFC) labels. The architecture is modular: a central inventory builder registers all tools, resources, and prompts; per-request filtering narrows availability based on authentication, feature flags, toolsets, and read-only mode. The HTTP server uses a chi router with middleware for CORS, body limits, token extraction, scope challenge, and MCP method parsing. A React-based UI (Primer components) provides sandboxed forms for creating and editing issues and pull requests, served as embedded HTML resources. The server also includes lockdown mode for prompt injection mitigation, sanitization of user-authored content, field filtering to reduce response size, and telemetry for metrics collection. External dependencies include the MCP Go SDK, go-github (REST), shurcooL/githubv4 (GraphQL), and various utility libraries for OAuth, HTML sanitization, and configuration.
This repository implements an MCP (Model Context Protocol) server that exposes Chrome DevTools capabilities as tools for AI coding assistants. In production, it launches a headless or headed Chrome browser via Puppeteer, connects to the DevTools frontend SDK, and provides over 50 tools covering navigation, input automation, network inspection, performance tracing, heap snapshot analysis, CSS inspection, accessibility auditing (via Lighthouse), PWA management, and extension debugging. The architecture is a Node.js server that runs either as a long-lived daemon (Unix socket IPC) or as a CLI tool, with a configuration pipeline supporting CLI flags, config files, and environment variables. Key entry points are `src/bin/chrome-devtools-mcp.ts` (MCP server) and `src/bin/chrome-devtools.ts` (standalone CLI). Data flows involve collecting console messages, network requests, and DevTools issues per page via `PageCollector`, processing performance traces via `ChunkedTraceParser` and `PerformanceTrace`, and formatting results through specialized formatters (`ConsoleFormatter`, `CssFormatter`, `HeapSnapshotFormatter`, etc.) that support both text and structured JSON output. External dependencies include Puppeteer for browser control, the DevTools frontend SDK for advanced features (heap snapshots, stack traces), Lighthouse for audits, and a telemetry system (Clearcut) for usage statistics.
OpenCLI is a large-scale CLI framework that provides over 100 structured commands for interacting with diverse web services (social media, e-commerce, finance, academic databases, AI tools, etc.) via browser automation or direct HTTP APIs. It is designed for AI agents and developers who need deterministic, machine-readable access to websites. The architecture centers on a command registry pattern where each command declares metadata (site, name, access level, auth strategy, arguments, output columns) and either a function or a declarative pipeline of steps (navigate, evaluate, map, filter, sort, limit). Authentication is handled per-site via a shared helper that registers login/whoami commands. The tool manages browser sessions through a Chrome extension (Browser Bridge) and CDP, with a daemon for persistent connections. It includes a plugin system, shell completion, observation/tracing with redaction, and a skill system for AI agent documentation. The codebase is actively maintained with frequent releases, extensive unit tests, and e2e tests, but its heavy reliance on site-specific DOM selectors and API endpoints introduces fragility and maintenance burden.
This repository is a curated collection of 177+ domain-specific scientific 'skills' for AI agents, following the Agent Skills standard. Each skill is a self-contained module providing a CLI tool, documentation, and tests for a specific scientific or technical task—ranging from single-cell RNA-seq analysis (scanpy) and molecular docking (diffdock) to clinical report validation and ISO standards readiness. The architecture is a monorepo of independent skills, each with its own scripts/, references/, assets/, and tests/. Skills are designed to be safe, bounded, and reproducible: they validate inputs before execution, enforce resource limits, avoid network access unless explicitly required, and produce structured JSON reports. The repository also includes a shared test infrastructure (skill_contract) and a meta-skill (autoskill) that can automatically propose new skills from screen activity. While primarily an application library for AI agents, it has strong data/research characteristics due to its heavy use of scientific data formats and validation of research artifacts.
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.
This repository is a monorepo of 'skills' for the Minis AI assistant platform, designed to extend the assistant's capabilities with domain-specific workflows, API integrations, and automation scripts. Each skill is a self-contained directory with a SKILL.md (instruction set for the AI), executable scripts (Python/shell), reference documentation, and evaluation test cases. The skills cover a wide range of tasks: social media management (Weibo, Twitter/X, Xiaohongshu, Telegram, Bilibili), media processing (YouTube downloader, PDF conversion, TTS, image generation), financial data retrieval (US/Korea/China stocks, fund flows), productivity (Notion API, todoocard e-paper, whenpeak energy prediction), video composition (HyperFrames framework), and system utilities (Android dev environment, Cloudflare DNS, qBittorrent). The architecture is modular and agent-driven: the AI selects a skill based on user intent, reads its SKILL.md, and invokes the provided scripts via shell_execute. Output is typically JSON for machine consumption. The codebase demonstrates strong engineering practices with structured skill definitions, evaluation frameworks, and reusable patterns like cookie-based auth, SQLite message stores, and deterministic animation analysis. However, many skills depend on reverse-engineered or unofficial APIs, hardcoded paths tied to the Minis iOS environment, and external tools (ffmpeg, pandoc, typst), introducing maintenance and portability risks.
This repository provides a Python library for converting web pages into text optimized for Large Language Model (LLM) input. It fetches HTML content using Playwright (headless browser) and processes it to extract meaningful text while preserving structural information like tables, links, and images in a text format. The core processing logic converts HTML tables to markdown, handles image and link preservation (or removal), and strips unnecessary tags (script, style) to reduce noise. The library is designed as a preprocessing step before feeding web content to LLMs for tasks such as data extraction or summarization. It includes three main modules: HTML fetching, HTML processing, and a combined convenience function.