aicommits is a CLI tool that automatically generates git commit messages using AI. It supports multiple AI providers (OpenAI, Together AI, Groq, xAI, Ollama, LM Studio, OpenRouter, and custom OpenAI-compatible endpoints) and offers both agentic generation (using tool-calling LLMs) and one-shot fallback for models that don't support tools. The tool reads staged git diffs, sends them to the configured LLM, and produces commit messages in various formats (plain, conventional commits, gitmoji, subject+body). It includes a git hook for seamless integration, a PR generation feature, config management, auto-update, and a VS Code extension. The architecture is a monolith CLI application built with TypeScript, using cleye for argument parsing, @clack/prompts for interactive prompts, and the Vercel AI SDK for LLM interactions. The codebase is well-structured with extensive tests, modern TypeScript practices, and careful handling of edge cases like large diffs, model fallbacks, and timeout management.
This repository is a pnpm monorepo for @stylistic/eslint-plugin, a community-maintained ESLint plugin that provides formatting and stylistic rules for JavaScript, TypeScript, JSX, and related syntaxes. It ports formatting rules that were deprecated or removed from ESLint core and typescript-eslint, giving users a drop-in path to continue enforcing style conventions. The main deliverable is an npm library consumed through ESLint flat config; there is no server, database, or runtime application. The plugin exposes roughly a hundred rules, each with typed options, autofix support, parser-specific test coverage, and generated metadata and type declarations.
Agent Flow is a real-time visualization tool for monitoring AI agent orchestration, specifically designed for Claude Code and Codex sessions. It captures agent events via hook scripts and file tailing, processes them through a simulation layer, and renders an interactive node graph showing agent relationships, tool calls, discoveries, and performance metrics. The system comprises three main components: a VS Code extension for editor integration, a standalone Node.js server for direct use, and a Next.js-based web application serving as the core visualization frontend. Events are transmitted via Server-Sent Events (SSE) from a relay server to the frontend, which uses React with Tailwind CSS and d3-force for physics-based layout. Key features include live monitoring, timeline scrubbing, session replay, file attention tracking, token usage visualization, and stress testing scenarios. The architecture emphasizes performance through ref-based state management, memoized computations, and virtualized lists for handling large event logs.
gh-stack is a GitHub CLI extension for managing stacked pull requests. It allows developers to create a stack of branches, each building on the previous one, and submit them as a chain of PRs. The tool handles rebasing, syncing, pushing, and merging the stack atomically, with both interactive TUI and non-interactive CLI modes. The architecture is a Go CLI built with Cobra, using Bubble Tea for interactive TUI components and lipgloss for styling. Git operations are abstracted behind an interface (internal/git/gitops.go) with mock support for testing. GitHub API integration is handled via go-gh, supporting GraphQL and REST endpoints for PR creation, stack management, and async merge. Local stack state is persisted as a JSON file in the git directory with optimistic concurrency and file locking. Key entry points include main.go calling cmd.Execute(), which registers all subcommands (init, add, submit, sync, rebase, push, merge, checkout, etc.). External dependencies include the GitHub CLI (gh), git, and the GitHub API. The codebase demonstrates strong engineering practices with extensive test coverage, interface-based mocking, and a modular internal package structure.
dotnet-claude-kit is an opinionated Claude Code plugin that transforms the AI assistant into an expert .NET 10 developer. It provides 47 skills (knowledge + workflow orchestrators), 10 specialist agents (e.g., dotnet-architect, ef-core-specialist), 10 always-loaded rules, 5 project templates, automation hooks, and a Roslyn-based MCP server (CWM.RoslynNavigator) offering 22 read-only code analysis tools. The MCP server delivers token-efficient semantic queries (symbol resolution, anti-pattern detection, dead code analysis, dependency graphs) via stdio, replacing expensive file reads. The architecture is modular: skills are markdown files loaded on demand, agents route requests to specialists, and the MCP server provides a robust program analysis backend. The system supports multiple AI coding tools (Claude Code, Cursor, Codex CLI, OpenCode) with cross-tool rule parity validation. Its core philosophy emphasizes guided over prescriptive development, modern .NET only (.NET 10/C# 14), and token-conscious interactions. The codebase demonstrates strong engineering with clean abstractions, extensive unit tests (200+ tests), CI/CD for NuGet publishing, and well-documented ADRs. The MCP server components (WorkspaceManager, SymbolResolver, anti-pattern detectors, pagination) are highly reusable and exhibit non-obvious craftsmanship. While the large skill surface requires synchronization, the overall quality is excellent for a developer tooling project.
CC Switch is a desktop application built with Tauri (Rust backend + React/TypeScript frontend) that serves as a unified management hub for multiple AI coding assistants, including Claude Code, Claude Desktop, Codex, Gemini CLI, Grok Build, OpenCode, OpenClaw, and Hermes Agent. Its core function is provider switching: it manages configurations, API keys, OAuth tokens, and MCP servers across these tools, and provides a local HTTP proxy that routes API requests to different AI providers with failover, circuit breaking, and usage tracking. The application also includes session management, skills/prompts synchronization, cloud sync (S3/WebDAV), deep link import/export, and a usage dashboard with cost tracking. The architecture follows a command-service-DAO pattern in Rust, with a React frontend using TanStack Query for state management, react-hook-form for forms, and shadcn/ui components. The proxy subsystem is particularly sophisticated, implementing format conversion bridges between different AI API protocols (Anthropic Messages, OpenAI Chat/Responses, Gemini), streaming transforms, thinking budget optimization, cache injection, and content encoding handling with bomb protection. The frontend is organized around per-app provider forms, a universal provider panel, and settings pages for proxy, MCP, skills, and usage. Key features include: 50+ provider presets for third-party API relay services, one-click provider switching with live config backup/restore, a local proxy with auto-failover and circuit breaker, session history browsing across supported apps, skills installation from GitHub repos, prompt management with per-app sync, and usage statistics with custom pricing. The application supports i18n (English, Japanese, Chinese) and runs on Windows, macOS, and Linux.
OpenHands/OpenHands is the frontend application for the OpenHands AI agent platform, known as Agent Canvas. It is a React single-page application (SPA) built with Vite, TypeScript, Tailwind CSS, and React Router. The application provides a comprehensive user interface for interacting with AI coding agents (OpenHands, Claude Code, Codex, Gemini, or any ACP-compatible agent) via an agent server. It supports multiple backends (local self-hosted, cloud at app.all-hands.dev) with a backend registry that routes API calls accordingly. The UI includes a chat interface with real-time WebSocket event streaming, a conversation panel for managing multiple sessions, a file explorer with Monaco editor, terminal emulator, browser snapshot view, git integration (commits, diff viewer, push/pull), settings for LLM profiles, MCP servers, secrets, skills/plugins, and an automation dashboard for scheduled or event-driven agent runs. The application is also published as an npm package (@openhands/agent-canvas) for embedding in other applications, and supports Electron desktop builds. The architecture follows a modern React pattern with Zustand for client-side state management (conversations, events, UI preferences), TanStack React Query for server-state caching and synchronization, and react-i18next for internationalization. The backend abstraction layer is a key architectural feature: every service (settings, profiles, git, secrets, automations, etc.) branches on the active backend kind (local vs cloud) and delegates to either a direct SDK client (@openhands/typescript-client) or a cloud proxy (callCloudProxy). This dual-transport pattern is enforced by guard tests that prevent ad-hoc HTTP calls outside vetted files. The application also includes a manifest system for declarative automation setup, a tool visualizer registry for rendering agent tool calls (bash, file editor, search, task), and extensive mock infrastructure (MSW) for development and testing. Key entry points include the root layout (src/routes/root-layout.tsx) which provides the main shell with sidebar, command menu, and onboarding; the conversation main view (src/components/features/conversation/conversation-main/conversation-main.tsx) with resizable panels for chat and tabs; the settings pages (src/routes/settings.tsx) with schema-driven forms; and the automation dashboard (src/routes/automations-list.tsx). External dependencies include the agent server REST API, cloud proxy endpoints, @openhands/typescript-client SDK, @openhands/extensions for automation catalogs, and various UI libraries (HeroUI, framer-motion, xterm.js, Monaco editor). The codebase is actively maintained with over 84k stars, frequent commits, and a large test suite (Vitest unit tests, Playwright E2E tests, Stryker mutation testing).
Pixel Agents is a developer tool that visualizes AI coding agents (primarily Claude Code) as animated pixel-art characters in a virtual office environment. It ships as both a VS Code extension and a standalone CLI (`npx pixel-agents`), sharing a common runtime. The system monitors agent sessions in real-time via HTTP hooks (preferred) or JSONL file polling (fallback), normalizes events through a provider abstraction, and renders agent state (tool usage, context tokens, team structures, permissions) on a Canvas-based pixel-art office map. The architecture follows a hub-and-spoke pattern: a Fastify HTTP/WebSocket server aggregates agent activity, an AgentRuntime manages lifecycle and state, and a MessageTransport abstraction (PostMessage for VS Code, WebSocket for standalone) broadcasts updates to the React 19 + Canvas webview UI. The codebase is well-structured with clean interfaces (HookProvider, TeamProvider, StateAdapter), extensive test coverage (unit, integration, and Playwright e2e with a mock Claude CLI), and CI-enforced contract drift detection (AsyncAPI spec ↔ generated TypeScript, e2e inventory). While only the Claude provider ships, the provider registry is designed for multi-CLI support. The project demonstrates strong engineering practices with some complexity risks in dual-mode detection, consent flow edge cases, and cross-platform path handling.
Kache is a build cache system for Rust and C/C++ that acts as a transparent compiler wrapper (via RUSTC_WRAPPER or as a drop-in for cc/c++). It caches compilation artifacts using content-addressed storage with Blake3 hashing, enabling zero-copy restoration via reflinks/hardlinks/copies. The system features a daemon for asynchronous remote operations (S3/filesystem), a CLI/TUI for cache management and monitoring, and advanced capabilities like dependency chain analysis for cache misses, extra inputs for user-defined cache key influences, and predictive prefetching. Architecture-wise, it consists of a compiler wrapper core, a background daemon, a remote planning service (kache-service), and extensive testing/benchmarking harnesses. The code demonstrates strong craftsmanship in areas like cache key normalization, zero-copy restoration strategies, and compiler abstraction patterns.
CodeGraph is a Python command-line tool that performs static analysis on Python source code to generate dependency graphs. It parses Python files to extract functions, classes, and import statements, then builds a graph showing how these entities depend on each other. The tool outputs an interactive HTML visualization (using D3.js by default) or can export the data to CSV or print it to the console. The architecture is modular, consisting of a parser (using Python's tokenize module), a core module that builds the dependency graph, utility functions for file discovery, and a visualizer that supports both D3.js (interactive) and matplotlib (legacy) backends. The tool does not execute the code being analyzed, making it safe and fast for large codebases. Key strengths include a robust parser that handles various import styles and class inheritance, and a flexible visualization system that provides features like search, collapsing/expanding nodes, and detailed tooltips. The project is actively maintained with comprehensive tests and supports multiple Python versions.
This repository is a collection of specialized 'Skills' for the Claude AI assistant, each designed to enhance Claude's capabilities for specific professional tasks. The McKinsey Consultant Skill implements McKinsey's Problem Solving methodology to guide users through structured business analysis and generate professional PowerPoint presentations. The Mimeng Writing Skill helps create viral Chinese-style articles by encoding specific writing techniques. The Find-session Skill assists in locating and resuming specific Claude Code conversations through grep-based search of conversation history. The US Government Shutdown Tracker Skill fetches and analyzes economic data from the FRED API to assess liquidity impacts of government shutdowns, generating visualizations and status assessments. The repository demonstrates thoughtful architecture, particularly in the McKinsey Consultant Skill's progressive disclosure approach to manage Claude's context limitations, and contains several reusable components for PPT styling, economic data analysis, and visualization.
The UTCP-MCP Bridge is a multi-language implementation that exposes Universal Tool Calling Protocol (UTCP) tools as Model Context Protocol (MCP) tools, enabling MCP clients like Claude Desktop to discover and call any UTCP-registered tool. The system consists of MCP servers (in Node.js/TypeScript, Python, Rust, and a web-based implementation) that initialize a UTCP client, register providers from configuration, and expose standard MCP tools for tool management (register/deregister manuals, call tools, search tools, list tools, get tool info, and get required variables). The architecture cleanly separates MCP server concerns from UTCP client operations, with each language implementation following similar patterns but idiomatic to its ecosystem. The bridge handles MCP specification nuances like proper content block preservation for binary data and provides dynamic provider management through REST APIs in the web UI.
This repository is not a traditional application but a distribution and runtime for 'Superpowers' – a collection of structured skill definitions (markdown files with YAML frontmatter) that shape the behavior of AI coding agents (Claude Code, Codex, Gemini CLI, etc.). The core product is a set of carefully crafted instructions (e.g., subagent-driven development, brainstorming, systematic debugging, test-driven development) plus per-harness bootstrap injection scripts, plugin manifests, and a small zero-dependency visual companion server. The project's architecture is a multi-harness plugin system: each agent platform gets a plugin manifest and a session-start hook that injects the bootstrap skill, enabling the agent to invoke Superpowers skills via a 'Skill' tool or native equivalents. The repository demonstrates high engineering craftsmanship in its skill design (rationalization tables, Red Flags, evidence-driven iteration) and in the accompanying scripts (polyglot hook runner, secure WebSocket server, worktree isolation). It is actively maintained with frequent releases and a formal design/plan/specification process. However, the primary value is in the skill content rather than reusable software components; reuse outside the Superpowers ecosystem requires adapting the bootstrap injection and tool mappings for a new harness.
Quotio is a macOS application for managing AI provider accounts and tracking quota usage. It follows a Clean Architecture with four layers: Domain (core models), Application (business logic), Infrastructure (platform services), and Presentation (SwiftUI UI). The app provides both Local Proxy Mode (running a local proxy server CLIProxyAPI) and Monitor Mode (quota-only tracking) for AI services like Claude, OpenAI Codex, GitHub Copilot, Antigravity, and others. Key features include OAuth authentication flows, secure credential storage (Keychain/YubiKey), menu bar integration, automatic updates via Sparkle, telemetry via PostHog, AI CLI tool configuration, and Cloudflare tunnel management. The application uses modern Swift concurrency, protocol-oriented programming, and actor-based state management.
cargo-careful is a Rust CLI cargo subcommand that re-runs a user's build/test/run under a specially constructed Rust toolchain. The binary in src/main.rs expects to be invoked as `cargo careful <subcommand>`, supports run, test, build, rustc, nextest, and setup, and locates the active rustc version and host target. It finds the rust-src rustup component (offering to install it interactively unless running in CI), builds a per-target/per-sanitizer sysroot in a user cache directory via the rustc_build_sysroot library, then invokes cargo with that custom sysroot and encoded RUSTFLAGS so both the sysroot and the user's crate get extra runtime checking.
Ponytail is a skill ecosystem for AI coding agents that enforces a 'lazy senior developer' mindset through a priority ladder: YAGNI, reuse existing code, prefer stdlib/native features, avoid unrequested abstractions, and write minimal working code. It delivers this via platform-specific adapters (hooks, command files, plugin manifests) for agents like Claude Code, Codex, GitHub Copilot, OpenCode, Gemini CLI, and others. The core skill definition lives in skills/ponytail/SKILL.md, with companion skills for review, audit, debt tracking, gain scoring, and help. The system includes automated validation scripts to maintain consistency across platform-specific rule copies and version manifests, benchmark suites to measure code/token/cost reductions, and test coverage for hook behavior and plugin integrity.
JSON Crack is an open-source, browser-based tool for visualizing, formatting, converting, and exploring JSON, YAML, CSV, and XML data as interactive graphs. The monorepo (Turborepo) contains four workspaces: a Next.js web app (apps/www) that provides the full editor experience with a Monaco-based text editor, split-view layout, graph canvas, and various utility modals (jq, JSONPath, schema validation, code generation); a VS Code extension (apps/vscode) that embeds the same graph view as a webview panel; a Chrome extension (apps/chrome-extension) that injects a 'Raw'/'Graph' toggle on any JSON page; and a reusable React component package (packages/jsoncrack-react) that exposes `JSONCrack` as a standalone component along with a `parseGraph` utility and TypeScript types. All data processing happens client-side — the app is a fully static Next.js export served behind NGINX. The architecture is frontend-only, relying on Zustand for state, reaflow for graph layout, react-zoomable-ui for pannable/zoomable canvas, and jsonc-parser for AST-driven parsing. The codebase is well-organized, with clear separation of concerns, good TypeScript coverage, and unit tests in the core package.
Agno is a Python framework for building, orchestrating, and deploying AI agents. It provides a unified abstraction over dozens of LLM providers (OpenAI, Anthropic, Gemini, Groq, DeepSeek, etc.) and supports rich tool integration, multi-agent teams, workflow engines, RAG knowledge bases, persistent session storage, and human-in-the-loop patterns. The architecture centers on core classes: `Agent`, `Team`, `Workflow`, `Knowledge`, and `Toolkit`, all composable through a consistent configuration interface. Agents can be served via the `AgentOS` runtime, which exposes REST, MCP, A2A, Slack, and WhatsApp endpoints with JWT-based auth, scheduling, and observability. The framework includes a comprehensive evaluation suite (`AccuracyEval`, `PerformanceEval`, `ReliabilityEval`), a learning machine for persistent user profiling and memory, and an environments module for reproducible agent rollouts and scorer-based export. While primarily an application framework, it also exhibits data/research characteristics through its evaluation infrastructure, knowledge chunking/embedding pipelines, and systematic experiment tooling. The extensive cookbook (300+ examples) doubles as integration tests, demonstrating patterns ranging from simple single-agent tasks to complex distributed teams and nested workflows. Key entry points include `agno.agent.Agent`, `agno.team.Team`, `agno.workflow.Workflow`, `agno.os.AgentOS` (`agno serve`), and the `agno` CLI. The codebase is large and actively maintained, with a broad integration surface across models, vector databases, storage backends, and third-party tools. Technical drift is moderate, with some experimental model wrappers and rapidly evolving model IDs that may require updates.
DevToys is a cross-platform desktop application that bundles over 30 developer utilities (JSON formatter, Base64 encoder/decoder, hash generator, regex tester, etc.) into a single interface. The application uses an embedded Blazor WebView for its UI, enabling a modern web-like component model with rich editors (Monaco Editor), responsive layouts, and platform-specific theming. It follows an MVVM architecture with MEF (Managed Extensibility Framework) for dependency injection and plugin discovery, allowing third-party extensions to add new tools. The project also includes a CLI variant and an SDK (DevToys.Api) for extension development. Architecturally, the codebase is organized into platform-specific host projects (Windows WPF, macOS AppKit, Linux GTK) that all share a common Blazor UI layer (DevToys.Blazor) and business logic (DevToys.Business, DevToys.Core). Key entry points are the native window classes (e.g., MainWindow.xaml on Windows) which initialize the Blazor WebView and MEF composition. Data flows begin with clipboard or file input, which passes through smart detection services to suggest relevant tools, then renders the tool's UI via a fluent builder API. The settings system uses typed definitions and platform-agnostic storage. External dependencies include .NET 8, Blazor, SixLabors.ImageSharp, Monaco Editor (downloaded and vendored), and several community libraries (FuzzySharp, OneOf, System.CommandLine). The codebase demonstrates strong engineering practices: extensive localization (40+ languages), accessibility features, theme support (dark/light/compact), and a comprehensive Blazor component library. While the MEF-based plugin system is functional, it relies on the legacy System.ComponentModel.Composition package, and the platform-specific implementations (e.g., file storage, clipboard) are duplicated across Windows, macOS, and Linux, posing a moderate maintenance burden.
Air is a command-line live-reload utility for Go application development. It watches a project directory for file changes, automatically rebuilds the project using a configurable build command, and restarts the resulting binary. The tool includes an embedded HTTP reverse proxy that injects a JavaScript snippet into HTML responses, enabling automatic browser reload via Server-Sent Events after each successful rebuild. It supports custom build commands, pre/post hooks, environment file loading, platform-specific build overrides, and watch rules that run commands instead of triggering a full rebuild (e.g., for frontend asset pipelines or code generation). The architecture is a single Go binary with a main event loop that uses filesystem notifications (or polling) to detect changes, spawns build processes, and manages child process lifecycle. The codebase is well-structured with clear separation of concerns: configuration parsing (runner/config.go), engine orchestration (runner/engine.go), file watching (runner/watcher.go), HTTP proxy (runner/proxy.go), and platform-specific process management (runner/util_*.go). It includes a comprehensive test suite and CI pipelines for Linux, macOS, and Windows. The proxy component, in particular, demonstrates sophisticated handling of content encoding (gzip, brotli), streaming responses (SSE, chunked transfer), and hop-by-hop header management, making it a reusable pattern for adding live-reload capabilities to any Go web application.