Reasonix is a local AI coding agent engine written in Go, providing a terminal UI, desktop application (Electron + React), and HTTP server for interacting with large language models (OpenAI, Anthropic, DeepSeek, etc.) to automate software engineering tasks. The kernel manages sessions, context windows, planning, sub-agent delegation, tool execution (file operations, shell, browser, MCP servers), and a sophisticated safety sandbox. It persists conversation history with checkpoints for undo/rewind, tracks token usage, and maintains an evidence ledger for auditing tool effects. The architecture is a monolithic Go binary with multiple frontends: a CLI/TUI, a desktop host that communicates via SSE/JSON, and a REST API server. A plugin system using the Model Context Protocol (MCP) allows extension. Separate Cloudflare Workers handle account management, forum, and crash reporting. The codebase is well-structured with a clean layered architecture (base utilities, domain contracts, state persistence, runtime agent, assembly wiring, frontends), extensive test coverage, and internal linters enforcing quality. It is actively maintained with frequent commits and professional CI/CD pipelines.
Gstack is a production-grade AI agent skill framework and headless browser automation toolchain designed for Claude Code, Codex, Cursor, and other coding agents. It provides a structured skill system (50+ slash-command skills like `/ship`, `/review`, `/plan-ceo-review`) with a resolver pipeline that generates per-host `SKILL.md` templates from TypeScript sources. The repo also contains a fully functional headless browser daemon (`browse/`) with anti-bot stealth, multi-layer prompt injection defense (canary tokens, ML classifiers, URL blocklist, envelope sentinel), CDP escape hatch, SOCKS5 proxy bridge, and secure file I/O. Additional subsystems include markdown-to-PDF generation (`make-pdf/`), iOS QA automation (`ios-qa/`), design mockup generation (`design/`), a secret redaction engine, and a cross-session knowledge base (gbrain). The codebase is unusually well-tested with extensive unit, integration, and periodic paid E2E tests against real LLM APIs. While primarily an application, it includes data pipeline components like telemetry aggregation, eval result stores, and a brain cache specification with TTL-based entities and calibration weights, making it a hybrid with strong data engineering discipline.
This repository is the openai/codex monorepo, which implements a local AI coding agent called Codex (also referred to as Codex CLI). It provides a terminal user interface (TUI), command-line interface (CLI), and a local app-server daemon that manages AI-driven coding sessions. The architecture is client-server: the TUI/CLI communicates with the local app-server via JSON-RPC over Unix sockets or WebSockets, while the exec-server handles sandboxed command execution with platform-specific security policies (macOS Seatbelt, Windows sandbox, Linux bubblewrap). The system is built entirely in Rust, with additional TypeScript and Python SDKs for programmatic access. It supports a rich extension ecosystem including plugins, skills, MCP servers, memories, and a guardian safety layer for approval workflows. The protocol layer is generated from Rust types into TypeScript schemas, ensuring type safety across the boundary. The codebase is well-structured, heavily tested, and follows modern Rust practices (async/await, trait-based abstractions, comprehensive error handling). It is not a data research project; there are no notebooks, CSV files, or ML pipelines.
This repository is a meta-application: a curated, opinionated framework of prompts ('skills') designed to govern the behavior of AI coding agents like Claude Code and GitHub Copilot Codex. It does not contain traditional application code but instead defines a structured software development methodology executed by an AI agent. The system transforms an AI agent from a simple chat interface into a disciplined, stateful development partner that plans, implements, reviews, and maintains code according to explicit workflows. The architecture is a monolith of interdependent markdown files organized into a skill hierarchy. The `ask-matt` skill acts as a router, directing user requests to the appropriate workflow. Core primitives like `grilling` (structured interview) and `domain-modeling` (glossary/ADR creation) are reused by higher-level skills. Execution engines like `implement` and `code-review` drive the actual development cycle. A key innovation is the 'stateful workspace' pattern, where the agent writes decisions to files (GLOSSARY.md, ADRs, specs) to maintain context across sessions and manage token limits. The codebase demonstrates exceptionally high craftsmanship in prompt engineering, with clear patterns for context management, sub-agent delegation, and human-in-the-loop interaction. It is actively maintained with a detailed changelog. However, its complexity is a double-edged sword: the tight coupling between skills and the reliance on specific model behavior creates a fragile ecosystem. The documented open bugs and high cognitive load for users are significant risks, preventing it from achieving an 'exceptional' rating despite its innovative design. The repository is a brilliant but brittle system for professional AI-assisted development.
OpenCode is an open-source AI coding agent platform that provides a multi-interface development environment including a desktop app (Electron), terminal UI (TUI), CLI, web console, and headless server. It integrates with numerous LLM providers (Anthropic, OpenAI, Google, Groq, etc.) and offers session management, a plugin system, file editing, shell commands, and real-time collaboration features. The architecture is a monorepo with packages for core logic, UI components, server, SDK, and integrations. Key entry points include the CLI (`opencode`), TUI, desktop app, and web console. Data flows involve session event sourcing, LLM request routing, and database persistence (SQLite locally, PlanetScale for cloud). External dependencies include Effect-TS, SolidJS, Electron, Bun, and various LLM provider APIs. The codebase demonstrates high craftsmanship with extensive use of Effect-TS for functional effect management, a well-defined plugin system, and a rich set of UI components built with SolidJS and Kobalte. It includes comprehensive testing (unit, e2e, performance benchmarks) and a robust CI/CD pipeline. However, the monorepo is large and complex, with some duplication between UI versions (v1/v2) and experimental features that may introduce drift. Overall, it is a well-engineered, actively maintained project suitable for reuse of its core patterns and components.
Codewhale is an open-source, terminal-native AI coding agent that operates as a TUI (ratatui), CLI, headless runtime, MCP server, and a web frontend. It manages full development workflows: reading repositories, editing files, running commands, reviewing changes, and orchestrating multi-agent fleets. The codebase is a Rust monorepo with ~52 crates, a Next.js website with 18+ locales, a VS Code extension, packaging for npm/Homebrew/Arch/Windows, and companion pet apps. The architecture is event-driven with a pluggable tool system, model-agnostic provider routing, session-based journaling, and a contract-based command framework. It supports dozens of LLM providers (DeepSeek, OpenAI, Anthropic, Ollama, etc.) and features sandboxed execution, telemetry with a strict no-IP privacy contract, and a plugin marketplace. The project is heavily tested with unit, integration, PTY/Cucumber, and hermetic bash tests, and enforces budgets for dead code and blocking calls.
PiDeck is an open-source Electron desktop application that serves as a comprehensive workbench for AI coding agents, primarily wrapping the `pi` coding agent and the DeepSeek Harness (DSH) backend. It provides a rich session-centric chat workspace with features including multi-project management, Git integration, a built-in terminal, voice transcription, image generation, scheduled automation tasks, a desktop pet companion, and extensive configuration options. The application supports importing sessions from other tools like Claude, Codex, Cursor, and OpenCode, and offers a web service variant for remote access. Architecturally, PiDeck follows the standard Electron pattern with a main process (Node.js services, IPC handlers, filesystem operations), a preload script for secure IPC bridging, and a renderer process built with React 19, TypeScript, Jotai for state management, and Tailwind CSS v4 with shadcn/ui-style components. The codebase is organized into `src/main/` for backend services, `src/renderer/` for the UI, and `src/shared/` for cross-process types and utilities. Key entry points include the main process index, renderer bootstrap, and numerous IPC modules that validate inputs and delegate to domain services. Data flows center on session files stored in JSONL format (for pi) or compressed JSONL (for DSH), with model catalogs, usage statistics, and configuration persisted in user data directories. The application manages multiple backends through a unified session catalog, with runtime state synchronized via IPC events and Jotai atoms. External dependencies include the pi-coding-agent CLI, DSH runtime packages, node-pty for terminal emulation, whisper.cpp for local speech-to-text, and electron-updater for cross-platform updates. The codebase demonstrates strong engineering practices with extensive unit tests (node:test), Playwright E2E tests, pure-function modules extracted for testability, and consistent IPC boundary validation patterns.
A production-grade AI coding agent (the Codex CLI) that operates as a terminal-based assistant. It provides a multi-modal, extensible platform for thread-based conversations with language models (OpenAI, Bedrock, Ollama), including sandboxed code execution, MCP tool integration, plugin/skills/hooks extension system, and state persistence via SQLite. The architecture is a Rust monorepo with a client-server split: a high-level TUI or CLI sending JSON-RPC messages to an app-server that manages session state, model routing, and execution policies. The system supports cross-platform sandboxing (Linux bubblewrap, Windows managed sandbox, macOS seatbelt) and includes comprehensive telemetry, rollout tracing, and guardian approval pipelines. It is a fork of OpenAI's Codex CLI, with significant Rust rewrite and enhanced extensibility. While the codebase exhibits strong engineering practices (extensive testing, layered configuration, well-defined protocol types, and platform-agnostic abstractions), it is a large monorepo with many interdependent crates, some legacy modules, and platform-specific workarounds that reduce overall cohesion. Key reusable components include the protocol type definition crate (with clever no-op macro optimizations for build speed), a RAII OpenTelemetry timer, a RedactedString wrapper for secret handling, and token-aware text truncation utilities.
Pi Web is a full-stack Next.js application that provides a browser-based interface for the Pi coding agent, an AI-powered coding assistant. It shares session files, configuration, and credential storage with the Pi CLI, enabling users to manage AI coding sessions, browse and edit files, run terminal commands, and configure models/plugins/skills—all from a web browser. The application is designed for local use, running on Node.js ≥22.19 and opening at 127.0.0.1:30141 by default. Architecturally, Pi Web is a Next.js 16 App Router application with React 19 client components, a comprehensive REST API layer, and real-time streaming via Server-Sent Events (SSE) for agent events and terminal output. It features a PWA with service worker support for push notifications and offline fallback, optional password authentication with HMAC-signed session tokens, and an extension system for custom UI widgets. The frontend is organized around a chat-centric workspace with resizable panels for session management, file viewing, terminal emulation, and configuration. Key capabilities include session lifecycle management (create, fork, rename, delete, branch), file browsing with syntax highlighting and previews (images, audio, video, PDF, DOCX), Git worktree support, subagent runtime for background tasks, model catalog configuration with provider presets, and internationalization (English, Simplified Chinese, Traditional Chinese). The codebase is extensively tested with over 100 test files using Node's test runner and jiti for TypeScript imports, covering both unit and integration tests for API routes, components, and utilities.
UmaDev is an AI-powered development agent that orchestrates multiple first-class AI coding CLIs (Claude Code, Codex, Grok Build, Kimi Code, OpenCode) as subprocesses, providing a unified terminal UI, governance, knowledge retrieval, and a spec-driven pipeline. It acts as a 'project manager' for AI coding agents, handling planning, execution, review, and acceptance. The architecture is a multi-crate Rust workspace with a TUI (ratatui), agent orchestration, governance engine, knowledge retrieval (BM25 + optional local embeddings), contract validation, and cross-platform process management. It is distributed via npm with platform-specific binaries. The codebase demonstrates high craftsmanship with pervasive fail-open patterns, bounded resource usage, and extensive testing. Key subsystems include a deterministic governance engine with 113 content checks, a hybrid retrieval system with CJK-aware tokenization, a cross-process run lock with boot-id liveness, and a host-owned Git commit transaction with rollback. While primarily an application, it includes a curated knowledge corpus (~400 markdown files) and an offline embedding model, giving it a hybrid character. The repository is actively maintained with a clear release pipeline and CI/CD. Notable design patterns include: fail-open governance (every check wrapped in catch_unwind), bounded file system operations (RootedDir with no-follow, size limits), circuit breaker for compaction, and source tree fingerprinting for freshness. The codebase is well-structured with clear separation of concerns across 11 crates, though some files are large hotspots (e.g., app.rs, director_loop.rs). Overall, it is a sophisticated, production-quality tool for AI-assisted software development.
Peon-ping is a cross-platform sound notification system for AI coding agents (Claude Code, Cursor, Codex, OpenCode, etc.). It intercepts agent lifecycle events (session start/stop, task complete, error, permission requests) via shell hooks and IDE-specific adapters, translates them into a standardized CESP (Coding Event Sound Pack Specification) JSON format, and plays themed sound effects with optional desktop notifications and TTS speech. The architecture is event-driven and hook-based: each IDE has a thin adapter script that pipes CESP events to a core hook script (`peon.sh` on Unix, `peon.ps1` on Windows) which performs sound selection from configurable packs, asynchronous audio playback via platform-native players, state persistence (atomic file I/O), and notification dispatch (macOS overlay, system notifications, relay for remote/SSH sessions). Additional features include a trainer (exercise reminders), an MCP server for agent-controlled sound playback, and a sound pack registry with 160+ packs. The codebase applies an adapter pattern, atomic state I/O, structured debug logging (ADR-002), and a path-rules-based pack resolution system. It is heavily tested with BATS (Unix) and Pester (Windows) suites, managed via an agent-based gitban workflow with sprint planning and code reviews. Dependencies include Python3, audio players (afplay, ffplay, pw-play, PowerShell MediaPlayer), and platform-specific notification tools. Key concerns are the monolithic hook scripts (single ~5000-line files per platform), cross-platform code duplication, and the maintenance burden of 20+ IDE adapters.
This is a monorepo for 'pi', an AI coding assistant platform. The repository contains multiple packages including a coding agent with a terminal UI (TUI), multi-provider AI integration (OpenAI, Anthropic, Google, Bedrock, Mistral, xAI, and more), a durable execution framework for conversation persistence, a protocol layer with strict CBOR encoding, and telemetry infrastructure. The coding agent supports interactive mode with session management, tool orchestration, subagents, and MCP (Model Context Protocol) integration. The architecture is a TypeScript monorepo using npm workspaces with packages for AI providers, coding agent, durable execution, protocol, telemetry, and TUI components. The AI package provides a unified interface across multiple providers with OAuth flows, model catalogs, and streaming support. The coding agent implements a TUI with themes, keybindings, and interactive components. The durable package provides event-sourced storage with SQLite and JSONL backends, session management, and compaction. The repository also includes evaluation infrastructure (Docker-based evals), benchmarks for storage and delta traversal, and telemetry for usage tracking. The codebase demonstrates strong engineering practices with clean abstractions, reusable components, and comprehensive test coverage, though some areas (durable harness, experimental services) are still evolving.
Mistral Vibe is a production-grade terminal-based AI coding agent by Mistral AI. It provides an interactive CLI powered by Textual for multi-turn LLM conversations, file editing, shell execution, and subagent delegation. The system is architected around a core agent loop that orchestrates tool calls with a permission system, session management (resume, rewind, fork), and an event-driven checkpointing mechanism for file state snapshots. It integrates with multiple LLM providers (Mistral, Anthropic, OpenAI, Vertex) via a backend adapter pattern, and supports external integrations through MCP (Model Context Protocol) servers, custom hooks, and a skill system. The codebase heavily employs layered configuration, ports/adapters for audio, notifications, and update checking, and includes an app server for IDE integration via the ACP (Agent Communication Protocol). It also features telemetry via OpenTelemetry and GrowthBook-based experiments. The repository is actively maintained with recent commits, a comprehensive test suite (>1400 tests), and CI/CD pipelines for PyPI releases and PyInstaller binaries.
DeepTide is a cross-platform terminal AI coding agent. The Rust workspace (deeptide-core, deeptide-host, deeptide-cli, deeptide-gui) implements the production agent engine: an interactive REPL session with an agent loop, tool dispatch (bash, edit, web, git, memory, MCP, LSP, vision, cron, planning), cross-provider model routing with local-first/cloud-escalation policies, cost tracking, tokens-per-second telemetry, tool usage observability, durable memory with BM25 retrieval ranking, session import/checkpoint/rewind, sensitive-file read protection, and a theme system for syntax highlighting and diffs. The CLI and GUI share a common host layer, and the npm package downloads prebuilt Rust binaries. Architecturally it is a multi-crate Rust workspace plus supporting native components: native/ds4 is a hard-forked DeepSeek V4 Flash Metal inference engine for local LLM execution, and native/dsgo is a Swift gateway that translates between Anthropic and OpenAI protocols with SSE streaming. Primary entry points are crates/deeptide-cli/src/main.rs (CLI), crates/deeptide-gui/src/main.rs (eframe/egui GUI), and bin.js (Bun launcher that delegates to @paean-ai/zero-cli). External dependencies include DeepSeek/Anthropic/OpenAI-compatible APIs, local Metal GPU inference, and GitHub Releases for binary distribution. The repo also contains 50+ self-contained HTML5 Canvas pixel-art games and Three.js showcases under samples/, which appear to be AI-generated demo content demonstrating agent output quality rather than core product code. These share heavily duplicated boilerplate (seeded RNG, localStorage save/load, bilingual i18n, screen state machines). The core Rust code is well-tested with integration tests covering routing, cost tracking, memory ranking, tool result summarization, and slash commands; live API tests are marked #[ignore]. Hybrid note: while primarily an application, it contains research-oriented elements such as memory capture benchmarks (benchmarks/auto_capture_bench.py), prompt cache layout benchmarks (benchmarks/cache_memory_bench.py), and deterministic puzzle generation algorithms with uniqueness verification.
Vibe Kanban is a full-stack, dual-deployment application (local Tauri desktop app + remote cloud service) that combines Kanban-style issue tracking with AI coding agent workspaces. The local backend is a Rust Axum server backed by SQLite, while the remote backend uses PostgreSQL with ElectricSQL for real-time sync. The system allows users to create projects, manage issues, and launch coding workspaces where AI agents (Claude, Codex, Gemini, Copilot, etc.) execute tasks on isolated branches with preview servers, git operations, and automated code review. It includes a relay tunnel system for remote host pairing, a WebRTC transport for low-latency streaming, and an MCP server for external tool integration. The frontend is built with React, Tailwind CSS, and a shared component library, supporting localization in 7 languages. The project is officially sunsetting, as stated in the README, but the codebase remains a substantial example of a modern Rust/TypeScript monorepo with real-time collaboration, AI executor abstraction, and multi-platform delivery.
SuperCoder is a local-first, open-source AI coding agent with a desktop application (Tauri + Rust + React) and a suite of backend services. The core agent (Rust crate) provides an LLM-driven loop with tool execution (file editing, bash, git, code search), subagent spawning, and an 'Auto' mode where an orchestrator LLM generates plans executed by worker agents. The desktop app offers a rich UI for agent interaction, diff review, file exploration, and permission management. A separate Go-based 'Context Engine' service indexes codebases into vector (Qdrant), graph (FalkorDB), and text stores, enabling semantic code search, dependency analysis, and automated PR review with risk scoring. The repository also includes a legacy v1 backend (Go) with workflow executors for Django/Flask/Next.js code generation and a workspace service for managing isolated development environments. While primarily an application, the context engine introduces data/research elements through its indexing pipelines, retrieval strategies, and code review analytics.
Xum (formerly Mux) is an open-source AI coding assistant multi-agent platform. Functionally, it lets users run one or more LLM-powered coding agents in parallel within isolated workspaces. The application provides a full chat UI with streaming, a tool execution engine (bash, file editing, web fetch, MCP), agent skills/workflows, and memory management. It supports multiple AI providers (Anthropic, OpenAI, Google, etc.) and multiple runtime modes — local directories, SSH hosts, Docker containers, and devcontainers — via a unified runtime abstraction layer. Architecture: The system is a hybrid monolith/dual-deployment. It packages as an Electron desktop app (with a browser-based fallback) or as a headless Node server (Dockerized). Typed IPC is handled by in-house oRPC over WebSocket/MessagePort. Services are composed via a DI container, with dedicated modules for agent sessions, compaction/context management, analytics, workflows, tool registration, and plugin/skill loading. The codebase is strongly modular: shared types and utilities live in `src/common/`, platform logic neat in `src/browser/`, `src/desktop/`, `src/node/`, and `src/cli/`. The VS Code extension in `vscode/` uses shared UI primitives. Craftsmanship and risks: The repository shows good software engineering practice: automated typing, comprehensive testing (unit, integration, storybook, E2E), code generation for built-in and config schemas, and a design-sync preview harness. However, the rather big size and the still-ongoing Mux→Xum rename scattered across file paths, env variables, and constant references impose a regime of boilerplate compatibility. Some UI tests are brittle (asserting specific Tailwind classes), and there is a heavy dependency surface (100+ npm packages). Overall the codebase is professional and well-structured.
This repository is the documentation site for Factory, an AI-native software development platform centered on the Droid CLI. It contains bilingual (English and Japanese) documentation covering CLI usage, enterprise deployment, integrations, skills, hooks, and benchmarks. The repository also includes CI/CD workflows, changelog automation scripts, and a translation pipeline. While no application source code is present, the documentation is highly structured and includes reusable patterns for skill definitions, hooks, and plugin packaging. The codebase is actively maintained with frequent updates, but exhibits moderate technical drift due to rapid version churn, model name instability, and bilingual documentation divergence.