Awesome AI AgentsDesktop Automation

taracodlabs/aiden

⭐ 832 TypeScript repository created 2026-03-07

Aiden is a TypeScript autonomous agent runtime that takes a goal and carries it through to verified execution on a real computer. It ships as the aiden-runtime npm package, runs on Windows, Linux, WSL and macOS in API mode, and presents an operator terminal interface after a guided first-launch setup. The stated distinguishing idea is that neither a successful shell command nor a model claiming completion counts as proof. Work is modelled as an explicit pipeline of job, plan and claims, attempt, effect, approval, execution, evidence, verification, verdict and proof, with each stage tracked separately so interrupted, stale or conflicting work can be recovered and reconciled. Around 76 skills and 121 tools give the agent access to files, shell commands, code, browser workflows driven by Playwright and headless Chromium, MCP servers, APIs, repositories and messaging channels across nine channels. Control features include risk-tiered approvals, trust levels, budgets, interruption, scoped permissions, leases and generation fencing so that consequential actions stay visible to the operator. Documented use cases are a codebase mode that snapshots a repository, makes conflict-safe changes, runs tests and builds and performs Git operations with durable evidence; research and report writing; browser form and tab workflows; background automation reacting to files, schedules, email and webhooks through an opt-in daemon; personal file and system operations; and delegation of sub-tasks to isolated sub-agents whose results are combined. State is kept in SQLite with FTS5 for persistent memory and run history. Nineteen model providers are supported, including Anthropic, OpenAI, Google, Groq, custom endpoints and local Ollama, under a bring-your-own-key model with no hosted service in between. The project is developed by a single author and licensed AGPL-3.0.

https://github.com/taracodlabs/aiden

autonomous-agentcomputer-controlbrowser-automationterminalmcpsub-agentsbyoktypescript

Also in Desktop Automation

bytedance/UI-TARS-desktop

UI-TARS Desktop is a GUI Agent application that uses a Vision-Language Model to enable natural language control of computers across multiple platforms with real-time visual recognition and automation capabilities.

asweigart/pyautogui

PyAutoGUI is a cross-platform Python module that enables programmatic control of the mouse and keyboard for GUI automation, including features like screen capture and image recognition.

bytebot-ai/bytebot

Bytebot is a containerized Linux desktop environment that enables programmatic control and remote access for automation, scraping, CI tasks, and remote work through a unified REST API and VNC interfaces.

OthersideAI/self-operating-computer

The Self-Operating Computer Framework enables multimodal AI models to autonomously operate a computer by interpreting screen visuals and executing mouse and keyboard actions to achieve user-defined objectives.

wonderwhy-er/DesktopCommanderMCP

Desktop Commander MCP is a server that integrates with the Claude desktop app to provide terminal control, file system search, and diff-based file editing capabilities, enabling advanced AI-assisted desktop management.

jacklandrin/OnlySwitch

OnlySwitch is a customizable all-in-one macOS menu bar app that consolidates system toggles, shortcuts, and AI-powered controls to enhance user productivity and convenience.

iflytek/astron-rpa

AstronRPA is an enterprise-grade open-source Robotic Process Automation desktop application that enables low-code/no-code workflow automation for desktop and web applications with strong enterprise security, collaboration, and AI agent integration.

yuruotong1/autoMate

autoMate is an AI-driven local automation assistant that uses natural language commands to enable users to automate complex computer tasks without programming, supporting local deployment and full interface control for enhanced privacy and flexibility.