Awesome AI AgentsDesktop Automation

openkursar/hello-halo

⭐ 1702 TypeScript repository created 2026-01-13

Halo is a cross-platform desktop application, also usable from the web, that packages an agent runtime with a product layer for individuals and teams. Its engine is pluggable and supports Claude Code, Codex and other backends, and the project states full compatibility with Claude Code agent capabilities, MCP and Skills. Deployment is local, with no cloud dependency and no separate backend service, which the authors position as an answer to enterprise compliance requirements. The central concept is the AI Digital Human: an agent given a task and an execution frequency that then runs on schedule without supervision, using the same engine, MCP toolchain and browser access as interactive conversations. Examples cited include replying to comments and direct messages on Chinese social platforms, publishing scheduled content, monitoring brand mentions and competitors, patrolling internal OA, CRM and ERP systems for overdue tickets and anomalies, generating standup reports from Jira, GitLab and GitHub activity, watching CI/CD pipelines and creating incident tickets, and assembling weekly summaries. Digital Humans can be installed from a store, published in a private organizational store, or created by describing them in plain language. Rather than letting the model click through pages, Halo uses Browser Actions: reusable JavaScript files stored as skills that perform one concrete operation on one platform and run inside a real browser through a browser_run tool with access to the page DOM, cookies and internal APIs, so the model decides what and when while the script knows how. This approach is applied to public platforms and internal enterprise systems alike. Control and reporting are available through WeChat and WeCom in both directions, and progress can be reviewed remotely from a phone or web client.

https://github.com/openkursar/hello-halo

ai-workstationdesktop-agentbrowser-automationscheduled-agentslocal-deployment

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.