freshcrate
Home > AI Agents > Auto-Use

Auto-Use

Auto-Use Computer Use — drives your OS, browser, scours the web, writes your code. One agent, end to end.

Description

Auto-Use Computer Use — drives your OS, browser, scours the web, writes your code. One agent, end to end.

README


✨ Features

  • GUI-based automation
  • Multi-agent system
  • Web agent
  • CLI agent
  • AppScript
  • Secure sandbox

🎯 Example Tasks

Just describe what you want — Auto Use picks the right tool for the job.

🖥️ GUI Task

"Open Chrome, go to YouTube, and search for Python tutorials"

👨‍💻 Coding Task

"Create a Python Flask API with user authentication"

🌐 Web Search Task

"Find the latest NVIDIA stock price and quarterly revenue"

💻 CLI Task

"Check disk space and clean up temp files"

🍎 AppScript Task

"Send an iMessage to John saying I'll be 10 minutes late"

🎯 What Can Auto Use Do?

Category Examples
Browser Fill forms, extract data, navigate sites, download files
Productivity Create documents, manage spreadsheets, organize files
Development Write code, debug errors, run tests, manage git
System Install software, configure settings, manage processes
Research Search web, compile information, generate reports

🧠 Supported Providers

Auto Use supports 6 LLM providers:

  • Anthropic
  • Google
  • Groq
  • OpenAI
  • OpenRouter
  • Perplexity

📋 Requirements

  • macOS (Apple Silicon or Intel) or Windows 10/11
  • API Key from any supported provider

🚀 Setup

💡 Recommended for most users: We strongly encourage installing the latest binary build from our official website for a fully seamless installation and the complete UI experience — no manual setup required.

The steps below are for developers who want to run Auto Use directly from source.

🍎 macOS

  1. Run the setup script

    bash MacOS_setup.sh
  2. Add your API key(s)

    Copy the example env file and fill in your keys:

    cp .env.example .env

    Then open .env and add the API key for whichever provider(s) you want to use.

  3. Run Auto Use

    python main.py

🪟 Windows

  1. Run the setup script

    windows_setup.bat
  2. Add your API key(s)

    Copy the example env file and fill in your keys:

    copy .env.example .env

    Then open .env and add the API key for whichever provider(s) you want to use.

  3. Run Auto Use

    python main.py

Note: On Windows, Python 3.13.3 is the preferred version for best compatibility.


🛡️ Safety

  • Sandbox Isolation — Code runs in a protected environment
  • No System Modification — Won't delete files or run destructive commands without permission
  • Permission Awareness — Asks for confirmation before accepting elevation prompts
  • Path Protection — Blocks access to critical system folders

🌟 Why Auto Use?

Feature Auto Use Others
Multi-agent system
Domain knowledge injection
Multi-provider LLM support Limited
Vision-based automation
Coding agent
Web search integration
Secure sandbox

💻 OS Support

This repository supports both macOS and Windows — the two platform builds live side-by-side in the same repo:

  • macOSAuto_Use/macOS_use
  • WindowsAuto_Use/windows_use

👤 Author

Ashish Yadav — founder of Autouse AI


📄 License & Attribution

Licensed under the Apache License 2.0 — see LICENSE and NOTICE.

If you use, fork, reference, or derive from this project, you must:

  1. Preserve the copyright notice and the NOTICE file.
  2. Credit Ashish Yadav (Autouse AI) as the original author.
  3. Link back to the project: https://github.com/auto-use

How to cite

Yadav, Ashish. Autouse AI — Computer Use. Autouse AI, 2026. https://github.com/auto-use

Release History

VersionChangesUrgencyDate
V1.01. MacOS support. 2. Added Gemini and GCP Vertex AI providers. 3. Added Perplexity provider. 4. Enhanced the scanning technique. 5. Optimized the application to reduce resource consumption. 6. Upgraded the coding agent approach. 7. Implemented a new user interface.Medium4/10/2026
V0.3.41. Improved OCR detection. 2. Removed LLaMA 4 Maverick from Groq and added GPT-OSS 120B for CLI, paired with Scout from Groq. 3. Removed Gemini 3 Pro as it is deprecated and replaced it with Gemini 3.1 Pro, keeping all connections intact via OpenRouter. 4. Added Sonnet 4.6 from Anthropic. 5. Added more application and domain knowledge to the system. 6. The main agent now has additional tool capabilities to handle the file system without touching the GUI. Low3/3/2026

Dependencies & License Audit

Loading dependencies...

Similar Packages

prompt-osA desktop AI agent that controls your local machine — runs commands, manages files, executes code, browses the web autonomously etc. Supports Claude, GPT, Gemini, Llama, DeepSeek, and more. .exe availv1.0.0
claude-skills220+ Claude Code skills & agent plugins for Claude Code, Codex, Gemini CLI, Cursor, and 8 more coding agents — engineering, marketing, product, compliance, C-level advisory.v2.0.0
hermes-gate🏛️ Hermes Gate — Terminal TUI for managing remote Hermes Agent sessions with auto-reconnect, detach support, and zero config0.0.0
Paper2Slides📊 Transform research papers into professional slides and posters seamlessly and quickly with Paper2Slides, saving you valuable time.main@2026-04-21
agent-osAutonomous multi-agent system that turns tasks into code, PRs, and self-healing workflowsmain@2026-04-21