rohanarun
Open-Agent-Studio
HTML

No description available.

Last updated Jun 30, 2026
314
Stars
38
Forks
3
Issues
0
Stars/day
Attention Score
37
Language breakdown
HTML 46.0%
Python 37.5%
TeX 16.4%
Batchfile 0.0%
Makefile 0.0%
โ–ธ Files click to expand
README

Open Agent Studio - Build Unlimited Computer Use Agents Without Running Out Of Credits (Mac/Windows/Linux)

The first cross-platform desktop application for Agentic Process Automation An open-source alternative to UIPath and traditional RPA tools using unlimited VLM models for semantic targets. Downloads Platform License Star History ๐Ÿš€ Get Started โ€ข ๐Ÿ“– Documentation โ€ข ๐Ÿค Contributing โ€ข ๐Ÿ’ฌ Support

๐ŸŒŸ What is Open Agent Studio?

Open Agent Studio is an open-source alternative to UIPath and traditional RPA tools by enabling Agentic Process Automation through natural language. Instead of brittle selectors and complex code, describe what you want in plain English and let AI handle the rest. It uses unlimited free VLM models with state of the art object detection from our synthetic dataset to achieve state of the art computer use without credits across unlimited servers and agents.

โœจ Key Features

  • ๐ŸŽฏ Semantic Targets: Future-proof automation that survives UI changes
  • ๐ŸŽฌ Video-to-Agent: World's first video-based agent creation
  • ๐ŸŒ Cross-Platform: Works on Windows and Linux
  • ๐Ÿ”— Built-in API: Every instance includes a REST API
  • ๐Ÿง  AI-Powered: GPT-4 integration for intelligent decision making
  • ๐Ÿ”„ Self-Healing: Robust verification and testing loops

๐Ÿ“ฅ Installation

Windows

  • Extract the ZIP file
  • Run the application (click "More info" โ†’ "Run anyway" if Windows shows security warnings)

Linux

  • Extract and run

๐Ÿ“บ Video Tutorials

โœจ Tools built using Open Agent Studio


๐Ÿš€ Quick Start

1. Create Your First Agent

{
  "key": "yourapikey",
  "json_output": [
    {
      "type": "open tab",
      "target": "https://example.com"
    },
    {
      "type": "click",
      "target": "Login button",
      "browser_mode": true
    }
  ],
  "goal": "Navigate to website and click login"
}

2. Test Locally

curl -X POST http://localhost:8080/agents \
  -H "Content-Type: application/json" \
  -d @your_agent.json

๐ŸŽฏ Semantic Targets

Instead of fragile CSS selectors, use natural language:
{
  "type": "click",
  "target": "blue submit button",
  "browser_mode": true
}
This works even if the website completely changes its design!

๐Ÿ›  Agent Node Types

๐ŸŒ Browser Automation

Click

{
  "type": "click",
  "target": "Submit button",
  "browser_mode": true
}

Type Text

{
  "type": "keypress",
  "prompt": "Hello, World!"
}

Open Tab

{
  "type": "open tab",
  "target": "https://example.com"
}

Wait/Delay

{
  "type": "delay",
  "time": 5
}
๐Ÿง  AI & Data Processing

GPT-4 Processing

{
  "type": "gpt4",
  "prompt": "Summarize the following text:",
  "input": ["article_text"],
  "data": "summary"
}

Python Execution

{
  "type": "python",
  "code": "import pandas as pd\nprint('Hello from Python!')"
}

Semantic Scraping

{
  "type": "semanticScrape",
  "target": "product prices",
  "data": "price_data"
}
๐Ÿ“Š Integrations

Google Sheets

{
  "type": "googlesheetsadd_row",
  "URL": "sheet_url",
  "Sheet_Name": "Sheet1",
  "data": ["John", "Doe", "30"]
}

Email

{
  "type": "email",
  "to": "user@example.com",
  "subject": "Automation Report",
  "body": "Task completed successfully!"
}

API Calls

{
  "type": "api",
  "URL": "https://api.example.com/data",
  "headers": {"Content-Type": "application/json"},
  "body": {"key": "value"}
}

๐Ÿ“– Complete Example

Here's a complete agent that scrapes data, analyzes it, and sends results:
{
  "key": "yourapikey",
  "json_output": [
    {
      "type": "open tab",
      "target": "https://news.ycombinator.com"
    },
    {
      "type": "semanticScrape",
      "target": "top story headlines",
      "data": "headlines"
    },
    {
      "type": "gpt4",
      "prompt": "Summarize these headlines and identify key trends:",
      "input": ["headlines"],
      "data": "analysis"
    },
    {
      "type": "googlesheetscreate",
      "URL": "sheet_url",
      "SheetName": "newsanalysis"
    },
    {
      "type": "googlesheetsadd_row",
      "URL": "sheet_url",
      "SheetName": "newsanalysis",
      "data": ["{{analysis}}"]
    },
    {
      "type": "email",
      "to": "manager@company.com",
      "subject": "Daily News Analysis",
      "body": "Please find today's analysis attached.",
      "data": "analysis"
    }
  ],
  "goal": "Scrape news, analyze trends, save to sheets, and email results"
}

๐Ÿ“ก Agent API Reference

POST /agents

Creates and runs a new agent. Request:
{
  "key": "yourapikey",
  "json_output": [...],
  "goal": "description"
}
Response: Returns execution results and verification data.

๐Ÿ—บ Roadmap

  • [X] Open Agent Cloud - Cloud-based execution Done!
  • [X] Enhanced Video-to-Agent - Improved conversion accuracy Done!
  • [ ] Advanced Evaluations - Better testing for generalized agents
  • [ ] Improved Testing Loop - Self-healing automation
  • [X] Full Open Source Backend - Complete local deployment Done!

๐Ÿค Contributing

We welcome contributions! Here's how you can help:

๐Ÿš€ Get Started

  • Join our community discussions
  • Check out open issues and feature requests

๐ŸŽฏ Areas We Need Help

  • Evaluations for generalized agents
  • Testing loop improvements
  • Video-to-agent enhancement
  • Documentation and tutorials
  • Bug reports and fixes

๐Ÿ“‹ Development Setup

# Clone the repository
git clone https://github.com/rohanarun/Open-Agent-Studio.git

Email: rohan@cheatlayer.com


๐Ÿ’ฌ Support


๐Ÿ† Our Story

Founded during the pandemic to help people rebuild their businesses with AI, we were the first startup approved by OpenAI to sell GPT-3 for automation in August 2021. We invented "Semantic Targets" and achieved 97% accuracy with our Atlas-2 multimodal model. Our Vision: In a future where AI can generate custom, secure, and free versions of expensive business software, we're building tools that level the playing field for everyone.
Made with โค๏ธ by the Cheat Layer Team Get Started Now โ€ข Star on GitHub โ€ข Join the Community
๐Ÿ”— More in this category

ยฉ 2026 GitRepoTrend ยท rohanarun/Open-Agent-Studio ยท Updated daily from GitHub