droidrun 0.1.0__tar.gz → 0.2.0__tar.gz

droidrun-0.2.0/CHANGELOG.md

@@ -0,0 +1,54 @@
+# Changelog
+
+All notable changes to the DroidRun project will be documented in this file.
+
+## [0.2.0] - 2025-05-21
+
+### Added
+- **New LLM Providers**
+  - Added support for Ollama (local LLM models)
+  - Added support for DeepSeek models
+  - Case-sensitive provider names: OpenAI, Anthropic, Gemini, Ollama, DeepSeek
+
+- **Planning System**
+  - Added DroidAgent with planning capabilities for complex tasks
+  - Introduced task decomposition for multi-step operations
+
+- **LlamaIndex Integration**
+  - Replaced custom LLM wrapper with LlamaIndex integration
+  - Added direct support for LlamaIndex LLM classes
+
+- **Tracing and Debugging**
+  - Added integration with Arize Phoenix for execution tracing
+  - Added token usage analysis
+  - Added execution time metrics
+
+- **CLI Enhancements**
+  - Added `--reasoning` flag to enable planning capabilities
+  - Added `--tracing` flag for execution tracing with Phoenix
+
+- **Documentation**
+  - Added comprehensive documentation for new features
+  - Created dedicated pages for planning and tracing
+  - Updated all examples to reflect new API patterns
+
+### Changed
+- **Agent Architecture**
+  - Replaced ReActAgent with the new DroidAgent system
+  - Refactored agent initialization to use tools_instance and tool_list
+  - Changed API from `task` parameter to `goal` parameter
+
+### Deprecated
+- Old agent initialization pattern with `device_serial` parameter
+- Direct LLM provider initialization (replaced by LlamaIndex)
+- Non-case-sensitive provider names
+
+### Removed
+- ReActAgent class (replaced by DroidAgent)
+- LLMReasoner class (replaced by LlamaIndex)
+- Some previously documented tools that were not fully implemented
+
+### Fixed
+- Various UI interaction issues
+- Improved error handling in device connections
+- More reliable Android element detection

droidrun-0.2.0/CONTRIBUTING.md

@@ -0,0 +1,95 @@
+# Contributing to DroidRun
+
+Thank you for your interest in contributing to DroidRun! This document provides guidelines and instructions for contributing to the project.
+
+## Getting Started
+
+1. Fork the repository on GitHub
+2. Clone your fork:
+   ```bash
+   git clone https://github.com/YOUR_USERNAME/droidrun.git
+   cd droidrun
+   ```
+3. Set up your development environment as described below
+
+## Development Setup
+
+1. Create and activate a virtual environment:
+   ```bash
+   python -m venv .venv
+   source .venv/bin/activate  # On Windows: .venv\Scripts\activate
+   ```
+
+2. Install development dependencies:
+   ```bash
+   pip install -e ".[dev]"
+   ```
+
+## Making Contributions
+
+1. Create a new branch for your feature:
+   ```bash
+   git checkout -b feature/your-feature-name
+   ```
+
+2. Make your changes following our coding standards:
+   - Use type hints for Python functions
+   - Follow PEP 8 style guidelines
+   - Write descriptive commit messages
+   - Update documentation as needed
+
+3. Commit your changes:
+   ```bash
+   git add .
+   git commit -m "feat: add your feature description"
+   ```
+
+4. Push to your fork:
+   ```bash
+   git push origin feature/your-feature-name
+   ```
+
+5. Open a Pull Request
+
+## Documentation
+
+- Update the README.md if you change functionality
+- Add docstrings to new functions and classes
+- Update the documentation in the `docs/` directory
+
+## Community
+
+- Join our [Discord server](https://discord.gg/ZZbKEZZkwK) for discussions
+- Follow us on [Twitter/X](https://x.com/droid_run)
+- Check our [Documentation](https://docs.droidrun.ai)
+- Report bugs and request features through [GitHub Issues](https://github.com/droidrun/droidrun/issues)
+
+## Pull Request Process
+
+1. Update documentation for any modified functionality
+2. Update the changelog if applicable
+3. Get at least one code review from a maintainer
+4. Once approved, a maintainer will merge your PR
+
+## Release Process
+
+Releases are handled by the maintainers. Version numbers follow [Semantic Versioning](https://semver.org/).
+
+## Questions?
+
+If you have questions about contributing:
+1. Check existing GitHub issues
+2. Ask in our Discord server
+3. Open a new GitHub issue for complex questions
+
+Thank you for contributing to DroidRun! 🚀
+
+## Language
+
+English is the preferred language for all contributions, including:
+- Code comments
+- Documentation
+- Commit messages
+- Pull requests
+- Issue reports
+- Community discussions

{droidrun-0.1.0 → droidrun-0.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: droidrun
-Version: 0.1.0
+Version: 0.2.0
 Summary: A framework for controlling Android devices through LLM agents
 Project-URL: Homepage, https://github.com/droidrun/droidrun
 Project-URL: Bug Tracker, https://github.com/droidrun/droidrun/issues
@@ -28,7 +28,15 @@ Classifier: Topic :: Utilities
 Requires-Python: >=3.10
 Requires-Dist: aiofiles>=23.0.0
 Requires-Dist: anthropic>=0.7.0
+Requires-Dist: arize-phoenix
 Requires-Dist: click>=8.1.0
+Requires-Dist: llama-index
+Requires-Dist: llama-index-callbacks-arize-phoenix
+Requires-Dist: llama-index-llms-anthropic
+Requires-Dist: llama-index-llms-deepseek
+Requires-Dist: llama-index-llms-gemini
+Requires-Dist: llama-index-llms-ollama
+Requires-Dist: llama-index-llms-openai
 Requires-Dist: openai>=1.0.0
 Requires-Dist: pillow>=10.0.0
 Requires-Dist: pydantic>=2.0.0
@@ -40,17 +48,31 @@ Requires-Dist: mypy>=1.0.0; extra == 'dev'
 Requires-Dist: ruff>=0.1.0; extra == 'dev'
 Description-Content-Type: text/markdown
 
-# 🤖 DroidRun
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="./static/droidrun-dark.png">
+  <source media="(prefers-color-scheme: light)" srcset="./static/droidrun.png">
+  <img src="./static/droidrun.png"  width="full">
+</picture>
+
+[![GitHub stars](https://img.shields.io/github/stars/droidrun/droidrun?style=social)](https://github.com/droidrun/droidrun/stargazers)
+[![Discord](https://img.shields.io/discord/1360219330318696488?color=7289DA&label=Discord&logo=discord&logoColor=white)](https://discord.gg/ZZbKEZZkwK)
+[![Documentation](https://img.shields.io/badge/Documentation-📕-blue)](https://docs.droidrun.ai)
+[![Twitter Follow](https://img.shields.io/twitter/follow/droid_run?style=social)](https://x.com/droid_run)
+
 
 DroidRun is a powerful framework for controlling Android devices through LLM agents. It allows you to automate Android device interactions using natural language commands.
 
 ## ✨ Features
 
 - Control Android devices with natural language commands
-- Supports multiple LLM providers (OpenAI, Anthropic, Gemini)
-- Easy to use CLI
+- Supports multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama, DeepSeek)
+- Planning capabilities for complex multi-step tasks
+- LlamaIndex integration for flexible LLM interactions
+- Easy to use CLI with enhanced debugging features
 - Extendable Python API for custom automations
 - Screenshot analysis for visual understanding of the device
+- Execution tracing with Arize Phoenix
 
 ## 📦 Installation
 
@@ -63,7 +85,7 @@ pip install droidrun
 ### 🔧 Option 2: Install from Source
 
 ```bash
-git clone https://github.com/yourusername/droidrun.git
+git clone https://github.com/droidrun/droidrun.git
 cd droidrun
 pip install -e .
 ```
@@ -131,6 +153,8 @@ Create a `.env` file in your working directory or set environment variables:
 export OPENAI_API_KEY="your_openai_api_key_here"
 export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
 export GEMINI_API_KEY="your_gemini_api_key_here"
+export DEEPSEEK_API_KEY="your_deepseek_api_key_here"
+# For Ollama, no API key is needed
 ```
 
 To load the environment variables from the `.env` file:
@@ -151,15 +175,6 @@ droidrun devices
 droidrun connect 192.168.1.100
 ```
 
-### 🔄 4. Verify the setup
-
-Verify that everything is set up correctly:
-
-```bash
-# Should list your connected device and show portal status
-droidrun status
-```
-
 ## 💻 Using the CLI
 
 DroidRun's CLI is designed to be simple and intuitive. You can use it in two ways:
@@ -175,13 +190,16 @@ droidrun "Open the settings app"
 
 ```bash
 # Using OpenAI
-droidrun "Open the calculator app" --provider openai --model gpt-4o-mini
+droidrun "Open the calculator app" --provider OpenAI --model gpt-4o-mini
 
 # Using Anthropic
-droidrun "Check the battery level" --provider anthropic --model claude-3-sonnet-20240229
+droidrun "Check the battery level" --provider Anthropic --model claude-3-sonnet-20240229
 
 # Using Gemini
-droidrun "Install and open Instagram" --provider gemini --model gemini-2.0-flash
+droidrun "Install and open Instagram" --provider Gemini --model models/gemini-2.5-pro-preview-05-06
+
+# Using Ollama (local)
+droidrun "Check battery level" --provider Ollama --model llama2
 ```
 
 ### ⚙️ Additional Options
@@ -190,6 +208,15 @@ droidrun "Install and open Instagram" --provider gemini --model gemini-2.0-flash
 # Specify a particular device
 droidrun "Open Chrome and search for weather" --device abc123
 
+# Enable vision capabilities
+droidrun "Analyze what's on the screen" --vision
+
+# Enable planning for complex tasks
+droidrun "Find and download a specific app" --reasoning
+
+# Enable execution tracing (requires Phoenix server running)
+droidrun "Debug this complex workflow" --tracing
+
 # Set maximum number of steps
 droidrun "Open settings and enable dark mode" --steps 20
 ```
@@ -201,40 +228,73 @@ If you want to use DroidRun in your Python code rather than via the CLI, you can
 ```python
 #!/usr/bin/env python3
 import asyncio
-import os
-from droidrun.agent.react_agent import ReActAgent
-from droidrun.agent.llm_reasoning import LLMReasoner
-from dotenv import load_dotenv
-
-# Load environment variables from .env file
-load_dotenv()
+from droidrun.agent.droid import DroidAgent
+from droidrun.agent.utils.llm_picker import load_llm
+from droidrun.tools import load_tools
 
 async def main():
-    # Create an LLM instance (choose your preferred provider)
-    llm = LLMReasoner(
-        llm_provider="gemini",  # Can be "openai", "anthropic", or "gemini"
-        model_name="gemini-2.0-flash",  # Choose appropriate model for your provider
-        api_key=os.environ.get("GEMINI_API_KEY"),  # Get API key from environment
+    # Load tools
+    tool_list, tools_instance = await load_tools()
+    
+    # Load LLM
+    llm = load_llm(
+        provider_name="Gemini",  # Case sensitive: OpenAI, Ollama, Anthropic, Gemini, DeepSeek
+        model="models/gemini-2.5-pro-preview-05-06",
         temperature=0.2
     )
     
     # Create and run the agent
-    agent = ReActAgent(
-        task="Open the Settings app and check the Android version",
-        llm=llm
+    agent = DroidAgent(
+        goal="Open the Settings app and check the Android version",
+        llm=llm,
+        tools_instance=tools_instance,
+        tool_list=tool_list,
+        vision=True,      # Enable vision for screen analysis
+        reasoning=True    # Enable planning for complex tasks
     )
     
-    steps = await agent.run()
-    print(f"Execution completed with {len(steps)} steps")
+    # Run the agent
+    result = await agent.run()
+    print(f"Success: {result['success']}")
+    if result.get('reason'):
+        print(f"Reason: {result['reason']}")
 
 if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-Save this as `test_droidrun.py`, ensure your `.env` file has the appropriate API key, and run:
+You can also use LlamaIndex directly:
 
-```bash
-python test_droidrun.py
+```python
+import asyncio
+from llama_index.llms.gemini import Gemini
+from droidrun.agent.droid import DroidAgent
+from droidrun.tools import load_tools
+
+async def main():
+    # Load tools
+    tool_list, tools_instance = await load_tools()
+    
+    # Create LlamaIndex LLM directly
+    llm = Gemini(
+        model="models/gemini-2.5-pro-preview-05-06",
+        temperature=0.2
+    )
+    
+    # Create and run the agent
+    agent = DroidAgent(
+        goal="Open the Settings app and check the Android version",
+        llm=llm,
+        tools_instance=tools_instance,
+        tool_list=tool_list
+    )
+    
+    # Run the agent
+    result = await agent.run()
+    print(f"Success: {result['success']}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
 ```
 
 ## ❓ Troubleshooting
@@ -259,6 +319,27 @@ If DroidRun is using the wrong LLM provider:
 1. Explicitly specify the provider with `--provider` (in CLI) or `llm_provider=` (in code)
 2. When using Gemini, ensure you have set `GEMINI_API_KEY` and specified `--provider gemini`
 
+### 📊 Tracing Issues
+
+If you're using the tracing feature:
+1. Make sure to install Arize Phoenix: `pip install "arize-phoenix[llama-index]"`
+2. Start the Phoenix server before running your command: `phoenix serve`
+3. Access the tracing UI at http://localhost:6006 after execution
+
+### 🎬 Demo Videos
+
+1. **Shopping Assistant**: Watch how DroidRun searches Amazon for headphones and sends the top 3 products to a colleague on WhatsApp.
+   
+   Prompt: "Go to Amazon, search for headphones and write the top 3 products to my colleague on WhatsApp."
+   
+   [![Shopping Assistant Demo](https://img.youtube.com/vi/VQK3JcifgwU/0.jpg)](https://www.youtube.com/watch?v=VQK3JcifgwU)
+
+2. **Social Media Automation**: See DroidRun open X (Twitter) and post "Hello World".
+   
+   Prompt: "Open up X and post Hello World."
+   
+   [![Social Media Automation Demo](https://img.youtube.com/vi/i4-sDQhzt_M/0.jpg)](https://www.youtube.com/watch?v=i4-sDQhzt_M)
+
 ## 💡 Example Use Cases
 
 - Automated UI testing of Android applications
@@ -267,6 +348,22 @@ If DroidRun is using the wrong LLM provider:
 - Remote assistance for less technical users
 - Exploring Android UI with natural language commands
 
+## 🗺️ Roadmap
+
+### 🤖 Agent:
+- **Improve memory**: Enhance context retention for complex multi-step tasks
+- **Expand planning capabilities**: Add support for more complex reasoning strategies
+- **Add Integrations**: Support more LLM providers and agent frameworks (LangChain, Agno etc.)
+
+### ⚙️ Automations:
+- **Create Automation Scripts**: Generate reusable scripts from agent actions that can be scheduled or shared
+
+### ☁️ Cloud:
+- **Hosted version**: Remote device control via web interface without local setup
+- **Add-Ons**: Marketplace for extensions serving specific use cases
+- **Proxy Hours**: Cloud compute time with tiered pricing for running automations
+- **Droidrun AppStore**: Simple installation of Apps on your hosted devices
+
 ## 👥 Contributing
 
 Contributions are welcome! Please feel free to submit a Pull Request.

{droidrun-0.1.0 → droidrun-0.2.0}/README.md

@@ -1,14 +1,28 @@
-# 🤖 DroidRun
+
+<picture>
+  <source media="(prefers-color-scheme: dark)" srcset="./static/droidrun-dark.png">
+  <source media="(prefers-color-scheme: light)" srcset="./static/droidrun.png">
+  <img src="./static/droidrun.png"  width="full">
+</picture>
+
+[![GitHub stars](https://img.shields.io/github/stars/droidrun/droidrun?style=social)](https://github.com/droidrun/droidrun/stargazers)
+[![Discord](https://img.shields.io/discord/1360219330318696488?color=7289DA&label=Discord&logo=discord&logoColor=white)](https://discord.gg/ZZbKEZZkwK)
+[![Documentation](https://img.shields.io/badge/Documentation-📕-blue)](https://docs.droidrun.ai)
+[![Twitter Follow](https://img.shields.io/twitter/follow/droid_run?style=social)](https://x.com/droid_run)
+
 
 DroidRun is a powerful framework for controlling Android devices through LLM agents. It allows you to automate Android device interactions using natural language commands.
 
 ## ✨ Features
 
 - Control Android devices with natural language commands
-- Supports multiple LLM providers (OpenAI, Anthropic, Gemini)
-- Easy to use CLI
+- Supports multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama, DeepSeek)
+- Planning capabilities for complex multi-step tasks
+- LlamaIndex integration for flexible LLM interactions
+- Easy to use CLI with enhanced debugging features
 - Extendable Python API for custom automations
 - Screenshot analysis for visual understanding of the device
+- Execution tracing with Arize Phoenix
 
 ## 📦 Installation
 
@@ -21,7 +35,7 @@ pip install droidrun
 ### 🔧 Option 2: Install from Source
 
 ```bash
-git clone https://github.com/yourusername/droidrun.git
+git clone https://github.com/droidrun/droidrun.git
 cd droidrun
 pip install -e .
 ```
@@ -89,6 +103,8 @@ Create a `.env` file in your working directory or set environment variables:
 export OPENAI_API_KEY="your_openai_api_key_here"
 export ANTHROPIC_API_KEY="your_anthropic_api_key_here"
 export GEMINI_API_KEY="your_gemini_api_key_here"
+export DEEPSEEK_API_KEY="your_deepseek_api_key_here"
+# For Ollama, no API key is needed
 ```
 
 To load the environment variables from the `.env` file:
@@ -109,15 +125,6 @@ droidrun devices
 droidrun connect 192.168.1.100
 ```
 
-### 🔄 4. Verify the setup
-
-Verify that everything is set up correctly:
-
-```bash
-# Should list your connected device and show portal status
-droidrun status
-```
-
 ## 💻 Using the CLI
 
 DroidRun's CLI is designed to be simple and intuitive. You can use it in two ways:
@@ -133,13 +140,16 @@ droidrun "Open the settings app"
 
 ```bash
 # Using OpenAI
-droidrun "Open the calculator app" --provider openai --model gpt-4o-mini
+droidrun "Open the calculator app" --provider OpenAI --model gpt-4o-mini
 
 # Using Anthropic
-droidrun "Check the battery level" --provider anthropic --model claude-3-sonnet-20240229
+droidrun "Check the battery level" --provider Anthropic --model claude-3-sonnet-20240229
 
 # Using Gemini
-droidrun "Install and open Instagram" --provider gemini --model gemini-2.0-flash
+droidrun "Install and open Instagram" --provider Gemini --model models/gemini-2.5-pro-preview-05-06
+
+# Using Ollama (local)
+droidrun "Check battery level" --provider Ollama --model llama2
 ```
 
 ### ⚙️ Additional Options
@@ -148,6 +158,15 @@ droidrun "Install and open Instagram" --provider gemini --model gemini-2.0-flash
 # Specify a particular device
 droidrun "Open Chrome and search for weather" --device abc123
 
+# Enable vision capabilities
+droidrun "Analyze what's on the screen" --vision
+
+# Enable planning for complex tasks
+droidrun "Find and download a specific app" --reasoning
+
+# Enable execution tracing (requires Phoenix server running)
+droidrun "Debug this complex workflow" --tracing
+
 # Set maximum number of steps
 droidrun "Open settings and enable dark mode" --steps 20
 ```
@@ -159,40 +178,73 @@ If you want to use DroidRun in your Python code rather than via the CLI, you can
 ```python
 #!/usr/bin/env python3
 import asyncio
-import os
-from droidrun.agent.react_agent import ReActAgent
-from droidrun.agent.llm_reasoning import LLMReasoner
-from dotenv import load_dotenv
-
-# Load environment variables from .env file
-load_dotenv()
+from droidrun.agent.droid import DroidAgent
+from droidrun.agent.utils.llm_picker import load_llm
+from droidrun.tools import load_tools
 
 async def main():
-    # Create an LLM instance (choose your preferred provider)
-    llm = LLMReasoner(
-        llm_provider="gemini",  # Can be "openai", "anthropic", or "gemini"
-        model_name="gemini-2.0-flash",  # Choose appropriate model for your provider
-        api_key=os.environ.get("GEMINI_API_KEY"),  # Get API key from environment
+    # Load tools
+    tool_list, tools_instance = await load_tools()
+    
+    # Load LLM
+    llm = load_llm(
+        provider_name="Gemini",  # Case sensitive: OpenAI, Ollama, Anthropic, Gemini, DeepSeek
+        model="models/gemini-2.5-pro-preview-05-06",
         temperature=0.2
     )
     
     # Create and run the agent
-    agent = ReActAgent(
-        task="Open the Settings app and check the Android version",
-        llm=llm
+    agent = DroidAgent(
+        goal="Open the Settings app and check the Android version",
+        llm=llm,
+        tools_instance=tools_instance,
+        tool_list=tool_list,
+        vision=True,      # Enable vision for screen analysis
+        reasoning=True    # Enable planning for complex tasks
     )
     
-    steps = await agent.run()
-    print(f"Execution completed with {len(steps)} steps")
+    # Run the agent
+    result = await agent.run()
+    print(f"Success: {result['success']}")
+    if result.get('reason'):
+        print(f"Reason: {result['reason']}")
 
 if __name__ == "__main__":
     asyncio.run(main())
 ```
 
-Save this as `test_droidrun.py`, ensure your `.env` file has the appropriate API key, and run:
+You can also use LlamaIndex directly:
 
-```bash
-python test_droidrun.py
+```python
+import asyncio
+from llama_index.llms.gemini import Gemini
+from droidrun.agent.droid import DroidAgent
+from droidrun.tools import load_tools
+
+async def main():
+    # Load tools
+    tool_list, tools_instance = await load_tools()
+    
+    # Create LlamaIndex LLM directly
+    llm = Gemini(
+        model="models/gemini-2.5-pro-preview-05-06",
+        temperature=0.2
+    )
+    
+    # Create and run the agent
+    agent = DroidAgent(
+        goal="Open the Settings app and check the Android version",
+        llm=llm,
+        tools_instance=tools_instance,
+        tool_list=tool_list
+    )
+    
+    # Run the agent
+    result = await agent.run()
+    print(f"Success: {result['success']}")
+
+if __name__ == "__main__":
+    asyncio.run(main())
 ```
 
 ## ❓ Troubleshooting
@@ -217,6 +269,27 @@ If DroidRun is using the wrong LLM provider:
 1. Explicitly specify the provider with `--provider` (in CLI) or `llm_provider=` (in code)
 2. When using Gemini, ensure you have set `GEMINI_API_KEY` and specified `--provider gemini`
 
+### 📊 Tracing Issues
+
+If you're using the tracing feature:
+1. Make sure to install Arize Phoenix: `pip install "arize-phoenix[llama-index]"`
+2. Start the Phoenix server before running your command: `phoenix serve`
+3. Access the tracing UI at http://localhost:6006 after execution
+
+### 🎬 Demo Videos
+
+1. **Shopping Assistant**: Watch how DroidRun searches Amazon for headphones and sends the top 3 products to a colleague on WhatsApp.
+   
+   Prompt: "Go to Amazon, search for headphones and write the top 3 products to my colleague on WhatsApp."
+   
+   [![Shopping Assistant Demo](https://img.youtube.com/vi/VQK3JcifgwU/0.jpg)](https://www.youtube.com/watch?v=VQK3JcifgwU)
+
+2. **Social Media Automation**: See DroidRun open X (Twitter) and post "Hello World".
+   
+   Prompt: "Open up X and post Hello World."
+   
+   [![Social Media Automation Demo](https://img.youtube.com/vi/i4-sDQhzt_M/0.jpg)](https://www.youtube.com/watch?v=i4-sDQhzt_M)
+
 ## 💡 Example Use Cases
 
 - Automated UI testing of Android applications
@@ -225,6 +298,22 @@ If DroidRun is using the wrong LLM provider:
 - Remote assistance for less technical users
 - Exploring Android UI with natural language commands
 
+## 🗺️ Roadmap
+
+### 🤖 Agent:
+- **Improve memory**: Enhance context retention for complex multi-step tasks
+- **Expand planning capabilities**: Add support for more complex reasoning strategies
+- **Add Integrations**: Support more LLM providers and agent frameworks (LangChain, Agno etc.)
+
+### ⚙️ Automations:
+- **Create Automation Scripts**: Generate reusable scripts from agent actions that can be scheduled or shared
+
+### ☁️ Cloud:
+- **Hosted version**: Remote device control via web interface without local setup
+- **Add-Ons**: Marketplace for extensions serving specific use cases
+- **Proxy Hours**: Cloud compute time with tiered pricing for running automations
+- **Droidrun AppStore**: Simple installation of Apps on your hosted devices
+
 ## 👥 Contributing
 
 Contributions are welcome! Please feel free to submit a Pull Request.