droidrun 0.2.0__tar.gz → 0.3.1__tar.gz

droidrun-0.3.1/.github/workflows/publish.yml

@@ -0,0 +1,76 @@
+name: Publish Python 🐍 distribution 📦 to PyPI and TestPyPI
+
+on: push
+
+jobs:
+  build:
+    name: Build distribution 📦
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v4
+      with:
+        persist-credentials: false
+    - name: Set up Python
+      uses: actions/setup-python@v5
+      with:
+        python-version: "3.x"
+    - name: Install pypa/build
+      run: >-
+        python3 -m
+        pip install
+        build
+        --user
+    - name: Build a binary wheel and a source tarball
+      run: python3 -m build
+    - name: Store the distribution packages
+      uses: actions/upload-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+
+  publish-to-pypi:
+    name: >-
+      Publish Python 🐍 distribution 📦 to PyPI
+    if: startsWith(github.ref, 'refs/tags/')
+    needs:
+    - build
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/droidrun 
+    permissions:
+      id-token: write
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution 📦 to PyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+
+  publish-to-testpypi:
+    name: Publish Python 🐍 distribution 📦 to TestPyPI
+    needs:
+    - build
+    runs-on: ubuntu-latest
+
+    environment:
+      name: testpypi
+      url: https://test.pypi.org/p/droidrun
+
+    permissions:
+      id-token: write
+
+    steps:
+    - name: Download all the dists
+      uses: actions/download-artifact@v4
+      with:
+        name: python-package-distributions
+        path: dist/
+    - name: Publish distribution 📦 to TestPyPI
+      uses: pypa/gh-action-pypi-publish@release/v1
+      with:
+        repository-url: https://test.pypi.org/legacy/

droidrun-0.3.1/.gitignore

@@ -0,0 +1,23 @@
+dist/
+# Python bytecode files
+__pycache__/
+*.py[cod]
+*$py.class
+trajectories/
+*.class
+
+test.py
+test.ipynb
+*.log
+
+messages_log.json
+
+.idea
+.vscode
+.vscode-test
+.vscode-test-*
+.idea/*
+.vscode/*
+patch_apis.py
+.git
+.arize-phoenix

{droidrun-0.2.0 → droidrun-0.3.1}/CONTRIBUTING.md

@@ -64,6 +64,29 @@ Thank you for your interest in contributing to DroidRun! This document provides
 - Check our [Documentation](https://docs.droidrun.ai)
 - Report bugs and request features through [GitHub Issues](https://github.com/droidrun/droidrun/issues)
 
+## Security Checks
+
+To ensure the security of the codebase, we have integrated security checks using `bandit` and `safety`. These tools help identify potential security issues in the code and dependencies.
+
+### Running Security Checks
+
+Before submitting any code, please run the following security checks:
+
+1. **Bandit**: A tool to find common security issues in Python code.
+   ```bash
+   bandit -r droidrun
+   ```
+
+2. **Safety**: A tool to check your installed dependencies for known security vulnerabilities.
+   ```bash
+   safety check
+   ```
+
+You can also run both checks using the provided script:
+```bash
+python -m droidrun.tools.security_check
+```
+
 ## Pull Request Process
 
 1. Update documentation for any modified functionality
@@ -92,4 +115,4 @@ English is the preferred language for all contributions, including:
 - Commit messages
 - Pull requests
 - Issue reports
-- Community discussions
+- Community discussions

droidrun-0.3.1/PKG-INFO

@@ -0,0 +1,150 @@
+Metadata-Version: 2.4
+Name: droidrun
+Version: 0.3.1
+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
+Project-URL: Documentation, https://docs.droidrun.ai/
+Author-email: Niels Schmidt <niels.schmidt@droidrun.ai>
+License: MIT
+License-File: LICENSE
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Topic :: Communications :: Chat
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Application Frameworks
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Topic :: Software Development :: Quality Assurance
+Classifier: Topic :: Software Development :: Testing
+Classifier: Topic :: Software Development :: Testing :: Acceptance
+Classifier: Topic :: System :: Emulators
+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-google-genai
+Requires-Dist: llama-index-llms-ollama
+Requires-Dist: llama-index-llms-openai
+Requires-Dist: llama-index-llms-openai-like
+Requires-Dist: openai>=1.0.0
+Requires-Dist: pillow>=10.0.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: python-dotenv>=1.0.0
+Requires-Dist: rich>=13.0.0
+Provides-Extra: dev
+Requires-Dist: bandit>=1.7.0; extra == 'dev'
+Requires-Dist: black>=23.0.0; extra == 'dev'
+Requires-Dist: mypy>=1.0.0; extra == 'dev'
+Requires-Dist: ruff>=0.1.0; extra == 'dev'
+Requires-Dist: safety>=2.0.0; extra == 'dev'
+Description-Content-Type: text/markdown
+
+<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)
+[![Benchmark](https://img.shields.io/badge/Benchmark-🏅-teal)](https://droidrun.ai/benchmark)
+[![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 and iOS devices through LLM agents. It allows you to automate device interactions using natural language commands. [Checkout our benchmark results](https://droidrun.ai/benchmark)
+
+- 🤖 Control Android and iOS devices with natural language commands
+- 🔀 Supports multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama, DeepSeek)
+- 🧠 Planning capabilities for complex multi-step tasks
+- 💻 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
+
+```bash
+pip install droidrun
+```
+
+## 🚀 Quickstart
+Read on how to get droidrun up and running within seconds in [our docs](https://docs.droidrun.ai/v3/quickstart)!
+
+
+## 🎬 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 mobile applications
+- Creating guided workflows for non-technical users
+- Automating repetitive tasks on mobile devices
+- Remote assistance for less technical users
+- Exploring mobile 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.
+
+## 📄 License
+
+This project is licensed under the MIT License - see the LICENSE file for details. 
+
+## Security Checks
+
+To ensure the security of the codebase, we have integrated security checks using `bandit` and `safety`. These tools help identify potential security issues in the code and dependencies.
+
+### Running Security Checks
+
+Before submitting any code, please run the following security checks:
+
+1. **Bandit**: A tool to find common security issues in Python code.
+   ```bash
+   bandit -r droidrun
+   ```
+
+2. **Safety**: A tool to check your installed dependencies for known security vulnerabilities.
+   ```bash
+   safety scan
+   ```

droidrun-0.3.1/README.md

@@ -0,0 +1,97 @@
+<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)
+[![Benchmark](https://img.shields.io/badge/Benchmark-🏅-teal)](https://droidrun.ai/benchmark)
+[![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 and iOS devices through LLM agents. It allows you to automate device interactions using natural language commands. [Checkout our benchmark results](https://droidrun.ai/benchmark)
+
+- 🤖 Control Android and iOS devices with natural language commands
+- 🔀 Supports multiple LLM providers (OpenAI, Anthropic, Gemini, Ollama, DeepSeek)
+- 🧠 Planning capabilities for complex multi-step tasks
+- 💻 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
+
+```bash
+pip install droidrun
+```
+
+## 🚀 Quickstart
+Read on how to get droidrun up and running within seconds in [our docs](https://docs.droidrun.ai/v3/quickstart)!
+
+
+## 🎬 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 mobile applications
+- Creating guided workflows for non-technical users
+- Automating repetitive tasks on mobile devices
+- Remote assistance for less technical users
+- Exploring mobile 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.
+
+## 📄 License
+
+This project is licensed under the MIT License - see the LICENSE file for details. 
+
+## Security Checks
+
+To ensure the security of the codebase, we have integrated security checks using `bandit` and `safety`. These tools help identify potential security issues in the code and dependencies.
+
+### Running Security Checks
+
+Before submitting any code, please run the following security checks:
+
+1. **Bandit**: A tool to find common security issues in Python code.
+   ```bash
+   bandit -r droidrun
+   ```
+
+2. **Safety**: A tool to check your installed dependencies for known security vulnerabilities.
+   ```bash
+   safety scan
+   ```

{droidrun-0.2.0 → droidrun-0.3.1}/docs/docs.json

@@ -10,6 +10,29 @@
   "favicon": "/favicon.png",
   "navigation": {
     "versions": [
+      {
+        "version": "0.3.0",
+        "groups": [
+          {
+            "group": "Getting Started",
+            "pages": [
+              "v3/overview",
+              "v3/quickstart"
+            ]
+          },
+          {
+            "group": "Core Concepts",
+            "pages": [
+              "v3/concepts/agent",
+              "v3/concepts/planning",
+              "v3/concepts/android-control",
+              "v3/concepts/ios-control",
+              "v3/concepts/portal-app",
+              "v3/concepts/tracing"
+            ]
+          }
+        ]
+      },
       {
         "version": "0.2.0",
         "groups": [
@@ -63,6 +86,10 @@
       {
         "label": "GitHub",
         "href": "https://github.com/droidrun/droidrun"
+      },
+      {
+        "label": "Benchmark",
+        "href": "https://droidrun.ai/benchmark"
       }
     ],
     "primary": {
@@ -73,7 +100,8 @@
   },
   "footer": {
     "socials": {
-      "github": "https://github.com/droidrun/droidrun"
+      "github": "https://github.com/droidrun/droidrun",
+      "x": "https://x.com/droid_run"
     }
   }
 }

{droidrun-0.2.0 → droidrun-0.3.1}/docs/introduction.mdx

@@ -5,7 +5,7 @@ description: 'Welcome to DroidRun - Control Android devices with LLM agents'
 
 # Welcome to DroidRun
 
-DroidRun is a powerful framework that enables you to control Android devices through LLM agents. It provides a simple and intuitive way to automate Android device interactions using natural language commands.
+DroidRun is a powerful framework that enables you to control Android devices through LLM agents. It provides a simple and intuitive way to automate Android and iOS device interactions using natural language commands.
 
 ## Features
 
@@ -31,42 +31,32 @@ DroidRun is a powerful framework that enables you to control Android devices thr
 droidrun "Open the settings app"
 
 # With specific provider
-droidrun "Open calculator app" --provider gemini --model gemini-2.0-flash
-
-# With vision capabilities
-droidrun "Open Calculator and take a screenshot" --vision
+droidrun "Open calculator app" --provider Gemini --model models/gemini-2.5-pro
 ```
 
 Or with Python:
 
 ```python
 import asyncio
-import os
-from droidrun.agent.react_agent import ReActAgent
-from droidrun.agent.llm_reasoning import LLMReasoner
+from droidrun import DroidAgent, load_llm, AdbTools
 
 async def main():
-    # Create an LLM instance
-    llm = LLMReasoner(
-        llm_provider="gemini",  # "openai", "anthropic", or "gemini"
-        model_name="gemini-2.0-flash",
-        api_key=os.environ.get("GEMINI_API_KEY"),
-        temperature=0.2,
-        vision=True  # Enable vision capabilities
-    )
+    # initialize agent tools (ios/adb/web)
+    tools = AdbTools(serial=device)
+
+    # initialize llm adapter
+    llm = load_llm(provider_name="Gemini", model="models/gemini-2.5-pro")
     
-    # Create and run the agent
-    agent = ReActAgent(
-        task="Open the Settings app",
-        llm=llm,
-        vision=True  # Enable screenshot analysis
+    # Create the DroidAgent
+    agent = DroidAgent(
+      goal=command,
+      llm=llm,
+      tools=tools,
     )
+
+    result = await agent.run()
     
-    steps = await agent.run()
-    
-    # Get token usage statistics
-    stats = llm.get_token_usage_stats()
-    print(f"Total tokens used: {stats['total_tokens']}")
+    print(f"Success: {result['success']} in {result['steps']} steps -> {result['reason']}")
 
 if __name__ == "__main__":
     asyncio.run(main())
@@ -74,9 +64,15 @@ if __name__ == "__main__":
 
 ## Prerequisites
 
+- API key for at least one LLM provider (OpenAI, Anthropic, or Google Gemini)
+
+**for Android**
 - Android device connected via USB or ADB over TCP/IP
 - ADB (Android Debug Bridge) installed
-- API key for at least one LLM provider (OpenAI, Anthropic, or Google Gemini)
+- Droidrun Portal installed on device
+
+**for iOS**
+- Run the [Droidrun Portal iOS service]()
 
 ## Getting Started
 

{droidrun-0.2.0 → droidrun-0.3.1}/docs/v2/concepts/agent.mdx

@@ -145,7 +145,6 @@ agent = DroidAgent(
     reasoning=True,                 # Enable planning
     max_steps=15,                   # Maximum planning steps
     timeout=1000,                   # Overall timeout
-    max_retries=3,                  # Retry attempts
     enable_tracing=True,            # Execution tracing
     debug=False                     # Debug mode
 )
@@ -223,7 +222,6 @@ print(f"Task history: {result['task_history']}")
    - Consider device performance
 
 4. **Handle Errors Properly**
-   - Configure max_retries for robustness
    - Check task_history for debugging
 
 5. **Memory Usage**

{droidrun-0.2.0 → droidrun-0.3.1}/docs/v2/concepts/planning.mdx

@@ -85,7 +85,6 @@ agent = DroidAgent(
     tools_instance=tools,
     reasoning=True,  # Enable planning
     max_steps=15,    # Maximum planning iterations
-    max_retries=3,   # Retry attempts for failed tasks
     timeout=1000     # Overall timeout in seconds
 )
 ```
@@ -134,7 +133,6 @@ Planning is most effective for:
    - Consider device and network performance
 
 3. **Error Handling**
-   - Set reasonable max_retries
    - Check task_history for debugging failed tasks
 
 4. **Memory Usage**

{droidrun-0.2.0 → droidrun-0.3.1}/docs/v2/concepts/tracing.mdx

@@ -50,7 +50,7 @@ from droidrun.tools import load_tools
 
 async def main():
     tool_list, tools_instance = await load_tools()
-    llm = load_llm(provider_name="Gemini", model="models/gemini-2.5-pro-preview-05-06")
+    llm = load_llm(provider_name="Gemini", model="models/gemini-2.5-pro")
     
     # Enable tracing
     agent = DroidAgent(

{droidrun-0.2.0 → droidrun-0.3.1}/docs/v2/overview.mdx

@@ -37,7 +37,7 @@ DroidRun is a powerful framework that enables you to control Android devices thr
 droidrun "Open the settings app"
 
 # With specific provider and model
-droidrun "Open calculator app" --provider Gemini --model models/gemini-2.5-pro-preview-05-06
+droidrun "Open calculator app" --provider Gemini --model models/gemini-2.5-pro
 
 # With vision and planning capabilities
 droidrun "Open Calculator and take a screenshot" --vision --reasoning
@@ -56,7 +56,7 @@ async def main():
     tool_list, tools_instance = await load_tools()
     llm = load_llm(
         provider_name="Gemini",  # OpenAI, ollama, Anthropic, Gemini, DeepSeek
-        model="models/gemini-2.5-pro-preview-05-06",
+        model="models/gemini-2.5-pro",
         temperature=0.2
     )
     

{droidrun-0.2.0 → droidrun-0.3.1}/docs/v2/quickstart.mdx

@@ -169,7 +169,7 @@ Test with these commands:
 droidrun "Open the settings app"
 
 # Using specific provider and model
-droidrun "Open calculator" --provider Gemini --model models/gemini-2.5-pro-preview-05-06
+droidrun "Open calculator" --provider Gemini --model models/gemini-2.5-pro
 
 # With vision and planning
 droidrun "Take a screenshot and describe what's on the screen" --vision --reasoning
@@ -218,7 +218,7 @@ async def main():
     tool_list, tools_instance = await load_tools()
     llm = load_llm(
         provider_name="Gemini",  # Case sensitive: OpenAI, Ollama, Anthropic, Gemini, DeepSeek
-        model="models/gemini-2.5-pro-preview-05-06",
+        model="models/gemini-2.5-pro",
         temperature=0.2
     )
     
@@ -260,7 +260,7 @@ async def main():
     
     # Create LlamaIndex LLM directly
     llm = Gemini(
-        model="models/gemini-2.5-pro-preview-05-06",
+        model="models/gemini-2.5-pro",
         temperature=0.2,
         additional_kwargs={"safety_settings": {"hate": "block_none"}}
     )