droidrun 0.1.0__py3-none-any.whl → 0.2.0__py3-none-any.whl

droidrun/tools/device.py

@@ -3,7 +3,7 @@ Device Manager - Handles Android device connections and management.
 """
 
 from typing import Optional, List
-from droidrun.adb import Device, DeviceManager as ADBDeviceManager
+from ..adb import Device, DeviceManager as ADBDeviceManager
 
 class DeviceManager:
     """Manages Android device connections and operations."""

droidrun/tools/loader.py

@@ -0,0 +1,60 @@
+import asyncio
+import logging
+from .actions import Tools
+from .device import DeviceManager
+from typing import Tuple, Dict, Callable, Any, Optional
+
+# Get a logger for this module
+logger = logging.getLogger(__name__)
+
+async def load_tools(serial: Optional[str] = None) -> Tuple[Dict[str, Callable[..., Any]], Tools]:
+    """
+    Initializes the Tools class and returns a dictionary of available tool functions
+    and the Tools instance itself. If serial is not provided, it attempts to find
+    the first connected device.
+
+    Args:
+        serial: The device serial number. If None, finds the first available device.
+        vision: Whether to include vision-related tools. (Set to false if you want to always send screenshot)
+
+    Returns:
+        A tuple containing:
+        - A dictionary mapping tool names to their corresponding functions.
+        - The initialized Tools instance.
+
+    Raises:
+        ValueError: If no device serial is provided and no devices are found.
+    """
+    if serial is None:
+        logger.info("No device serial provided, attempting to find a connected device.")
+        # Attempt to find a device if none is specified
+        device_manager = DeviceManager()
+        devices = await device_manager.list_devices()
+        if not devices:
+            logger.error("Device discovery failed: No connected devices found.")
+            raise ValueError("No device serial provided and no connected devices found.")
+        serial = devices[0].serial
+        logger.info(f"Using auto-detected device: {serial}") # Use logger.info
+
+    logger.debug(f"Initializing Tools for device: {serial}")
+    tools_instance = Tools(serial=serial)
+
+    tool_list = {
+        # UI interaction
+        "swipe": tools_instance.swipe,
+        "input_text": tools_instance.input_text,
+        "press_key": tools_instance.press_key,
+        "tap_by_index": tools_instance.tap_by_index,
+        #"tap_by_coordinates": tools_instance.tap_by_coordinates,
+
+        # App management
+        "start_app": tools_instance.start_app,
+        "list_packages": tools_instance.list_packages,
+        "complete": tools_instance.complete
+    }
+    logger.debug("Base tools loaded.")
+
+
+    # Return both the dictionary and the instance, as the agent might need the instance
+    logger.info(f"Tools loaded successfully for device {serial}.")
+    return tool_list, tools_instance

{droidrun-0.1.0.dist-info → droidrun-0.2.0.dist-info}/METADATA

@@ -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-0.2.0.dist-info/RECORD

@@ -0,0 +1,32 @@
+droidrun/__init__.py,sha256=LhCCBKH9M1PJG3jAsCG84zyK2WkbTR3WI58LrzuSXMA,659
+droidrun/__main__.py,sha256=ganC_pSTITSVwVmdEfd6qEkrHutt3UVoalXTBianP2w,97
+droidrun/adb/__init__.py,sha256=tBhoSFmkevb_xQcCfdrigPut9zAU1J4bagpT-TgBj8c,221
+droidrun/adb/device.py,sha256=yMndMpO-R0lPmLoZANr-aou8HldyD3TLCP9J5ZjJJao,10992
+droidrun/adb/manager.py,sha256=9xohDCbw8XvWW2Esglpcnk9H24hKJG3e9SkCBiFWlDI,2704
+droidrun/adb/wrapper.py,sha256=Yz3_JSIidq-5bf-t0UfawTutMaLrINS_1Y15m_Uss4g,7093
+droidrun/agent/codeact/__init__.py,sha256=B1wskXGB-xeGCZnUIZxBaEXz1f0YSxAHRljKqMH6nXQ,308
+droidrun/agent/codeact/codeact_agent.py,sha256=lyJfBmPshR50-k6wtrOBe3IwSJueiDBpuiGNaWxoagA,16015
+droidrun/agent/codeact/events.py,sha256=4O0fJWu_DwJoJF8SqQr8CpALsaSKNOGKksVS9yWWBsY,934
+droidrun/agent/codeact/prompts.py,sha256=vRt0z34ND-p1RGkfXbp96Q_-z8HbHmjVB9c2LHnzl7Q,4110
+droidrun/agent/droid/__init__.py,sha256=wSuPd9wDEreFYlclfmXEqiqKq0wJQTT3v3PY-WhS6q0,264
+droidrun/agent/droid/droid_agent.py,sha256=3JnCkusacpBYiWVFBnVRMGbFt61CJ2_bOn_QW-lFUTk,18576
+droidrun/agent/planner/__init__.py,sha256=CWWEA9H6xM-il832tpTG19bMl0j9r4fYXMLikqUGNeU,372
+droidrun/agent/planner/events.py,sha256=wWBz5F7_cyNQHJLZp-n-1ML89M82_chcdhUxXTj3k8M,381
+droidrun/agent/planner/prompts.py,sha256=8kWudnq8dPuhVpugyT53Y-NPLZvlQadIrjUUrKgy5h4,7065
+droidrun/agent/planner/task_manager.py,sha256=u70Syr9OiGKU4IOy9oqblLYjHfELBl-m5nmQc35RPqI,13348
+droidrun/agent/planner/workflow.py,sha256=jRLVkEejQk1Rul6mxBXLDtReS8K0G1UFAJdH1JHtXOk,18797
+droidrun/agent/utils/async_utils.py,sha256=Bf4J2TmT7Fbp4JKtvS1lfOYBmJ3lBUQ9D0lBYQfChus,2266
+droidrun/agent/utils/chat_utils.py,sha256=lSp6snn15EhrZj4eGGN3De710Btub5jV_euSz9LYUu4,3891
+droidrun/agent/utils/executer.py,sha256=PKgUwTer-IezZ-NecCGrgcRHjmRIm7RTmgwrUaXJSlQ,3535
+droidrun/agent/utils/llm_picker.py,sha256=KSjbOw6oqKuIQUm8lKDEhY13PTd5U70vY9Bb150AvBE,5782
+droidrun/cli/__init__.py,sha256=ra9bKoHTIkgRsVFRlWztROPPRswMv_A-wc2b2e0plmo,155
+droidrun/cli/main.py,sha256=NQKjHSxMTDSjNyXLnv8KnUQgTw61RFWRVKpL2aukT3M,21197
+droidrun/tools/__init__.py,sha256=_wTPn8jhAjtpMdHXc5LlCa2pokpCuM1kcEzxC94gpVg,237
+droidrun/tools/actions.py,sha256=0KM-eyJnWx4kIttKG7MVA8gwn9DNoxQv8It0nCyV-GE,34002
+droidrun/tools/device.py,sha256=Aq2NzERtFdPLiXXQ_km7DJbw2LAPgpCIf5DQB-VpzCA,1078
+droidrun/tools/loader.py,sha256=Glpxz7t1IDlitxcUslmhwPTTpNpx8y_ivLN6JF3CDoE,2372
+droidrun-0.2.0.dist-info/METADATA,sha256=mDCK2ij4tifCuew8zv8aii-6dRAyfv2ehs7GfvUknus,12479
+droidrun-0.2.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+droidrun-0.2.0.dist-info/entry_points.txt,sha256=o259U66js8TIybQ7zs814Oe_LQ_GpZsp6a9Cr-xm5zE,51
+droidrun-0.2.0.dist-info/licenses/LICENSE,sha256=s-uxn9qChu-kFdRXUp6v_0HhsaJ_5OANmfNOFVm2zdk,1069
+droidrun-0.2.0.dist-info/RECORD,,

droidrun/agent/__init__.py

@@ -1,16 +0,0 @@
-"""
-Droidrun Agent Module.
-
-This module provides a ReAct agent for automating Android devices using reasoning and acting.
-"""
-
-from .react_agent import ReActAgent, ReActStep, ReActStepType, run_agent
-from .llm_reasoning import LLMReasoner
-
-__all__ = [
-    "ReActAgent",
-    "ReActStep",
-    "ReActStepType",
-    "run_agent",
-    "LLMReasoner",
-]