The agentic AI companion to MultiViewer, the best app to watch motorsports
Project description
Pitwall 🏁
The agentic AI companion to MultiViewer, the best app to watch motorsports
Pitwall transforms your motorsport viewing experience by augmenting MultiViewer with an agentic intelligence you can interrogate over the course of a racing session.
Key Features
- 💬 Conversational Interface: Ask questions, request specific views, or let Pitwall decide what to show
- 🤖 AI-Powered Feed Management: A conversational interface to control driver onboards, broadcast feeds, and more.
- 🏎️ Racing Intelligence: Pit strategy, race control interpretation, and more.
- 🧠 Session Memory: Remembers context and preferences throughout your viewing session
- 🌐 Multi-Series Support: Works with all motorsports series that MultiViewer supports
- OpenRouter Powered: Use any of the thousands of LLMs on OpenRouter
Quick Start
Prerequisites
- Python 3.10 or higher
- MultiViewer installed and running
- A streaming subscription for the motorsport series you wish to watch.
- OpenRouter API key for AI model access
Installation
pip install pitwall
Basic Usage
- Start MultiViewer and ensure it's running on your system
- Set your API key:
export OPENROUTER_API_KEY="your-openrouter-api-key"
- Launch Pitwall:
pitwall
Example Commands
# Quick analysis of current session
pitwall quick "What's the current battle for the lead?"
# Start interactive chat mode
pitwall chat
# Use a specific AI model
pitwall chat --model claude-sonnet
# Check
pitwall models
# Resume a previous session
pitwall chat --session your-session-id
Configuration
Environment Variables
# Required: OpenRouter API key for AI models
export OPENROUTER_API_KEY="your-key-here"
# Optional: Custom MultiViewer host (default: localhost)
export MULTIVIEWER_HOST="192.168.1.100"
Model Options
Pitwall supports various AI models through OpenRouter:
- claude-sonnet: Anthropic Claude Sonnet (recommended)
- claude-opus: Anthropic Claude Opus (premium)
- gpt-41: OpenAI GPT-4.1
- gemini-pro: Google Gemini Pro
- llama: Meta Llama models
- deepseek: DeepSeek models
Advanced Features
Session Memory
Pitwall remembers your viewing sessions:
# List previous sessions
pitwall memory list
# Resume a specific session
pitwall chat --session abc123
# Export session data
pitwall memory export abc123 --output session.json
Development
Local Development
# Clone the repository
git clone https://github.com/RobSpectre/pitwall.git
cd pitwall
# Install in development mode
pip install -e .[dev]
# Run tests
pytest
# Run linting
black .
flake8 pitwall tests
mypy pitwall
Testing
# Run all tests
pytest
# Run with coverage
pytest --cov=pitwall
# Run specific test categories
pytest tests/test_cli.py
pytest tests/test_memory.py
pytest tests/test_pitwall.py
# Run across multiple Python versions
tox
Architecture
Pitwall is built with a modular architecture:
pitwall/
├── cli.py # Command-line interface
├── pitwall.py # Core AI agent logic
├── memory.py # Session management
├── prompts.py # AI prompt templates
└── __init__.py # Package initialization
License
This project is licensed under the MIT License - see the LICENSE file for details.
Meta
- Vibe-coded by Rob Spectre
- Released under MIT License
- Software is as is - no warranty expressed or implied, diggity.
- This package is not developed or maintained by MultiViewer or any racing series
- 🏎️ Go Weeyums! 🏎️
Acknowledgements
- MultiViewer for the incredible motorsport viewing platform
- mvf1 for MultiViewer MCP support
- PydanticAI for the AI agent framework
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file pitwall-0.1.1.tar.gz.
File metadata
- Download URL: pitwall-0.1.1.tar.gz
- Upload date:
- Size: 24.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
e0c3993adbb5898585ad52c3e245c05e85fdf51e92a71c571c599e194c0281a6
|
|
| MD5 |
04dfcd3d073950fa27a78458c2db1c78
|
|
| BLAKE2b-256 |
6f7938909f0624ae5e8b0492054556afbb513cdbd146e4e25eedd8a875b80720
|
File details
Details for the file pitwall-0.1.1-py3-none-any.whl.
File metadata
- Download URL: pitwall-0.1.1-py3-none-any.whl
- Upload date:
- Size: 19.2 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.10.12
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
16b1746e10803e7abc4f1252e2f258e75ed2bfba9c46362718e42cce4c300081
|
|
| MD5 |
bec845e9721abc11d46f4255d666e37a
|
|
| BLAKE2b-256 |
c1924fc7bc9a7025c28a585ecbf6b2a13ebb28eaf42cc6f0e985ed637ccfd4ec
|