Rocket League Replay Analysis with multiple AI agents (OpenAI, Anthropic, Gemini)
# RattleBrain
**RattleBrain** is a command-line tool, written in Rust, designed to bring the power of AI providers to your **Rocket League** replay analysis. By leveraging **[Rattletrap](https://github.com/tfausak/rattletrap)** for parsing replay files and connecting to one or more AI services (e.g., OpenAI, Anthropic, Google), RattleBrain extracts tactical insights, performance metrics, and actionable feedback to help you elevate your gameplay.
see the current [examples/feedback.md](examples/feedback.md) for an example of generated output.
also see the current [TODOs](TODO.md) for upcoming features.
## Usage
[Download](https://github.com/scottleedavis/rattlebrain/releases) and Run the latest release of **RattleBrain** with a replay file
```bash
./rattlebrain analyze <replay_file>
```
---
## Features
- **AI-Enhanced Analysis**: Analyze Rocket League replay files with the help of AI services for in-depth insights.
- **Dynamic AI Selection**: Automatically detects and configures available AI services via environment variables (e.g., `OPENAI_API_KEY`, `ANTHROPIC_API_KEY`, `GEMINI_API_KEY`).
- **Unified Reporting**: Combines outputs from multiple AI agents into a single, comprehensive report.
- **Tactical Insights**: Highlights key plays, strategic opportunities, and areas for improvement.
- **Performance Metrics**: Extracts useful data points to track your progress over time.
- **Lightweight and Fast**: Built with Rust for performance and efficiency.
---
## Getting Started
### Prerequisites
1. Install **Rattletrap**:
- RattleBrain uses [Rattletrap](https://github.com/tfausak/rattletrap/releases) to parse replay files, and is automatically downloaded if not detected in $PATH.
2. Obtain API Keys:
- Get API keys for the AI services you'd like to use (e.g., OpenAI, Gemini).
3. Set Environment Variables:
- Add API keys to AI Services in environment variables (at least 1):
```bash
export OPENAI_API_KEY=<Google's AI-powered research notebook that ingests your documents and becomes an expert on your content. Generates audio overviews, study guides, FAQs, and interactive discussions from uploaded sources.
Google DeepMind's experimental AI agent that can navigate websites, fill forms, and complete multi-step browser tasks autonomously. Uses Gemini's multimodal understanding to interact with web interfaces.
Google DeepMind's universal AI assistant prototype that can see, hear, and respond in real-time through your device camera and microphone. Demonstrates the future of multimodal AI interaction.
Google Cloud's enterprise platform for building, deploying, and managing AI agents powered by Gemini. Supports multi-agent orchestration, tool integration, and enterprise governance.
Gemini's agentic research capability that autonomously browses the web, synthesizes information from dozens of sources, and produces comprehensive research reports on any topic.
Interactive coding and content creation agent that generates, previews, and iterates on code, documents, and interactive applications in a side panel. Supports HTML/CSS/JS, Python, and more.