> ## Documentation Index
> Fetch the complete documentation index at: https://alexcode.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Data Usage

> Understanding how Alex Sidebar handles and protects your data

Alex Sidebar is designed with privacy and security in mind. We maintain strict data handling practices to protect your code and personal information.

## Core Principles

* No code storage or collection
* Opt-out of all third-party training data
* Minimal analytics collection (feature usage and diagnostics only)
* Local storage prioritization

## Infrastructure

### API Processing

All LLM interactions are processed through our secure infrastructure:

1. API endpoint: [https://api.alexcodes.app](https://api.alexcodes.app)
2. Server location: United States (Render hosting)
3. Processing workflow:
   * Context collection from user selection
   * Prompt construction with provided context
   * Secure routing to model providers
   * Response delivery without data persistence

### Future Data Practices

We maintain a strict opt-out-by-default policy for all users. Any future data collection initiatives will:

* Require explicit user consent
* Be clearly communicated
* Include granular opt-in controls
* Maintain existing user preferences

## Data Storage

### Code Embeddings

Alex Sidebar implements local embedding storage for search functionality:

1. **Generation Process**
   * Automatic embedding of Xcode project code
   * Processing through VoyageAI's embedding service
   * Explicit opt-out from provider data collection

2. **Storage Location**
   * Local SQLite database
   * Path: Application Support/com.DanielEdrisian.AlexSideBar
   * No cloud storage or sync

### Chat History

Chat data management follows local-first principles:

* Storage in Application Support directory
* No server-side persistence
* User-controlled retention

## AI Provider Integration

### Chat Models

Current providers:

* OpenAI
* Anthropic
* Perplexity

All integrations configured with:

* Training data opt-out enabled
* No persistent storage
* Request-only data transmission

### Code Application Models

Implementation providers:

* Groq
* Cerebras
* Fireworks AI
* Google (Gemini)

Security measures:

* Training opt-out enforced
* Temporary request processing
* No provider-side data retention

## Monitoring Systems

### Analytics Implementation

Posthog integration limited to:

* Feature activation events
* Command usage frequency
* No content or context collection
* Anonymous usage patterns

### Error Tracking System

Sentry implementation captures:

* Application crash reports
* Error stack traces
* Performance metrics
  * Frame rate analysis
  * UI responsiveness
* Basic system information
  * OS version
  * Device identifiers
  * IP addressing

## Authentication System

Firebase implementation handles:

* User authentication
* O1-Preview credit management
* Basic account state

For comprehensive details on our data handling practices, refer to our official documentation:

* [Terms of Service](https://alexcodes.app/terms)
* [Privacy Policy](https://alexcodes.app/privacy)