Authentication

Overview

Guardian requires authentication credentials to communicate with AI providers. This guide covers how to configure, manage, and secure your authentication setup.

Supported Providers

Guardian supports multiple AI providers for code analysis:

Provider	Description	Best For
Ollama	Local or self-hosted models	Privacy-focused, offline use
OpenAI	Hosted models	General purpose, fast responses
Anthropic	Hosted models	Deep code analysis, security review
Google Gemini	Hosted models	High speed, multimodal
Hosted Models	Provider-hosted AI models	Managed infrastructure

Initial Setup

Step 1: Obtain API Keys

1. OpenAI: Visit platform.openai.com
2. Anthropic: Visit console.anthropic.com
3. Google: Visit aistudio.google.com
4. Hosted Models: Generate the provider API key with the minimum required scope (see the in-app Settings note).
5. Ollama: No API key required for local installation

Step 2: Configure in Guardian

Open Settings (gear icon) and configure your provider:

1. Select your preferred Provider from the dropdown
2. Enter your API Key (if required)
3. Choose a Model from the available options
4. Click Save to apply

Step 3: Test Connection

The app will automatically validate your credentials when you start monitoring or use Guru.

Credential Storage

Guardian uses platform-native secure storage:

Platform	Storage Method	Encryption
macOS	Keychain	OS-managed
Windows	Credential Manager (DPAPI)	OS-managed
Linux	Secret Service API	OS-managed

Security Note: API keys are never stored in plain text files or exposed in logs.

Ollama Configuration

For local AI models using Ollama:

Local Setup

1. Install Ollama from ollama.com
2. Pull a model: ollama pull llama3.2
3. In Guardian, select Ollama provider
4. Set Base URL to http://127.0.0.1:11434 (Local) or your cloud endpoint

Cloud/Remote Setup

If you have a hosted Ollama instance:

1. Select Ollama provider
2. Choose "Cloud" from the Base URL dropdown or enter your custom endpoint

Rate Limit Management

Guardian automatically handles rate limits with exponential backoff. If you encounter rate limiting:

• Wait a few moments and try again
• Consider using a different provider temporarily

API Key Rotation

Regularly rotate your API keys for security:

1. Generate new key from provider dashboard
2. Update in Guardian Settings
3. Test by using Guru or starting monitoring
4. Revoke old key from provider dashboard

Troubleshooting

Common Issues

Error	Cause	Solution
"Invalid API Key"	Incorrect or expired key	Verify key in provider dashboard
"Rate Limited"	Too many requests	Wait and try again
"Network Error"	Connectivity issue	Check firewall/proxy settings
"Model Not Found"	Invalid model name	Update to supported model

Reset Credentials

To clear stored credentials:

1. Open Settings
2. Click "Clear" next to the API Key field
3. Re-enter new credentials

Best Practices

1. Use Separate Keys: One key per environment (dev, staging, prod)
2. Monitor Usage: Check provider dashboards for usage
3. Rotate Quarterly: Change keys every 3 months
4. Limit Scope: Use provider's API key restrictions if available
5. Never Commit: Keep keys out of version control