Overview
ARI supports multiple AI providers for the built-in AI Assistant and AI-powered module generation. All API keys are stored locally on your server and never shared with ARI or any third party.
Configure your AI providers in Settings > Integrations.
Supported Providers
OpenAI
The default provider for the AI Assistant module and module generation.
- Create an account at platform.openai.com
- Navigate to API Keys and generate a new key
- Add it in Settings > Integrations or set
OPENAI_API_KEYin your environment
Anthropic (Claude)
Use Claude models for the AI Assistant.
- Create an account at console.anthropic.com
- Generate an API key
- Add it in Settings > Integrations or set
ANTHROPIC_API_KEYin your environment
OpenRouter
Access a wide range of AI models through a single API. OpenRouter provides access to models from multiple providers.
- Create an account at openrouter.ai
- Generate an API key
- Add it in Settings > Integrations or set
OPENROUTER_API_KEYin your environment
Google Gemini
Use Google's Gemini models for the AI Assistant.
- Get an API key from Google AI Studio
- Add it in Settings > Integrations or set
GOOGLE_GEMINI_API_KEYin your environment
Task-Aware AI
The AI Assistant is context-aware. When you chat with it, ARI automatically injects your current tasks into the conversation context. This means the AI knows what you are working on and can provide more relevant suggestions, help you prioritize, and reference your actual data.
This works across modules — if you are in the Task Manager and ask the AI for help, it already knows your task list without you having to describe it.
Security Best Practices
- Never share your API keys or commit them to version control
- Use different keys for development and production
- Rotate keys periodically
- Set usage limits and billing alerts on each provider's dashboard
- Review API usage in each provider's dashboard regularly