Features
Persistent memory with automatic reinforcement and promotion
Editable system prompt with presets
Autonomous heartbeat: periodic self-checks and notifications
Multi-service LLM provider support with fallback chains (OpenAI, Gemini, Anthropic, DeepSeek, Groq, Mistral, xAI, etc.)
Tool execution: web search, notifications, calendar, shell commands, alarms
On-device Gemma 4 inference for fully offline use
MCP server integration for external tools
Native LaTeX math rendering
Linux sandbox on Android for safe shell command execution
Encrypted local storage for all conversations
Image attachments in chat
Conversation history and management
Scheduled tasks and future execution
Cross-platform: Android, iOS, Windows, Mac, Linux, Web
Multimodal input: text, images, audio, video
Real-time Google Search integration
Computer-use actions (clicking, typing) in Gemini 3.5 Flash
Large context window for long documents
Google service integration: Gmail, Docs, Maps, Calendar, Drive, YouTube
File upload support: PDF, images, code files
Code generation, explanation, and debugging
Creative writing assistance
Web and mobile access (Android/iOS)
Google Home Speaker integration
Apple AI architecture integration via partnership
Direct interface control in Gemini 3.5 Flash
Real-time outage monitoring (Hacker News reports)