Features
Automatic preference learning from Claude Code interactions
Context injection at session start or on-demand
Encrypted memory storage for privacy
Local-first architecture (data stays on device)
Plugin integration with Claude Code via single command
Support for multiple project-specific contexts
Resume sessions with full context intact
Custom memory editing (add, remove, update preferences)
Team-shared memory vaults (Pro tier)
Zero-config setup: five lines to start
Multi-agent orchestration (multiple AI agents)
File editing via VS Code extension
Terminal control and command execution
Git integration for version-aware assistance
Autonomous mode (coming soon)
Advanced task routing rules
Local processing for privacy
Customizable model deployment
