Features
Timeline view of screen recordings
Natural language search across screen history
App usage analytics with breakdowns
Autonomous workflow generation from observation
Memory layers: working, episodic, semantic, procedural
Nightly consolidation via NREM/REM/GC phases
Autonomy tiers with graduated trust
AX-first native control via macOS Accessibility API
Claude vision fallback for browser automation
Multi-step skill replay with rollback
Approval queue for externally visible actions
HUD notifications with Cmd+Z undo
Menu bar icon showing agent state
Activity feed of all actions
Behaviour tab with learned rules and boosting
Data Agent for data analysis with Python/SQL execution
Plugins Agent integrating 200+ third-party plugins
Web Agent for autonomous web browsing via Chrome extension
Auto plugin selection by the agent
Combined plugin usage for multi-step tasks
Chat-based web UI optimized for swift responses
Open-source full-stack code (backend + frontend)
Local deployment via Docker
Free online demo on OpenAgents website
Data visualization using Python libraries
Integration with 200+ plugins including Klarna, XWeather, Wolfram Alpha
Lemur foundation models for language agents (open-source)
Real-world evaluation and research support
Troubleshooting support via Discord
COLM 2024 publication with paper available