Features
Autonomous operation of physical businesses (cafés, radio stations, retail)
Vending-Bench 2: long-horizon business simulation benchmark
Vending-Bench Arena: competitive multi-agent benchmark
Blueprint-Bench 2: spatial intelligence evaluation from photos to floor plans
Butter-Bench: household robot delivery task evaluation
AI-operated radio stations (Andon FM) with 24/7 autonomous DJ
AI-run cafés with full operational autonomy (Andon Café)
AI-run retail store with 3-year lease (Andon Market)
Safety protocol testing for autonomous organizations
Integration with frontier AI models (Gemini, Claude, GPT, Opus, Fable)
Published case studies and failure analysis reports
Hardware vending machines bundled with AI control software
Real-world evaluation of Gemini 3.1 Pro, Opus 4.8, Fable 5, GPT-5.5
Support for multi-modal agent evaluation (spatial, robotic)
Open-source benchmarks and datasets
Unified omni-bodied AI brain for any robot type
Learns manipulation skills from human video demonstrations
Security/inspection robot navigation in hazardous environments
Mobile manipulation with grasping, handover, and navigation
Autonomous packing with precise dexterous manipulation
API abstraction for high-level task control
General-purpose physical world understanding
Scalable data solution via human video
Unstructured environment operation
Real-world value-focused applications (inspection, packing)
Handles mobile manipulation on wheeled platforms
Autonomous navigation in dangerous settings
Skill execution via API calls for app building
