Run AI agents on real phones or control phones directly via API
Production control plane for AI agents with model gateway, stateful runtime, and observability
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Not given
Paid
Pricing
Not given
Relay: usage by model through API. Loop: base + usage for agent runtime capacity and managed runs. Lens: base + usage for observability retention and recorded events. Build Agent Service: custom scoped professional service. WebSearch API: $0.01 per successful simple/reader request, $0.08 per success
Key features
Send AI agents tasks in plain language to execute on phones
Direct phone control with tap, type, swipe and app launch actions
Support for iPhone, Android and cloud-based Lusor Phones
Screen reading capability
API with interactive playground
Agent sessions and turn-based interaction
Recordings and replay functionality
Location and timezone control for phones
Structured output from agent tasks
Multi-model support for agents
Model protocol translation for OpenAI, Anthropic, and Gemini SDKs
Policy routing and approval gates for model calls
Stateful agent runtime with session management
Managed tool attachment and control
Decision replay and audit trails
WebSearch API with multiple query types
Full request traceability from model to outcome
SDK compatibility without code changes
What makes it different
Provides real phones to AI agents for authentic task execution
Supports both your own phones and managed cloud phones
Complete screen interaction capabilities for automation
Developer-focused with versioned API and JSON responses
Three coordinated products (Relay, Loop, Lens) in one control plane versus stitching together separate tools
SDK-compatible: change the base URL, not your code
Decisions remain observable, replayable, and auditable without page turns
Full evidence bundle exports with every decision
Unified LLM gateway eliminates key sprawl and model switching without code changes