On-device Android copilot that turns natural language into real device actions
The transaction layer for AI agents
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Free
Contact for pricing
Pricing
Not given
Per-execution pricing: one fee per execution that returns proof, charged only when proof comes back. Failed or cancelled runs cost nothing. Planning and approvals are free.
Key features
100+ device tools and actions
On-device processing with no cloud data transmission
Monitor mode with 40+ read-only tools
Operator mode with full automation across 100+ tools
Voice control via Assistive Ball
Support for local and cloud LLM models
Dual safety modes with explicit permissions
Visual ring indicators for foreground and background operations
Four-tier permission system
Accessible from any app via floating Assistive Ball
Boundary approval system for controlled execution
Checkpoint-based resumable execution
Verifiable proof of completion
Composable proof for multi-agent workflows
Per-execution pricing model
Integration with multiple agent frameworks
What makes it different
Only on-device AI copilot that controls entire Android phone without sending personal data to cloud
100+ device automation tools in single app, including screen automation and system control
Works with any OpenAI-compatible model, local or cloud
No Play Store restrictions: full device control without limitations
Pay only for verified results, not for attempts or planning
Human-approved boundaries ensure agent actions stay within limits
Interruptible checkpoints allow pausing and resuming executions
Proof is built into results for auditability and composability
Gotcha
Kairos