An always-on personal AI agent for your Mac that keeps working after you close the window, asks before it acts, and learns from your corrections.
The transaction layer for AI agents
Stage
MVP
MVP
Founded
Not given
Not given
Based in
Not given
US
Pricing model
Not given
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
Always on: keeps working after you close the window
Persistent memory
Browses the web
Focused automation with scheduled routines
Lives everywhere: menu bar, Telegram and Slack
Asks before it acts
Learns from your corrections
Multiple AI model support
Local data storage
Runs in macOS sandbox
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
Keeps working after you close the window with background running in menu bar
Asks before it acts with user approval built into all actions
Local data storage on your Mac with encrypted API keys
Flexible AI model integration with multiple providers supported
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