Free: 0 € per month with 10,000 successful tool calls each month. Premium: unlimited tool calls subject to fair-use rules, manage or cancel monthly through your account.
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
Connect ChatGPT and Claude through Model Context Protocol
Manage files with AI assistants
Run authorized terminal commands
Device-specific access control
Local approval for sensitive actions
OAuth and secure pairing
Support for macOS, Windows and Linux
Launch and monitor applications
Revokable device access
Encrypted HTTPS connection
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
Keep your computer powered on and in control while AI assistants execute approved actions
No port forwarding or hidden background service required
Visible terminal agent with explicit local approval for sensitive operations
Stop the connection at any time by closing the agent
Device pairing tied to your account with transparent management
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
Kairos