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
Records and checks work evidence
Identifies remaining open tasks
Local checks on your computer
Optional AI-powered review
Compatible with Codex, Claude Code, and Cursor
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
Open source with no licensing costs
Local verification without sending data to external services
Prevents AI agents from drifting or forgetting task progress
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
FinishUP
Kairos