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
Integrates with Slack, Linear, and GitHub
Runs on your own devices using your existing Claude and Codex subscriptions
Shared skills that teams can publish and install
Recurring schedules for progress updates and routine checks
Shared memory across company and channels
Access control for devices, skills, memory, and schedules
Proactive responses to surface missing context
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
Runs on your own machines with no separate model billing
Multiplayer by default with work visible to entire team
Lives in existing collaboration tools, not a separate app
Shared skills and memory compound across the team
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
Merlin
Kairos