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
Cloud - run applications on stable HTTPS routes
CLI - command-line access to workspace and cloud
MCP integration - bring your own AI agents
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
Works with AI agents you already use via MCP integration
All workspace apps included at no extra cost
Single CLI for humans and agents to access all tools
Cloud services separate from workspace pricing
Set agent direction and permissions yourself
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