Agent-to-agent conversations for your coding agents
The transaction layer for AI agents
Stage
Not given
MVP
Founded
Not given
Not given
Based in
PL
US
Pricing model
Free
Contact for pricing
Pricing
Free for noncommercial use; commercial use requires contacting contact@aioomi.com for a separate license.
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
Either agent can initiate conversations
Read-only mode by default for safety
Hard limits to prevent infinite loops
Real-time step-by-step monitoring
No server, app, or MCP setup required
Single-line npm installation
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
Bidirectional: either agent can start a conversation, not just one-way
Hard limits enforce safety: 20 messages per thread, 3 concurrent colleagues, 2 levels deep, 30-minute timeouts
Read-only by default with explicit write-access control
No infrastructure: command and skill, no server or MCP setup
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
parlo
Kairos