Coding agents on cloud machines with a record of every session
Stage
Startup
Not given
Founded
2026
Not given
Based in
SE
Not given
Pricing model
Paid
Free trial
Pricing
Starter: $199/month (2 active mandates, 5,000 rulings/month). Team: $799/month (20 active mandates, 100,000 rulings/month). Enterprise: Custom pricing. Additional: $20/month per further active mandate and $1 per further 1,000 rulings. Merchants accepting AI-agent payments: 0.5% per settled payment,
Free trial: two machines, up to 2 vCPU and 4 GiB. Cuna Inference pricing: models available at varying rates, such as GLM-5.2 at $1.00 per million input tokens and $4.00 per million output tokens.
Key features
Shadow mode for testing intents without execution
Execute intents in Sandbox (paper fills) or Production (queued orders)
Halt all signing across account with single control
Permissions limited by venue, action, per-transaction and daily caps, expiring within ninety days
Reconciled books recorded on-chain
Receipts with Decionis ruling, order, fill transaction, settlement, ledger entries and balance
HTTP API with strategy contract
Typed error handling with rate limiting and retry support
Idempotent intent submission with intentKey for safe retries
Isolated session execution with bounded authority
Web console for machine management
Complete action recording and visibility
OpenAI-compatible Chat Completions API
OpenCuna terminal agent
Multiple model provider support
Cuna Memory for agent state persistence
Token-based pay-as-you-go pricing
What makes it different
Pre-trade checks ensure intents meet policy before execution
Sandbox environment for paper trading and testing without real execution
Recorded decisions and books reconciled on-chain for audit and transparency
SDKs and MCP server free under Apache License 2.0
User retains custody and control; platform cannot access wallet or private keys
Your Agent. Not a Vendor's.
The work ends. The proof remains.
Complete session records and operational transparency