Open protocol for AI agent identity, DNS-anchored and post-quantum native, governed by a nonprofit
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
MX
Pricing model
Not given
Open source
Pricing
Free: 5 successful runs per UTC day after email verification. Starter: $9.90/month for 30M tokens/month. Builder: $19.90/month for 80M tokens/month. Pro: $39.90/month for 200M tokens/month. Scale: $79.90/month for 500M tokens/month. Tokens refresh monthly and do not roll over. One-time token packs a
Free to use. L0 credentials issued today. L1 enabled in agent.bar demonstration. L2 and L3 specified but not yet issued.
Key features
Choice decision type: select from supplied options
Score decision type: assign level on defined scale
Noul decision type: yes/no judgment against criterion
Decision flows: chain questions on canvas with branching
Batch processing for CSV, TXT, JSONL files up to 1,000 rows
Shared account balance across console, batch and API
Export results as CSV or JSONL
Failed requests are refunded
Probabilities included with all answers
W3C Verifiable Credentials (AID format)
Four trust levels (L0-L3) with progressive verification
DNS anchoring starting at L1
ML-DSA-65 + Ed25519 composite signatures
ARIA AP for signed requests and receipts
Append-only Trust Ledger with credential lifecycle events
Revocation capability with signed status lists
Public REST API verification endpoint
TypeScript SDK for credential verification
What makes it different
One API and console for playground, flows, batch and API access
Only questions on the executed path in flows are billed
Built on TypeSafe AI's Jev structured decision model
Test and measure decisions on your own data before production
Custom decision criteria defined by your own labels and rules
Post-quantum native from launch, not a migration plan
Governed by nonprofit to prevent capture
Complements existing protocols without replacing them
JevModel
ARIA Protocol