Proof of what an AI agent was allowed to do, and what it then did
TypeSafe AI for structured decisions, routing, moderation, and agent workflows
Stage
Startup
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Open source
Paid
Pricing
Not given
Free tier with 1,000 gift credits after sign-in and 10 free decisions daily. Starter: $10 for 100,000 credits. Builder: $100 for 1,000,000 credits. Scale: $1,000 for 11,000,000 credits. All credits valid for 365 days.
Key features
Signed permissions with passkey authentication
Receipts for each agent action with signatures
Free checker tool to verify compliance
Quantum-safe signatures (Ed25519 and ML-DSA-87)
Permission narrowing for helper agents
Permission cancellation with signed acknowledgement
JavaScript and Python libraries
LangChain and Pydantic AI middleware
Choice questions for label selection
Score questions for range values
Noul questions for non-answerable inputs
API key management and credit metering
Support triage routing
Content moderation gates
Confidence scores and explanations
Lead scoring and classification
What makes it different
Only open-source project combining machine-checkable limits, permission narrowing for helpers, and signed permission cancellation
Built entirely from published standards with no hand-made components
Free and no dependencies, sends nothing anywhere or holds money
Distinguishes between record integrity and whether agent stayed within permission
All published versions stay available for backward compatibility
Structured JSON responses instead of free-text parsing
Predictable credit-based pricing per decision
API resale foundation with credit packs and key management