Proof of what an AI agent was allowed to do, and what it then did
Spend control for AI agents
Stage
Startup
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Open source
Paid
Pricing
Not given
Starter $11/month for 1 user and up to 3 devices with spend caps, kill switch, loop detection, 30 days of history and email alerts. Pro $22/month for up to 5 members and 10 devices with everything in Starter plus Slack and Discord alerts, shared team budgets, 1 year of history and invoice reconcilia
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
Loop detection to catch runaway agents
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
Local by default with provider keys staying on your machine
Cost reserved before requests reach the provider to prevent overages
Works offline with local caps and kill switch continuing to function
Supports multiple models and providers including Claude, OpenAI and Anthropic
Team controls with scoped device access and shared budgets
Provared
Leash