Authorization layer for AI agent spend with human-approved mandates and tamper-evident proof
Hosted memory for AI agents that forgets like people do
Stage
Startup
Not given
Founded
2026
Not given
Based in
Not given
Not given
Pricing model
Free trial
Free trial
Pricing
Free 12 week pilot for card issuing platforms
Two meters: user turns (per user turn) and stored memory (per GB-month). Pricing to be announced. Free tier with monthly allowance of turns and memories.
Key features
Passkey-signed spend mandates with purpose, budget, merchants, and time windows
Real-time authorization decisions with sub-1 second response time at p99
Human challenge via passkey step-up for exceptional spend
Fail-closed payment processing if no decision arrives in time
Hash-chained evidence ledger with tamper-evident records
Exportable evidence packs for chargebacks and audits
Supports card, wallet, x402 and stablecoin payment rails
Conversation episodes with automatic cutting and concept-based organization
Activation fading by square root of time with significance tracking
Automatic fact extraction and indexing for recall
Recall system that surfaces relevant past facts when needed
Sleep function that fades context after 24+ hours of silence
Fallback to local tail when service is unreachable
What makes it different
Human-approved mandates enforce intent, not just static limits or merchant category blocks
Operates outside the agent in the issuer's authorization path, preventing agent bypass or override
Creates tamper-evident audit trail linked to agent identity, run, and policy version
Never holds funds or issues cards; integrates with existing issuer infrastructure
Single mandate and policy core across multiple payment rails and issuers
Forgets like people do with fading by time, not truncation
Your model, your key, your loop; service only holds history
Facts kept permanently even as episodes fade from view
Decorate, submit, report: only three lines of integration
Human-inspired memory mechanism based on cognitive science