| What it does | Authorization layer for AI agent spend with human-approved mandates and tamper-evident proof
| An engine for long-running agents that rebuilds its prompt under a cap and runs on your budget
|
|---|
| Stage | Startup
| MVP
|
|---|
| Founded | 2026
| Not given
|
|---|
| Based in | Not given
| Not given
|
|---|
| Pricing model | Free trial
| Freemium
|
|---|
| Pricing | Free 12 week pilot for card issuing platforms
| Prototype: free during beta, then from December 16, 2026 it costs $1 per 1,000 agent calls after 1,000 monthly included calls. Production: $20 a month with 20,000 agent calls included, then $1 per 1,000 calls after that. Top-ups: $1 per 1,000 calls, from $10 to $500 at a time, never expiring.
|
|---|
| 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
| - Prompt rebuilt from journal under token cap at each step to keep it bounded as history grows
- Spending limits checked before each model call at token prices you declare
- Resume after crash without repeating finished actions
- Tool calls returned as actions for your code to carry out
- Proof of what ran: check prompts, re-run engine, download hash-chained journal
- Integrations with Vercel AI SDK, OpenAI Agents SDK, LangGraph, Mastra, Pydantic AI
- MCP server for Claude Code, Claude Projects and Codex
- Works with any model via bring-your-own-key
- TypeScript and Python clients for HTTP API access
|
|---|
| 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
| - Bounded prompt under a fixed cap while history grows, so costs per call stop climbing on long sessions
- Every run recorded with cryptographic proof: rebuilable prompts, hash-chained journal, re-runnable engine
- Resumes from crash without repeating finished actions using stable idempotency keys
- Budget enforcement before each model call, not reactive overage billing
- No model key storage or logging; your provider bills you directly
|
|---|
| Free plan | Not given
| Not given
|
|---|
| Open source | Not given
| Not given
|
|---|
| Platforms | Not given
| Not given
|
|---|
| Public API | Not given
| Not given
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | Not checked yet ● no change since last check | Not checked yet ● no change since last check |
|---|
| Trust Flow (Majestic) | 0 | 0 |
|---|
| Citation Flow (Majestic) | 0 | 9 |
|---|
| Referring domains (Majestic) | 0 | 4 |
|---|
Levee
Argentic