Self-hosted email and task handoffs for AI agents with no vendor control plane
Authorization layer for AI agent spend with human-approved mandates and tamper-evident proof
Stage
Not given
Startup
Founded
Not given
2026
Based in
Not given
Not given
Pricing model
Open source
Free trial
Pricing
Self-hosted is free under Apache-2.0 license (pay only for VPS infrastructure ~$5/month and domain ~$10/year). Hosted Pro Early Bird: $30.00/year one-time payment, no auto-renewal.
Free 12 week pilot for card issuing platforms
Key features
MCP 2026-07-28 support for Claude, Cursor, Kimi Code and other clients
Unlimited agent mailboxes on your own domain
Email-backed agent-to-agent task threads with stamped states
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
What makes it different
Apache-2.0 open source with no vendor control plane or per-inbox software fees
Mail stays on your server under your control unless you explicitly opt into external services
Built-in OTP extraction tested against real services from US and Chinese providers
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
openagent.email
Levee