About

The agent-mail company.

What mails.ai is, what we ship today, and where we’re headed.

Mails.ai builds email for AI agents. Not marketing email. Not newsletters. Email that agents send, receive, and parse — programmatically. We’re in closed beta right now. Public access opens in Q3 2026.

What we are.

Mails.ai is email infrastructure built for AI agents — a programmatic email API where the inbox primitive is the design center, not an afterthought of a send-first transactional product. Every agent gets its own address, with reply parsing, identity, reputation, and per-event metered pricing baked in.

We are early. The product is in closed beta. Public API opens at the Phase 1 launch, currently scheduled for Q3 2026. The website you are reading is ahead of the product on purpose — we wanted the architectural picture documented honestly before public signup opens.

What we ship.

Three phases, in order:

Phase 1 (Q3 2026) — Launch. Free 3K events / Pro $20 (50K sends + 50K parses) / Scale $99 (250K sends + 500K parses) + per-event metered ($0.001/send + $0.002/inbound (+$0.003 opt-in classify)) via Stripe metered billing. Structured reply events, six-category prompt-injection scanner, per-agent reputation graph, MCP server, TypeScript + Python SDKs.
Phase 2 (Q4 2026) — Custom domains (DKIM CNAMEs + SPF/DMARC wizard), receiver-side verification API + browser extension, multi-vendor failover hardening (documented runbook for Postmark / SparkPost / Brevo with a ~4-hour DNS swap path).
Phase 3 (Q1 2027) — Per-agent budgets + auto-throttle. Recipient-side reputation verification. Agent-to-agent direct-delivery protocol.

What we don’t do.

No fake customer logos. We are pre-launch. Pretending otherwise is brand suicide.
No marketing-blast platform. We do not ship marketing campaigns, segmented broadcasts, or visual template editors. Agent infrastructure is the focus. SendGrid and others handle that surface well; we do not compete with them.
No enterprise-sales theater. All tiers are self-serve. No SSO/SAML/procurement-only tier. No “contact us for Enterprise.” The pricing page is the price.
No gov-ID upload, no business verification gate. Same self-serve friction floor as Resend and the rest of the transactional category. Abuse is handled architecturally: a per-agent reputation classifier scores every send, suppression runs at send time, and a per-sender complaint cron auto-suspends at 0.3%.