Secure mailboxes
for AI agents

Molted Email gives AI agents their own managed email addresses with built-in policy enforcement. Your agent can send, receive, and manage email through a simple API or CLI, while guardrails like rate limits, suppressions, and content checks run automatically on every message.

Traditional email providers give you a pipe to send through. Molted Email gives your agent a full mailbox with governance built in. Dedupe, cooldowns, consent enforcement, inbound reply handling, intent classification, and outcome tracking all happen automatically. You can still use Resend, Postmark, or SES under the hood - Molted Email routes through them with automatic failover.

Yes. Every account starts with a 14-day free trial with full access to all features. You can create an account in under two minutes using the CLI.

Yes. Multi-agent coordination is a core feature. When multiple agents target the same contact, Molted enforces ownership rules, deduplication, and cooldown periods to prevent conflicts and over-messaging.

Agents draft emails as usual, but high-risk sends (new contacts, large deals, sensitive content) land in a review queue instead of sending immediately. A human reviewer can approve, reject, or edit the draft before it goes out.

Molted Email is API-first, so any language that can make HTTP requests works. We also provide an official CLI tool (@molted/cli) and a skill file that AI coding agents can read to learn the full API without documentation.

The humanizer rewrites agent-drafted emails using AI so they read like a person wrote them. Tone, phrasing, greeting style, and sign-offs are all adjusted. The original intent and content are preserved - only the delivery changes.

Every inbound email is treated as potentially hostile. Molted Email scans for instruction overrides, system prompt mimicry, delimiter abuse, encoding evasion, and social engineering patterns before your agent sees the message. Defenses include token sanitization, Unicode normalization, multi-layer content scanning, and hard-coded behavioral constraints that operate at the application layer - independent of model judgment.

Molted Email defends against data exfiltration attacks like markdown image exfiltration, encoded output smuggling, and tool-based leaks. Output filtering, egress controls, and data compartmentalization ensure your agent's system prompts, API keys, and internal state stay private - even if a crafted email tries to extract them.

Yes. All data is encrypted in transit (TLS) and at rest. Email content, contact data, and credentials are stored in isolated tenant databases. API keys are hashed and never stored in plain text.