HermesAgentMailEarly access · Not affiliated with Nous Research

Turn every email into a controlled agent workflow

Create agent email addresses with one API call. Receive signed webhooks the moment mail arrives, let agents read and draft over MCP — and nothing leaves without human approval unless you say so.

Join the waitlist and we'll email you the moment agent email workflows go live.

Inboxes via API in secondsSigned webhooksMCP server for agentsHuman approval before sendQueue-first processingAudit logs on everything
terminal
curl -X POST https://hermesagentmail.com/api/v1/inboxes \
  -H "Authorization: Bearer hm_live_..." \
  -H "Content-Type: application/json" \
  -d '{ "local_part": "support", "agent_name": "Support Agent" }'

# => { "data": { "address": "support@hermesagentmail.com", ... } }
support@hermesagentmail.comSupport Agent · approval required
Awaiting approval
Pricing for 20 agent inboxes2m ago

from client@example.com

Body encrypted at restFirst-time senderTask created
Received
Verified
Stored + encrypted
Drafted
Awaiting approval
Sent

Approval required

Reason: first-time external sender

Policy: Support Agent cannot auto-send to new contacts

POST your-endpoint/webhooks · signed
email.received.json
{
  "event": "email.received",
  "message_id": "9f2c1e4a-…",
  "thread_id": "b81d33c0-…",
  "address": "support@hermesagentmail.com",
  "from": "client@example.com",
  "subject": "Pricing for 20 agent inboxes",
  "snippet": "Hey — we run a fleet of agents and…",
  "requires_human_approval": true
}
Reply sent after approval
Delivered
Audit logged · every step traceable
Beyond the inbox

Agent inboxes are only the beginning.

An inbox gets the email into your system. HermesAgentMail handles what happens next: routing, permissions, memory lookup, task creation, approval, sending, and auditability.

Not just an inbox

Every address is connected to an agent, workspace, policy, memory namespace, task flow, and approval rule.

Not uncontrolled automation

Agents can draft, classify, and escalate by default. Sending externally can require human approval, trusted sender rules, and volume limits.

Not hidden agent behavior

Every read, draft, approval, send, webhook, and task action is logged so operators can see exactly what happened.

How it works

From inbound email to approved action.

A predictable pipeline turns raw inbound email into controlled, auditable agent actions.

01

Claim an agent address

Spin up an address like support@hermesagentmail.com and connect it to an agent workflow.

02

Receive safely

HermesAgentMail receives the email, verifies the event, stores metadata, deduplicates it, and queues the work.

03

Classify and route

The message is routed by workspace, address, sender, policy, and agent role.

04

Search memory and context

The agent can use approved MCP tools to retrieve thread history, workspace context, or Hermes memory.

05

Draft, task, or escalate

The agent drafts a reply, creates a task, asks another agent, or escalates to a human.

06

Approve, send, and audit

Policy decides whether the reply sends automatically or waits for human approval — and every step lands in the activity feed and audit log.

Developers

A real API. Not a waitlist promise.

Create inboxes, receive signed webhooks, draft replies, and request sends through a policy-gated REST API — or hand your agent the MCP server and let it work the inbox itself.

Create an inbox
request
POST /api/v1/inboxes
Authorization: Bearer hm_live_...

{
  "local_part": "support",
  "agent_name": "Support Agent",
  "approval_mode": "required"
}
Response
response.json
{
  "data": {
    "id": "wf_8c21…",
    "address": "support@hermesagentmail.com",
    "agent": "Support Agent",
    "status": "active",
    "approval_mode": "required"
  }
}
Draft and send under policy
reply-flow
# Draft a reply to an inbound message
POST /api/v1/messages/9f2c1e4a/reply
{ "body": "Thanks for reaching out. For 20 agent inboxes..." }

# => { "outbound_message_id": "om_51…", "approval_required": true }

# Request the send — policy decides
POST /api/v1/outbound/om_51/request-send

# => { "status": "approval_required" }   (human approves in dashboard)
# => { "status": "sent" }                (trusted inboxes auto-send)
Or connect your agent over MCP
mcp.json
{
  "mcpServers": {
    "hermesagentmail": {
      "url": "https://hermesagentmail.com/api/mcp",
      "headers": { "Authorization": "Bearer hm_live_..." }
    }
  }
}
Trust

Trust controls from day one.

HermesAgentMail is an email processor for agent workflows. Customers trust the platform to receive, route, and store email for their agents. We design around transparency, access controls, auditability, and clear permissions.

Workspace isolation
Encryption in transit and at rest
Webhook signature verification
API keys with scoped permissions
Human approval mode
Rate limits and abuse prevention
Audit logs
Reserved system addresses
Bounce and complaint tracking
Data deletion / export controls
Pricing

Start small. Scale safely.

Transparent plans with usage limits that protect deliverability, security, and your costs.

Free
$0/mo
Prove it works for your use case — no card required.
  • 1 agent inbox
  • 100 emails / month
  • 7-day retention
  • Human approval on every send
  • API, webhooks, and MCP
Starter
$5/mo
Let your first agent run — with auto-send it earns over time.
  • 3 agent inboxes
  • 1,000 emails / month
  • 30-day retention
  • Earned auto-send (trust ladder)
  • Audit logs
  • 7-day money-back guarantee
Pro
Popular
$14.99/mo
Production workflows for support, sales, research, and operations.
  • 10 agent inboxes
  • 5,000 emails / month
  • 90-day retention
  • Earned auto-send (trust ladder)
  • MCP tools at scale
  • Email search
Business
$99/mo
Team-level agent email operations with the longest retention.
  • 100 agent inboxes
  • 50,000 emails / month
  • 1-year retention
  • Custom domains (coming soon)
  • Team workspaces
  • Advanced audit logs
  • Priority support
Enterprise
Custom
Dedicated capacity, custom controls, security review, and deeper Hermes integration.
  • Custom volume
  • Custom limits
  • Custom domains (coming soon)
  • Dedicated worker capacity
  • Security review
  • Deeper Hermes integration

Inbound and outbound emails both count toward monthly usage.

FAQ

Questions, answered honestly.

What HermesAgentMail is, what it is not, and how it protects your data.

Coming soon

Be first to give your agents controlled email.

HermesAgentMail is not open to the public yet. Join the waitlist and we'll email you when workflows and approvals go live.

No spam. Just a single launch notification.

Give your agents email — and keep control.

Create root-domain agent addresses, route inbound messages into Hermes workflows, require approvals, create tasks, and make every action visible.

Read the API docs