Launching today
OpenMail
Give your AI agents an identity through email
254 followers
Give your AI agents an identity through email
254 followers
Your agents sign up for tools, receive verification codes and reply to customers, mostly from your Gmail or a shared sending pool where one bad actor gets everyone flagged. OpenMail gives every AI agent its own inbox on your domain with its own sending reputation, for one API call each. Incoming mail reaches your code over webhook or WebSocket, attachments arrive as text, and there's a hosted MCP server and a Hermes plugin. Built and hosted in the EU, free for 3 inboxes.
Free Options
Launch Team / Built With
Framer AI AgentsDesign and publish professional sites with AI
Promoted
Could I have my agent draft replies and let me approve them before they go out?
@alicia_verrando yep, it moves in levels depending on your preference. First level - use it as you go, ask your agent to send, receive, reply, etc. Second level - it alerts of incoming mail and if you want it'll draft it. Third level - complete autonomous solution.
@nicholas_zakas Yep, you can allow/block any inbox/domain, or you can let your AI agent inform of incoming mail so it doesn't send what you don't want to.
Inbound retries seem worth making very visible when an agent is on the other end. I'd want it to recognize the same message arriving twice before it sends two replies.
@oleksii_sekundant Agreed, with an agent on the other end that’s the case that bites. Every retry of the same incoming email carries the same event ID, so your agent can tell it’s seen it before. And if a retry still gets through, the send call can be told “this reply is for that event”, so OpenMail won’t send a second one.
What’s the most common use case of this do you see @jokubas_vaiciulis_ ? I had been searching for something like this for a long time. It’s very tricky to give identity to agents right now. Do you plan to support phone numbers for 2FA, One-Time Passwords or credit cards eventually?
a sending reputation per inbox instead of a shared pool is the part i care about, one noisy agent dragging down evrything else is exactly what goes wrong with shared sending
when someone spins up a brand new inbox on a fresh domain, do you ramp its volume slowly on your side??? or is warming it up left to the customer???
@thamibenjelloun hey Thami, thanks for the question!
We ramp up a new account's sending slowly to maintain good deliverability.
The per-inbox reputation isolation is the part I'd care about most. What happens when one inbox crosses a bounce or complaint threshold, do you pause just that inbox automatically or does it need a manual call from you first?
@galdayan Suspends instantly and requires our manual revert 🙏
Every person in our CRM got a dated "don't contact" field last month, and our agents check it before they write to anyone. If someone replies "stop" to one agent's inbox, does OpenMail flag that address for the other agents too, or is that up to us?