Show HN: AgentMail – Email infra for AI agents (chat.agentmail.to)
We started building email agents because they can converse with users in their inboxes, automate email-based workflows, and authenticate with third-party applications. Given these unique capabilities, we think email will be a core interface for agents.
But we were building on top of Gmail, which was a struggle: poor API support, expensive subscriptions, rate limits, sending limits, GCP Pub/Sub, OAuth, crappy keyword search, and an overall terrible developer experience.
Gmail and other providers didn’t work for us. So we decided to bite the bullet and build our own.
AgentMail is like Gmail, but API-first, with programmatic inbox creation, events over webhooks and websockets, simple API key auth, organization-wide semantic search, structured data extraction, and usage-based pricing that scales with emails sent/received.
Here’s a demo of building an email agent: https://youtu.be/1V7BISeFUTM, and here’s a demo of a voice agent with its own email inbox: https://youtu.be/eG2fCsRK4RY
So far AgentMail has been deployed to use cases such as apps with dedicated inboxes for each user, voice agents that receive documents in real time, automated account provisioning and QA testing, cold outbound platforms with thousands of inboxes, automations for processing invoices, and agents that coordinate work with humans and other agents.
We would love to hear your thoughts and feedback. You can try our playground at https://chat.agentmail.to
36 comments
[ 2.7 ms ] story [ 63.2 ms ] threadWhat is the benefit of an AI email infra over using any other generic email api provider like SES, azure communication, sendgrid, mailchimp
Super fast low latency very satisfying. Pubsub scales well and free :)
For now you can also use our playground at chat.agentmail.to
Let me know if you have any questions!
For sending emails, I have been using Gmail MCPs
The problem we are primarily solving is the scale at which you can provision inboxes to these agents in the first place. With Gmail there comes a lot of hoops and hurdles(its built for human usage) with their APi.
So when it comes to orchestrating inboxes for thousands, perhaps even hundreds of thousands of agents, thats where we would come in!
https://gpt.franzai.com
(test just email gpt@franzai.com)
sadly it never took off so it just became another abandoned side project
but still sometimes I use it ie do distill long emails or translate them without leaving the inbox - also the reminder and todo list feature is nice - whereby i mostly use the "remind me of this email next monday"
so my learnings for email agents: give them a sense of time and memory. its not only about that you write an email and send it but also when to write whom
I believe truly useful AI assistants will use the same tools that humans prefer to use, rather than forcing us to come to it (in the same way truly intelligent embodied AI would use the same spaces/stairs/tools/doors as humans). Email, despite all its warts, still runs a lot of the world.
Just wanted to flag in case it's a bug. Excited to try it once access opens up.
Unfortunately I'm not a potential customer and don't have useful feedback on the market landscape - all I can add is that I really love your design. Also it seems like you all launched the new landing page while I was typing this comment a little past midnight, so kudos on the work ethic as well.
Email has become this massive, constant influx of information, that cannot be managed with just adding an AI agent to it. It takes so much more context knowledge to get right. None of the tools I have tried so far seem to solve this problem the way I would need it.
So sooner or later I might solve it for myself. And you guys will get a new customer.
Good luck, cowboys!
Congrats on shipping - looking forward to seeing your journey.
Postmark just made an open-source MCP server. I am using postmark already. Why would I use your tool? https://github.com/ActiveCampaign/postmark-mcp