Launch HN: AgentMail (YC S25) – An API that gives agents their own email inboxes
59 points
2 hours ago
| 20 comments
| HN
Hey HN, we're Haakam, Michael, and Adi. We're building AgentMail (https://agentmail.to), the email inbox API for agents. We’re not talking about AI for your email, this is email for your AI.

Email is an optimal interface for long-running agents. It’s multithreaded and asynchronous with full support for rich text and files. It’s a universal protocol with identity and authentication built in. Moreover, a lot of workflow critical context already lives in email.

We wanted to build email agents that you can forward your work to and get back a completed task. The agents could act entirely autonomously as you wouldn't need to delegate your identity. If they did get stuck they could just send you, or anyone else, an email.

Using Gmail, we kept getting stuck on the limitations of their API. No way to create inboxes programmatically. Rate and sending limits. OAuth for every single inbox. Keyword search that doesn't understand context. Per-seat pricing that doesn't work for agents.

So we built what we wished existed: an email provider for developers. APIs for creating inboxes and configuring domains. Email parsing and threading. Text extraction from attachments. Realtime webhooks and websockets. Semantic search across inboxes. Usage-based pricing that works for agents.

Developers, startups, and enterprises are already deploying email agents with AgentMail. Agents that convert conversations and documents into structured data. Agents that source quotes, negotiate prices, and get the best deals. Agents that emulate internet users for training models on end-to-end tasks.

Here's demo of Clawdbots communicating using AgentMail: https://youtu.be/Y0MfUWS3LKQ

You can get started with AgentMail for free at https://agentmail.to

Looking forward to hearing your thoughts and feedback.

MattDaEskimo
36 minutes ago
[-]
I'm concerned that this fits in "using today's innovation to solve outdated paradigms".

Google has A2A: An Agent-to-Agent Protocol. SaaS is plumetting in value.

Arbitrary semantics made sense when communications were human-dominated.

If agents dominate these fields, why wouldn't they simply set their own protocols and methods to communicate both text, binary, and agreed data structures?

There's an assumption that email is somehow the best channel, when you've found yourself that the most popular, functional interfaces don't align with your expectations.

Then, ultimately I have a single agent that can sit in numerous communication platforms, such as email

reply
mhykim
21 minutes ago
[-]
Fair concern, and I agree on the end state. Agents will eventually use native agent-to-agent protocols.

The question is the transition, because email is undoubtedly the most ubiquitous channel of communication in today. I would only give my agent an A2A integration if your agent has an A2A integration, but because you don't we are at a stalemate. I'd rather just give my agent an inbox where I know it can communicate with the other billions of people that already have an email address.

Email isn’t the final protocol for agents. It’s the bridge that lets them participate in today’s internet while native agent protocols/networks emerge.

reply
rippeltippel
1 hour ago
[-]
Finally agents can spam other agents, instead of humans.
reply
Haakam21
1 hour ago
[-]
I think agentic email communication can be productive as well!
reply
biddit
1 hour ago
[-]
> Agents that source quotes, negotiate prices, and get the best deals.

Didn't Alexa fail miserably with the "have AI buy something for me" theory?

There is a significant mental in allowing someone else make purchase decisions on my behalf:

- With a human, there is accountability.

- With deterministic software, there is reproducibility.

With an agent, you get neither.

FWIW - I am not anti-LLM. I work with them and build them full time.

reply
gustrigos
1 hour ago
[-]
We are using AgentMail for sourcing quotes here at scale with various top shippers. It’s not about letting the agent act in fully deterministic ways, it’s about setting up the right guardrails. The agents can now do most of the job, but when there’s low confidence on their output, we have human in the loop systems to act fast. At least in competitive industries like logistics, if you don’t leverage these types of workflows, you’re getting very behind, which ultimately costs you more money than being off by some dollars or cents when giving a quote back.
reply
biddit
39 minutes ago
[-]
Okay that makes sense.

Do you see more pushback in specific industries? I did some quote/purchasing automation work in food mfg a decade ago, and those guys were super difficult to work with. Very opaque, guarded, old-school industry.

reply
Haakam21
1 hour ago
[-]
This refers to B2B use cases that are live in production. Finding, contacting, and negotiating with vendors is a tedious process in many industries. In the time a human reaches out to 10 vendors, an agent reaches out to 100 or 1000. So it finds deals that a human would not have.
reply
trollbridge
13 minutes ago
[-]
Once vendors are getting AI spam sent to 1,000 of them and their competitors, they will stop responding and find other sales channels. This won't be sustainable.
reply
fmbb
53 minutes ago
[-]
But if you hire ten or 100 real humans you have accountability and the same number of contacts per day?

Are logistics companies really that poor so they cannot afford to pay workers wages?

reply
mhykim
16 minutes ago
[-]
The tradeoff isnt agents vs humans its where humans sit in the loop.

Sure hiring 10–100 humans gives accountability, but reality is it doesn't scale in any comparable way compared to agents in speed, coverage, or responsiveness. The sheer volume agents can pump out(more vendors, more quotes, faster cycles) is the benefit, while humans retain accountability at the decision boundary.

In practice the agent does the gruntwork, and the human gets looped in when confidence is low. Accountability doesnt dissapear, it gets concentrated where it matters most

reply
nerdsniper
1 hour ago
[-]
How does this differentiate from a solution like AWS SES? (Which I assume AI Agents would be quite adept at using to send email)

I understand the differentiator vs GMail, but API-based scripted email access isn’t new.

reply
Haakam21
1 hour ago
[-]
Because we built the same inbox infrastructure as Gmail. Inboxes have threads, threads have messages, messages have attachments. You can search, label, filter, reply, forward. None of this comes out of the box with SES.
reply
trollbridge
13 minutes ago
[-]
Couldn't someone just ask Claude Code to make an email system with threads/messages and handle attachments?

Doesn't seem like a particularly difficult problem to solve.

reply
benswerd
58 minutes ago
[-]
I didn't get it until you said this
reply
mrklol
18 minutes ago
[-]
Looks like SES + api access, isn’t Amazon offering that already?
reply
ktanishqk
6 minutes ago
[-]
> Because we built the same inbox infrastructure as Gmail. Inboxes have threads, threads have messages, messages have attachments. You can search, label, filter, reply, forward. None of this comes out of the box with SES.

aws just gives you a low-level smtp + api service. we are the application layer they do not offer but your agents need to actually use email as first-class users.

reply
smpandya
1 hour ago
[-]
Cool launch. Assuming you guys view email (and therefore SMTP) as becoming the de facto agent communication protocol in the long run. My question — why not something bespoke, similar to OpenAI’s Agentic Commerce Protocol or x402 from Coinbase?
reply
Haakam21
1 hour ago
[-]
Network effects - agents need to meet humans where they already work. Would rather use something standard than bespoke.
reply
trollbridge
12 minutes ago
[-]
And how long will humans and agents be communicating over email?

We have strict rules for our customer service people not to respond to what seems to be a bot, since all the "agent" based communication we get is for conducting scams. It is never worthwhile to engage with or pursue.

If we lose a sale or two, that's okay.

reply
wild_egg
1 hour ago
[-]
> Email is an optimal interface for long-running agents.

Long-running agents are themselves not optimal though. There are a ton of these coordination layers for long running agents now but they don't make any sense under other paradigms

reply
Haakam21
1 hour ago
[-]
Hmm why do you say that? Would love to hear your thoughts
reply
umrashrf
33 minutes ago
[-]
So AgentMail uses Mail Agent
reply
mhykim
10 minutes ago
[-]
Nope AgentMail is its own infra. Not a single line of Gmail/Outlook code in the codebase
reply
TacoCommander
9 minutes ago
[-]
whooosh
reply
throw03172019
2 hours ago
[-]
The 2FA via email case is great. I recently had to build a browser automation workflow that required 2FA. I ended up using Zapier to monitor email inbox and then extract the code and send back to our API. It was a bit slow.
reply
ckenst
1 hour ago
[-]
Why didn't you just use something like Mailinator? They specialize in this exact thing. Gives you an API to grab links and everything. That's what I use.
reply
Haakam21
2 hours ago
[-]
Yup plus webhooks are overkill for this. Need to set up a public HTTP server and pass messages to your agents. With websockets you can open connection right from your agent and close it in seconds once the 2FA code is delivered.
reply
trollbridge
11 minutes ago
[-]
... you had to use Zapier to extract an email from an inbox?
reply
dbushell
1 hour ago
[-]
Dead internet theory.
reply
chasd00
2 hours ago
[-]
hah this is a great idea! sending email is such a common way to communicate and having agents with an inbox makes so much obvious sense. heh just don't let their addresses get out who knows how they'll respond to spam and phishing attempts.
reply
Haakam21
1 hour ago
[-]
This is a good point. We have anti-spam measures in place and allow users to configure allow/blocklists to mitigate attacks.
reply
trollbridge
11 minutes ago
[-]
What about a concerted attack?

Spam doesn't matter for an agent mailbox, but sophisticated fraud does.

reply
rootnod3
2 hours ago
[-]
Can't wait for agents to change the code they are building to buy Amazon Point cards at Target and send the codes back.
reply
ritomsen09
1 hour ago
[-]
How do you think this will help with identity verification in the future?
reply
mhykim
1 hour ago
[-]
Email is already the internet’s identity layer. By giving agents their own inbox they don't need to borrow human identity rather act as first class actors on their own.

It lets agents plug into the same trust systems the web already uses! And this opens the door to new ways agents can do work and build credibility on the internet.

reply
Haakam21
1 hour ago
[-]
The nice thing about email is that identity verification is already built in. In fact online identity is based on email.
reply
pbronez
1 hour ago
[-]
Very interesting. I have a lot of enterprise AI use cases that would really benefit from being email native.

We’re an O365 GCC shop. Appreciate that your enterprise options include Bring Your Own Cloud, that makes things much easier for us.

It would be nice to have integrations with n8n and Glean.

reply
Haakam21
1 hour ago
[-]
Thats why we built it :) We have an integration with n8n, will build one for Glean
reply
thedrake
1 hour ago
[-]
and a request for gumloop. (a YC alum) https://docs.gumloop.com/
reply
alongub
1 hour ago
[-]
AgentMail looks amazing!
reply
wild_egg
1 hour ago
[-]
reply
ktanishqk
32 minutes ago
[-]
yup, hard to do that too. AgentMail actually gives agents email addresses and treats them as first class inbox owners with the capability of sending and receiving emails with any other email address.

the mcp agent mail project is agents getting their own identity in an internal messaging layer.

reply
waynenilsen
2 hours ago
[-]
amazing now do the same for voice and sms!
reply
stronglikedan
1 hour ago
[-]
Done. Texts can be sent to email addresses and texts can be sent via email, and you can dictate texts and have them read back to you with text-to-voice.
reply
Haakam21
1 hour ago
[-]
We have gotten a lot of requests for SMS. Seems like a natural next step.
reply
waynenilsen
1 hour ago
[-]
i think when someone makes the cli like this they're going to win

$ phone call bill

ok call_id=3f2a

$ phone status 3f2a

dialing

$ phone status 3f2a

answered

bill: hello

$ phone say 3f2a "hey, quick question"

ok

reply
singpolyma3
1 hour ago
[-]
Good luck getting this past A2P campaign registration rules...
reply
keepamovin
2 hours ago
[-]
Hey I’m also working on this what a coincidence: https://ai-chat.email

Second time at least HN is launching YC on one of my products:

BrowserBox - hyperbeam

Mailpilot/AI-chat.email - agentnail

reply
Haakam21
1 hour ago
[-]
Nice seems like we are building towards a similar vision. Would love to collaborate!
reply
keepamovin
1 hour ago
[-]
Sure, bud. Cut me in on your 500K!

My Show from 14 days ago: https://news.ycombinator.com/item?id=46629191 - hmm, why didn't it get into YC?

reply
freedomben
38 minutes ago
[-]
Just trying to provide you some helpful feedback. This reply comes off pretty rude, bitter, and immature. Probably not the look you want if you're trying to get funding.
reply
trollbridge
9 minutes ago
[-]
Or we could just accept reality that there is no moat around this kind of stuff.

This seems like an afternoon or weekend project to build, particularly with the promises made about how much more efficient coding is with AI tools now.

reply
HarryDu
2 hours ago
[-]
In the future all the agent communication will be using agentmail!
reply
Haakam21
1 hour ago
[-]
Don't know about all but certainly a significant proportion!
reply
rootnod3
2 hours ago
[-]
"Application error: a client-side exception has occurred while loading www.agentmail.to (see the browser console for more information)."

> Looks at developer console...

- "Failed to create WebGL context: WebGL is currently disabled." Dafuq does an email website need WebGL for?

- "Cookie “dmn_chk_xxxxxxxx-yyyy-dead-beef-123456789ABC” has been rejected for invalid domain."

Let me guess...vibe-coded?

reply
rootnod3
1 hour ago
[-]
Love getting downvoted for mentioning that the website doesn't properly load and reeks of vibe coding :D

If that's the quality y'all can live with and accept, no wonder the web turned to shit.

reply
kasane_teto
1 hour ago
[-]
trvth
reply
Haakam21
2 hours ago
[-]
Taking a look will make a fix asap
reply
trollbridge
6 minutes ago
[-]
This is just a graphic design gripe, but on:

https://www.agentmail.to/enterprise

the cutesy ASCII art is rendered in a proportional, not monospace, font, so it looks terrible.

reply
acedTrex
2 hours ago
[-]
I can smell it from here tbh
reply
rootnod3
2 hours ago
[-]
reply
kushbhuwalka
1 hour ago
[-]
lets goooo
reply