Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- WorkOS is launching auth.md which offers a generic version of this for allowing agents to sign up for services in general, and I think their security approach is a little bit better thought outby bookernath
- i love what workos is doing and i also spoke at their event already. we think this is complementary - we're not setting out to create a new standard, we're giving better access to what already exists.by adisingh13
- I'm just not seeing why anyone would buy a paid plan for this when they could buy a domain for <$10, and throw something like MXRoute or one of the numerous mailserver Docker scripts behind it. Then their LLM can make as many inboxes as they need without paying anything. The same thing could get bundled by the people who sell preconfigured OpenClaw VMs.
For a home user not even willing to do/pay for that, do they really need a whole API for making inboxes? Couldn't they just set up a second Gmail for LLMs and then put the password in their agent's memory?
- This is like saying - 'I don't understand why anybody would ever buy a pizza from a store. All you have to do is get some flour, water, tomato sauce, cheese, mix the flour and water together, whip the dough, add tomato sauce, put cheese on top of it, cook it for 20 minutes, and then serve it.'
So __much__ value is in the fact things are easy. Money is __not__ the most valuable thing in the world.
by HPMOR - I would imagine that many websites will block this domain, but that’s also ok because there’s nothing wrong with an owner deciding their site is for humans only. My hope is that you do not facilitate their circumvention of that policy.by janalsncm
- Not looking forward to a dehumanized internet where that’s mainstream… agents are tools to support humans, here you’re helping them impersonating humans. That feels pretty terrible to be honest
> The internet was made for humans exclusively, designed to keep machines out by default.
I don’t buy that at all. APIs exist to enable “machines” to interact with services
by dgellow - I do think agents will become users in the same capacity as humans.by Haakam21
- Actually, the internet has space for both. The problem is machines "acting like humans", that destroys the human experience. [machine <-> machine] is fundamental to keep the internet alive (services).by teamsolid
- In principle this tool allows the owner of a website to block this domain entirely. Although I’m not sure the incentives are really aligned.by janalsncm
- Any automation-friendly email hosting is going to have a serious spam problem, and therefore a blacklisting problem.
I suggest taking a look at what providers like Sendgrid, Mailchimp, etc are doing to prevent abuse.
by maltalex - thanks for the feedback! it is top of mind for us, and we've done our research to prevent this as much as possible. it is constantly ongoing and we never settle in our measures to protect against thisby adisingh13
- OK, I get this. I gave email addresses to all my agent profiles using Migadu, which required a password from me somewhere -- with a whole team of agents, this is a lot of manual setup by default. After I gave them emails, I invited them to team plans and discovered the many services that detect them as bots despite their email address at a domain and mailserver with good reputation. There is a problem to be solved here.
That being said -- my agents only email each other and me! AgentMail is an OK start with the human <-> agent requirement, but consider that is a whitelist of a single email. The feature for AgentMail should be: we let your agent sign up easily for an email, and it has a very limited list of addresses and domains it can send outgoing email. This is very unlike normal email! I actually can't think of a single (human-facing) provider that will enable me to blacklist domains at the mailserver level to prevent outgoing mail from going to forbidden destinations.
Allowing a bot/agent to send email to any domain, with only a tagline to indicate the bot, is spam. But -- just like sandboxing the network and CLI commands available to the agent on my Mac Mini -- sandboxing an agent's email would just be the smart thing to do.
Pivot to an agent email sandbox and you will get plenty of the right kinds of customers, who won't ruin your mailserver reputation. Provide some easy agent-friendly whitelists out-of-the-box like same-custom-domain, and a similar approval system for new addresses/domains built on your OTP setup.
by doublerebel - It looks interesting as a hackathon project. I might be short sighted but how does this is YC S25 level good?
This looks like one of the easiest way to get your domain blacklisted in all the email providers.
by saddist0 - > This looks like one of the easiest way to get your domain blacklisted in all the email providers.
Disrupt sounds like a strange word here. This is an area where they're going to have to innovate.
by coro_1 - I think its the energy and passion that YC is investing in. At times too much understanding stops you from doing things which may seem infeasible/wrong/illegal/unethical and one does not even goes in that direction.
However at scale or in some circumstances people may strike gold. Stripe is a good example I can think of, existing knowledgeable folks were scared of even getting into PCI compliance
by sandeepkd - What the use case apart from commercial spam here? If you even have one, elucidate it clearly and make this service impossible to use for sending spam emails impersonating humans.
As one example do what you could do to prevent spam, humans should have to opt in to receive email from this service. If it is useful they will and this is in fact required by law in many jurisdictions.
Otherwise your servers will be blacklisted for illegally sending spam and you will deserve it.
by grey-area - > Agent needs an inbox and hits AgentMail via curl. Agent receives instructions via MD
I'm fairly AI-optimistic, but I feel like I'm taking crazy pills. Every day the HN story is either "Apple patches actively exploited zero-click RCE" ... or ... "Show HN: Engage With Our Zero-Click RCE".
by m-hodges - > The internet was made for humans exclusively, designed to keep machines out by default.
This feels like a wrong assumption. Internet was not intended for humans explicitly. If anything browsers were the explicit medium made to allow the humans to interact with internet in safe manner.
> Every signup flow assumes a browser, a person reading a page, and clicking a confirmation link. Unless agents can't do that, they can't be first class users of the internet.
This again feels like a misconception. The systems just work with an identity verified by credentials, it doesn't matter if its a program or program prompted by a human that uses it
by sandeepkd - As somebody who spent a lot of time trying to get an agent to register an email address, their assumptions were correct. It is a PITA.
- I wonder what will happen if an agent could signup and use agent mail to receive confirmation email to login. True, there is a misconception.
- > We give AI agents their own email inboxes.
An inbox to receive mail seems good and valuable.
But I'm seeing that your service is also for sending e-mail.
Having a domain oriented toward AI e-mail sending feels like a fast path straight to spam block lists.
However good your intentions are, this will be used for AI spam. People hate AI spam. They will press the report spam button.
by Aurornis - maybe if they charge $, then there's a hashcash like PoW deterrentby TZubiri
- > An inbox to receive mail seems good and valuable.
The only receiving mail applications that come to mind are bots registering for accounts. The point of verifying email is to prove you're not a bot.
by TurdF3rguson - I received this email the other day:
Read to me like an LLM had written it. It references something I said in a HN comment, but it was clearly just an excuse to spamvertise their product.From: Kushal <kushal@kushalsm.com> Date: Mon, 18 May 2026 05:03:11 +0000 Saw your question on the Agent Vault thread about websocket-frame auth (Home Assistant) and the worry about the model reflecting the bearer token back into its own context. chrome-relay's answer is structurally different: the credential never enters the agent's context because the agent never touches it — the HA session lives in your real Chrome (cookies, WS handshake and all), and the agent drives the tab over CDP, only ever seeing the rendered page. URL: https://chrome-relay.kushalsm.com/ For your HA + agent setup today, are you keeping the session alive in a browser the agent attaches to, or doing the WS auth on the agent side and managing the token-in-context risk yourself? KushalI looked at the headers and it contained a List-Unsubscribe header pointing to https://api.agentmail.to
So basically somebody wrote a bot to scrape HN for comments related to some software they wanted to push and send targetted spam. agentmail.to is a Ycombinator funded email service for LLMs which can be, and is, used to send targetted spam and impersonate people. They could mostly solve this problem by adding a block of text to every email expaining an "AI" wrote it. They'd lose customers doing that though of course. I reported this abuse but haven't (and don't expect to) received a response.
I don't even get the point anyway. You can get Claude using an SMTP or IMAP server in seconds.
- Appreciate the concern Mike, and I actually read your email complaining, which helped us ship this next feature. We have a "sent via AgentMail" footer being added soon to outbound emails to identify emails coming from LLM's.
We also are working on adding more robust checks and LLM-based filtering to prevent messages which contain spam or outbound-like copy.
Re; AgentMail next to Claude, we're working on stateful inboxes which help agents actually recall and understand what they're sending and to who. The goal is to provide the rails for intelligent actors rather than slop.
by adisingh13 - See my comment in this thread - I got an email from "someone" (an AI clearly) that signed up for my service (togetherletters.com) from the same domain (agentmail.to) after we had launched on ProductHunt. I looked up the address and that email was never used for a signup and it was just a way to then pitch their product (second email, not the first one it sent). I hate this so much and this is going to now make email just as bad as parts of the web.by sanjayparekh
- You might want to check if your local laws protect against unsolicited emails. In Germany we have §7 UWG which would make that email likely illegal. The List-Unsubscribe header makes it clear it is marketing, automated outreach and not personal. In the UK there is this: https://ico.org.uk/for-organisations/direct-marketing-and-pr...by dgellow