Simplex (yc S24) – Browser Automation Platform for Developers
Mood
calm
Sentiment
mixed
Category
other
Key topics
Here’s a demo: https://youtu.be/7KpWJbOcm1Y
We’re excited to be posting on HN again! Back in January, we Show HN’d the earliest version of Simplex (https://news.ycombinator.com/item?id=42704160). We’ve now spent close to a year working with real customers, forward-deploying into their codebases, and building web agent systems for them from the ground up to understand what it takes to get agents working in production.
We built Simplex because we started seeing a pattern: companies would initially roll their own Playwright/Stagehand web automation solutions. This worked fine in the early prototype stages, but they’d quickly get overwhelmed with technical challenges as they productionized automations across all the websites their customers use.
As they scaled, they’d have to build and manage:
- Chrome infrastructure: You'll need remote browsers, extension support, browser settings for anti-bot detection/stealth, and a hundred more small fixes.
- DOM parsing: We’ve seen many web portals have really weird quirks (nested iframes, shadow DOM elements, dynamic loading, popups, unstable selectors, etc..) that are hard to parse with traditional/existing browser agents.
- Agent context engineering: Website state, user prompts, system prompts, past actions all take up a massive amount of context. Without managing this, agents can get caught in loops or take wrong actions.
- Caching/reliability: No matter how perfect your prompts are, it’s hard to guarantee consistency without caching/deterministic actions.
- Login/2FA: Solve captcha, fetch 2FA from email/text/Google Auth, encrypt/decrypt credentials to access portals blocked by login.
- Automation management: You’ll have to store all your prompts, scrapers, and agents, and find a way to make them reusable if you have the same workflows across different portals.
- User interface: Creating new workflows + debugging can take time. You’ll have to find easy ways to expose this to your engineers to make the process more efficient when you have hundreds of automations to build.
Simplex is a proper solution that handles all of the above for you. We offer both an UI/dashboard (which is what we use even as technical developers) and an extensive API for customers who are using Simplex in their existing AI agents. Our dashboard/API docs are here: https://simplex.sh/docs. We’d love for you to check them out!
You can get started for free with Simplex at (https://www.simplex.sh/) (you have to register to prevent abuse since we’re giving you a remote browser that connects to the internet).
Our first users have been AI companies across different industries like accounting, logistics/transportation, customer service, and healthtech. We’ve seen them:
- Fill out prior authorization forms on medical provider portals
- Download hundreds of PDFs from grocer portals across the US
- Automate and scrape structured data from traditional ERPs like NetSuite
- Submit bids/shipments on logistics/TMS portals
- Scrape lawyer/doctor license information across public government portals
- And more!
We’re excited to see more use cases as we open up the platform – this is our first time doing self-serve.
Wanted to end with a quick thank you to HN. The feedback on our first Show HN gave us confidence to steer our product in this direction, and has deeply shaped the last year of our lives. We’d love feedback, especially from anyone who’s tried solving this problem or built similar tools.
Happy to answer questions and looking forward to your comments!
Simplex, a browser automation platform for developers, launches on HN, sparking discussion around its pricing, features, and potential applications, as well as comparisons to existing solutions.
Snapshot generated from the HN discussion
Discussion Activity
Very active discussionFirst comment
37m
Peak period
26
Day 1
Avg / period
9.3
Based on 28 loaded comments
Key moments
- 01Story posted
Oct 2, 2025 at 12:07 PM EDT
about 2 months ago
Step 01 - 02First comment
Oct 2, 2025 at 12:44 PM EDT
37m after posting
Step 02 - 03Peak activity
26 comments in Day 1
Hottest window of the conversation
Step 03 - 04Latest activity
Oct 5, 2025 at 10:50 PM EDT
about 2 months ago
Step 04
Generating AI Summary...
Analyzing up to 500 comments to identify key contributors and discussion patterns
To be transparent, we're an early startup, and a big part of that is user validation. We've been lucky to have companies as small as 5 people sign onto our $2500/month plan -- it shows some commitment on their side and helps us understand whether it's a real problem for our users. That's the same reason the $2500/month plan isn't self serve (you have to talk to us first).
We're definitely thinking of adding a pay as you go plan! But we aren't there yet re: our understanding of the market, if that makes sense.
If you want to set up monthly billing in Coupa, you just manually create 12 invoices and schedule them out. Each time you have to retype all the account information from scratch, and there are a few landmine buttons on the page that will clear all the forms and make you start from scratch. I can't imagine the thousands of human hours lost every year to just filling out fields in Coupa.
Re: Puppeteer automation as part of the script -- we have a feature we wrote for one of our customers that we didn't promote to production where you can define a deterministic action in the dashboard that allows you to paste in JavaScript, but we're likely not to push that to prod anytime soon. Could you explain your reasoning for wanting to use Puppeteer still? We've generally seen customers fully switch over to Simplex instead of relying on their original Puppeteer/Playwright scripts -- since we have action caching, the underlying script (click on div locator with this div id, etc.) is pretty similar to what you'd get using Playwright.
As someone who has spent a LOT of my time in my career working on browser automation and testing, speed and cost was always key. Even with existing programmatic tools like selenium, playwright, cypress, etc speed and headfull hosting costs were already big issues. This seems orders of magnitude slower and more expensive. Curious how you pitch this to potential customers.
Edit: I just re-ran the demo and it seemed way faster this time??? the first time it said GOAL: PRESS_ENTER... (agent proceeds to think about it for 5-8 seconds) which seemed hilarious to me.
We also have an example of a complex, multi-agent workflow here that might be useful for you to look at: https://www.simplex.sh/blog/context-engineering-for-web-agen...
I suppose if you are hitting your target demographic dead-on with your marketing efforts, the value prop should be completely obvious to them, but still could be more explicit in your differentiation.
It really sucks to block an entire service, just because a few of its users can't control themselves. At the same time a lot of SaaS providers makes it impossible to report a single user/tenant and getting a paying user banned just isn't happening.
We gate full access to the platform partially for this reason. We debated giving fewer than 50 free browser sessions, for example, and have already banned a few accounts from our self-serve today that were unidentifiable/"company accounts" without a legitimate web presence.
One think I might add: limit how many requests per second your clients can make. Even if they can just scrape a small set of sites, they can still hammer a site into the ground. One of the things I think Google has been doing really well since their start is knowing when to back of a site. So either rate-limit your clients, or back of a site if you see responses slowing down.
We just had a company hit one of our sites pretty heavily, and when asking them of back off a bit, they just asked if we could perhaps rate-limit them. Apparently they don't know how to reduce their traffic themselves.
Want the full context?
Jump to the original sources
Read the primary article or dive into the live Hacker News thread when you're ready.