←back to thread

Show HN: Nxtscape – an open-source agentic browser

(github.com)
314 points felarof | 1 comments | 20 Jun 25 16:35 UTC | HN request time: 0.211s | source

Hi HN - we're Nithin and Nikhil, twin brothers and founders of nxtscape.ai (YC S24). We're building Nxtscape ("next-scape") - an open-source, agentic browser for the AI era.

-- Why bother building a new browser? For the first time since Netscape was released in 1994, it feels like we can reimagine browsers from scratch for the age of AI agents. The web browser of tomorrow might not look like what we have today.

We saw how tools like Cursor gave developers a 10x productivity boost, yet the browser—where everyone else spends their entire workday—hasn't fundamentally changed.

And honestly, we feel like we're constantly fighting the browser we use every day. It's not one big thing, but a series of small, constant frustrations. I'll have 70+ tabs open from three different projects and completely lose my train of thought. And simple stuff like reordering tide pods from amazon or filling out forms shouldn't need our full attention anymore. AI can handle all of this, and that's exactly what we're building.

Here’s a demo of our early version https://dub.sh/nxtscape-demo

-- What makes us different We know others are exploring this space (Perplexity, Dia), but we want to build something open-source and community-driven. We're not a search or ads company, so we can focus on being privacy-first – Ollama integration, BYOK (Bring Your Own Keys), ad-blocker.

Btw we love what Brave started and stood for, but they've now spread themselves too thin across crypto, search, etc. We are laser-focused on one thing: making browsers work for YOU with AI. And unlike Arc (which we loved too but got abandoned), we're 100% open source. Fork us if you don't like our direction.

-- Our journey hacking a new browser To build this, we had to fork Chromium. Honestly, it feels like the only viable path today—we've seen others like Brave (started with electron) and Microsoft Edge learn this the hard way.

We also started with why not just build an extension. But realized we needed more control. Similar to the reason why Cursor forked VSCode. For example, Chrome has this thing called the Accessibility Tree - basically a cleaner, semantic version of the DOM that screen readers use. Perfect for AI agents to understand pages, but you can't use it through extension APIs.

That said, working with the 15M-line C++ chromium codebase has been an adventure. We've both worked on infra at Google and Meta, but Chromium is a different beast. Tools like Cursor's indexing completely break at this scale, so we've had to get really good with grep and vim. And the build times are brutal—even with our maxed-out M4 Max MacBook, a full build takes about 3 hours.

Full disclosure: we are still very early, but we have a working prototype on GitHub. It includes an early version of a "local Manus" style agent that can automate simple web tasks, plus an AI sidebar for questions, and other productivity features (grouping tabs, saving/resuming sessions, etc.).

Looking forward to any and all comments!

You can download the browser from our github page: https://github.com/nxtscape/nxtscape

1. joshstrange ◴[21 Jun 25 15:55 UTC] No.44338489[source]▶
I got a chance to play with this a bit and while I see the promise it's still a far way off.

I asked it to find the best price for a new Seagate Exos 24TB drive on Amazon (GPT-4o):

> The best price found for a new Seagate EXOS 24TB enterprise hard drive on Amazon is $274.99 (model ST24000NM000C). This is a renewed/refurbished unit with 4.1/5 stars from 39 reviews. Note: The search results show mostly renewed units, and new units may be available at different prices on individual product pages.

Ok, fair, you couldn't find a new one on Amazon. I would have prefered a "Couldn't find one" instead of leading with the price and only in the second sentence mentioning it's a refurb. Note, this is mostly an LLM failing, not Nxtscape, that part seemed to work well overall.

I then followed up with "I only want a new drive, please look at other popular electronic retailers". It replied with (formatted slightly):

> Best Buy - WD Blue 2TB Internal Hard Drive ($59.99, on sale from $70)

> Newegg - Desktop Internal Hard Drives (500GB up to 8TB available) - Price range: $180-$299 - 4.5 store rating - Features: 30-day returns, 5-9 day delivery

> Amazon - Seagate EXOS Enterprise Hard Drives (up to 24TB)

> Additional options include SSDs from Newegg ($60-$201) if you're interested in faster storage solutions.

As almost always with LLMs, I see where it went off the beaten path. I didn't specify "a new one with the same specs I originally asked for", I shouldn't have to. This is probably mostly on the LLM, I don't know if Nxtscape could improve that with prompting (I don't know exactly what they are sending to judge either way). Also it got lazy with the Amazon response (no price).

One way that Nxtscape might be able to improve is to parse out what the user is asking for, creating a data structure to define a "result" (in my case: url, name, price, description?), use that to prompt the LLM to conform to that shape, then take the results and pass them all through a one-off LLM instance to summarize the data. I think that would help with the inconsistencies in the results. Then again, that's very "Data extraction"/"data lookup"-focused and I haven't even played with using it for input: Fill out this form, loop this process for input (mail merge), etc.

Really cool idea and I'll try throwing some other problems at it as I think of them, but mostly for fun/research, this doesn't seem like force-multiplier for my normal workflows (yet).