BrowserOS neo
The Missing Browser for Claude, Cowork & Codex
490 followers
The Missing Browser for Claude, Cowork & Codex
490 followers
BrowserOS neo is a web browser built NOT for you but for your AI agents. It runs on your machine and connects to Claude Code, Cowork, and Codex finishes real tasks on your behalf. It's magical!
Free
Launch Team
EneyProactive AI for Mac. Free test, 20,000 credits.
Promoted
Hi Product Hunt! 👋 Nikhil here, co-founder of BrowserOS. Fun fact: I’m building this product with my twin brother Nithin (@nithin_sonti)
Today we're launching BrowserOS neo: a browser built NOT for you, but for YOUR AI.
Here's the problem we ourselves kept hitting: Claude Code and Codex got scary good at reasoning about work, but the moment a task touched the web, like checking a dashboard or filling out a form or booking your dentist appointment, they hit a wall.
We tried several solutions out there today and none of them were a good fit. Cloud browsers (like browser-use) run in a datacenter, so logging into your accounts is a pain, and sites like Twitter and LinkedIn block you because you are on a datacenter IP. And headless browsers (like agent-browser) don't let you see what your agent is doing.
We realized what’s needed is a browser that is run locally, has your logins but can be easily driven by YOUR agents.
That’s what we built with BrowserOS neo! You import your logins from Chrome in one click and connect your agent (Claude Code, Cowork, Codex, OpenClaw, etc). And then you can start giving your agent any complex task and see it get magically done using neo!
To be clear, BrowserOS neo is NOT a Chrome replacement. It's a secondary browser that sits next to Chrome, and we’ve made it agent friendly.
The features you get today are:
🔓 Free and open source. It’s available on macOS and Windows.
👀 Watch your agent live. There's a cockpit view on your new-tab page that shows every agent, every site, every step.
🪙 Less tokens. BrowserOS neo hands your agent simplified snapshots of the web page instead of screenshots, so you burn way less tokens than using Claude’s Chrome extension and other solutions.
⏪ Rewind anything. Every agent session gets saved as a scrubbable video, so you can find the mistake and coach the agent.
🗂️ Your tabs are sacred. Agents work in their own tabs and can't touch the doc you're writing :)
🤖 Parallel agents. You can run as many agents as you want at once, each in its own tabs.
🔒 Privacy first. Everything stays on your machine, and every action is logged to a local file on your disk.
We'd genuinely love your feedback more than anything else today: what's the first task you'd hand an agent? Reply and I'll tell you honestly whether BrowserOS neo can do it today.
We also open source and you can find our full source code here: github.com/browseros-ai/BrowserOS
We're in the comments all day.
PS: We are big fans of OpenClaw, we initially named the product as BrowserClaw but had to rename it to BrowserOS neo because of SEO issues.
@nikhilsv92 Hi product hunt! Nithin here, the other co-founder. Nikhil covered what neo is, so I'll tell you what I actually do with it.
For the last few months I've been giving agents a lot more access to my accounts than most people are comfortable with! Not a sandbox but my real browser, signed into my real email, GitHub, and calendar 🙂 I hand work to Claude Code and Codex the way I'd hand it to a person, and let them go while I do something else. Most of it is boring and it just works. Some of it still gets me: this launch you're reading right now, an agent drove my browser to research it, pulled up other launches to learn from, and left edits in our doc. I never opened those tabs myself.
The reason I'm willing to hand over that much is the part we spent the most time building. I can watch the many agents live through the cockpit dashboard, every session saves as a video I can scrub back through, and every action also gets recorded. Also, since Claude Opus 4.5, models have gotten quite smart and very good at computer use and claude code has largely been quite good at completing the task correctly.
Honest question, since I'm still finding the edges of this: how much access would you give an agent today, and what would have to be true before you did?
@nithin_sonti @nikhilsv92 Finally! Loving this! Been waiting for a proper browser built for agents for so long!
@daniel_chua1 thank you! We’ve been using it for everything from managing expenses to creating ads. Let us know what you find useful and any feedback you have.
@daniel_chua1 this has been my coolest usecase for me: neo reads the top Hacker News threads and highlights the genuinely insightful comments right on the page.
Importing the Chrome logins is the whole pitch and it's also the line I'd want a paragraph under. A local browser holding real sessions means a prompt injection on any page the agent wanders onto is an authenticated action rather than a failed one, which is a much worse blast radius than a datacenter browser with no cookies. Does neo stop before a state changing request on a logged in site, or is that left to whichever agent you plugged in?
@asadmalik901 Great question! Neo wraps all webpage content in explicit untrusted-content boundaries and instructs the agent to treat it as data, never as commands. We’ve tested this across Claude Code, Codex, and other frontier harnesses and haven’t seen a prompt-injection failure so far.
I am more than satisfied with the functionality of BrowserOS neo (I have been using it since it was BrowserClaw). The primary pain point it has resolved for my workflow has been the ability to log in to platforms when providing browser access to desktop/CLI agentic tools. It has been one of the best tools for AI that I have used interms of giving me that feeling of actually colaborating. There are only a handful of AI tools that I use on a daily basis as a non-developer/non-technical person, and BrowserOS and BrowserOS neo are definitely among them. Wonderful job!
@sura_tsegaye Thank you for the feedback, appreciate it! Let us know what more you’d like to see in BrowserOS neo.
Maker here 👋 neo started as a tool I built for myself, and it's now part of my daily workflow. Most days I've got a couple of agents running in neo doing the web busywork I used to do by hand: checking dashboards, pulling data out of apps I'm logged into, filling forms. The part I didn't expect to love is just watching them work in the live cockpit instead of trusting a headless black box. Ask me anything 🙏
Any plans for Linux app?
@harry_douglas Neo is coming to Linux soon!
(our full agentic browser, BrowserOS is already on Linux if you want to give it a shot)
I've been using BrowserOS since the beginning. It's been excellent and I can't wait to try this out as well. Get us a version for Ubuntu guys!!
Browser as a tool for your AI is one of those things where you can’t believe you lived without it before. This is literally a game changer my coding workflows where I need to drive a browser reliably.
@samuel_crombie yeah totally agree. giving agents eyes has been super handy for any work involving real world interactions!
Thank you for the support,@samuel_crombie !
Closing the coding QA loop with BrowserOS neo has been our favorite use case as well! Loop engineering FTW!