BrowserOS neo - The Missing Browser for Claude, Cowork & Codex
by•
BrowserOS neo is a web browser built NOT for you but for YOUR AI agents. It runs on your machine and uses your logins, so Claude Code, Cowork, and Codex can finish real tasks on your behalf. Run many agents at once. Replay any session to see what your agents did. Free and open source, 12,000+ GitHub stars.


Replies
BrowserOS neo
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.
BrowserOS neo
@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?