---
title: 'OpenCode Browse Just Got 25X LIGHTER?!'
source: 'https://youtube.com/watch?v=WOVWsnyoqhY'
video_id: 'WOVWsnyoqhY'
date: 2026-11-21
duration_sec: 489
channel: 'Julian Goldie SEO'
---

# OpenCode Browse Just Got 25X LIGHTER?!

> Source: [OpenCode Browse Just Got 25X LIGHTER?!](https://youtube.com/watch?v=WOVWsnyoqhY)

## Summary

OpenCode Browse 0.1.0 is a major update to the tool that lets AI coding agents control your real browser. The entire project was rewritten in Rust, resulting in a 25x reduction in memory usage and a 23x reduction in program size. This video breaks down what changed, how it works, and demonstrates a real-world test of the tool.

### Key Points

- **The Problem: Memory Usage** [00:03] — OpenCode noticed that their AI browser tool was quietly consuming significant memory, prompting a complete rewrite.
- **What is OpenCode Browse?** [00:15] — It's a tool that lets your AI coding agent use your real browser, including your tabs, logins, and extensions. It consists of an MCP server and a browser extension.
- **MCP Explained** [00:45] — MCP (Model Context Protocol) is a standard way for AI agents to find and use tools. This allows the agent to open tabs, click, read pages, and take screenshots.
- **The Big News: Rust Rewrite** [01:11] — OpenCode released Browse 0.1.0, rewritten in Rust. This brings three headline changes: 25x less memory, 23x smaller size, and no more Playwright dependency with browser actions exposed directly to the agent.
- **Clarifying the Numbers** [01:42] — 25x refers to memory (RAM) usage, while 23x refers to the program's size on disk. The new Rust program is about 4.3 MB, compared to the old Node version's 53-64 MB. Memory per connection dropped from ~190 MB to 5.6 MB, a ~97% reduction.
- **Why It Matters** [02:11] — With the old version, keeping Browse running all day would consume nearly 200 MB. Now it's under 6 MB, making it barely noticeable.
- **How They Did It** [02:26] — The old version ran on Node and used Playwright, which is powerful but heavy. Developer Dax Rod rebuilt it in Rust, replacing only the parts they needed, resulting in a faster and lighter program.
- **Browser Actions as Tools** [03:19] — Browser actions are now exposed directly to the agent as tools, allowing it to mix browser actions with other MCP tools in a single flow. For example, opening a page, grabbing a list, looping over it, and calling another MCP tool for each item.
- **Difference from Normal Browser Automation** [03:48] — Typical Playwright setups launch a separate browser with a fresh profile, lacking logins. Browse uses your existing browser, so it can access logged-in pages without extra setup. It also runs in the background in collapsed tab groups and hands control back to you for logins or 2FA.
- **Real-World Test** [04:43] — The presenter tested Browse by asking the agent to act as a community growth assistant for the AI Profit Boardroom. The agent successfully browsed public pages and created a growth plan, including value proposition, audience groups, onboarding path, tutorials, and community themes. It also flagged outdated blog pages.
- **Other Use Cases** [05:23] — For coding, the agent can build a page, open it in the real browser, and take a screenshot to check it. For testing, it can click through flows on sites you're already logged into.
- **Honest Limitations** [05:50] — Version 0.1.0 is early and will change. Using your real browser means real accounts are exposed, so be aware of prompt injection risks. Use the allow list and consider a separate browser profile. Some websites may block automated browsing.
- **Getting Started** [06:19] — Go to opencodellc.ai and find the browse page. Install the browser extension first, or use one-line installs for Mac/Linux, Windows PowerShell, npm, and Bun. The code is open source on GitHub under anomalico/browse.
- **Final Takeaway** [06:47] — Browser tools for AI agents used to be heavy, but now this one is a few megabytes and works inside your real browser. There's a window of opportunity for business owners to learn these tools early.

### Conclusion

OpenCode Browse 0.1.0 represents a significant leap forward in AI browser automation, making it lighter, faster, and more integrated with your real browser. While it's early-stage and has some limitations, its performance and capabilities make it a valuable tool for developers and businesses looking to leverage AI agents.

## Transcript

lighter. What's quietly eating your memory every time your AI agent opens a browser? Most people never check. OpenCode just did, and they didn't like what they found. So they tore it down and rebuilt
it from scratch. Today I'm breaking down OpenCode Browse 0.1.0. What it is, what changed, and why it matters. And later, I'll show you what happened when I pointed it at a real website and handed it a big research
job. So what is OpenCode Browse? It lets your AI coding agent use your real browser, your actual browser with your tabs, your logins, and your extensions. It has two parts, an MCP server and a browser
extension. MCP stands for model context protocol. It's a standard way for AI agents to find and use tools. Together, these two parts let your agent open tabs, click around, read pages, and take
screenshots. It works with Chrome, Edge, Brave, Arc, Helium, Vivaldi, Opera, and Chromium. And it's not just for OpenCode. It works with any MCP client, including Claude
Code, Cursor, Codex, and Zed. Now here's the big news. OpenCode just released Browse 0.1.0, and they rewrote the whole thing in and they rewrote the whole thing in Rust. Three headline changes, 25 times
less memory, 23 times smaller, and no more playwright with browser actions exposed directly to your agent. People mix up those first two numbers, so let's be clear. 25x is memory. That's how much RAM it uses while it runs. 23x is size.
That's how big the program is on your computer. The new stack put real numbers on it. The new Rust program is about 4.3 megabytes. The old Node version was around 53 to 64 megabytes. And memory
for each Browse connection dropped from roughly 190 megabytes to 5.6 megabytes after a few calls. That's a drop of around 97%. Your agent might keep Browse running in the background all day. At almost 200
megabytes, you feel it. At under six, you barely notice it. So you can just So how did they do it? The old version ran on Node and leaned on Playwright. Playwright is a popular tool for controlling browsers with code.
It's powerful, but it's big and it brings a lot your agent never uses. So Dax Rod, a developer on Open Code, rebuilt it in Rust and replaced only the parts they actually needed. Rust is a programming language known for being
programming language known for being fast and light on memory. The result is Okay, quick pause before I show you the next part. If you want to learn tools like this step by step, check out the AI Profit Boardroom. We've got a 30-day
roadmap that walks you through getting set up with AI tools like this one, one step at a time. There are four coaching calls every week. So if you get stuck setting up something like Browse, you can bring it to a call and work through
it. You also get the videos, the prompts, and the files to copy so you're never starting from a blank page. Link in the description or go to ai profit boardroom.com. Right, the part I find most interesting
is that browser actions are now exposed directly to your agent as tools. Dax explained what that unlocks. All the browser tools are now available in code mode. So your agent can mix browser actions with your other MCP
tools in one go. His example was this. Open a page, grab a list of things, loop over them, and call another MCP tool for each one. One flow instead of a long chain of back and forth steps. So how is this different from normal
browser automation? A typical Playwright setup often launches a separate browser with a fresh profile. No logins. So when it hits a page that needs you signed in, it's stuck. Browse uses the browser you already have. If you're signed into a
extra setup. It's also built to stay out of your way. Agent tabs open in the background inside collapsed tab groups so you keep working. When the agent hits a login or a two-factor code, it hands the tab back
to you. You do that step, click continue, and the agent picks up where it left off. And if you already have a tab open, you can click a button in your toolbar and hand it to your agent. It can also take screenshots, record the
screen, and capture network traffic as a HAR file. That's a log of everything a page loaded, which is really handy when something breaks. And you can set an allow list so a session can only touch the sites you choose. Now let me show
you what happened when I tested it. I gave my agent a prompt to act as a community growth assistant for the AI Profit boardroom. Browse our public pages and build a growth plan without inventing anything it couldn't verify.
growth blueprint with our value proposition, the six audience groups from our 42 niche playbook page, a seven-day onboarding path, five starter tutorials, and seven daily community themes. It even flagged older blog pages
that no longer matched the homepage and noted that it never opened the private member area. So what else can you use this for? For coding, your agent can build a page, open it in your real browser, and take a
screenshot to check it. If something fails, it can check the network log to see why. For testing, it can click through a flow on a site you're already logged into, like your own dashboard. So how does it stack up against other AI
browser tools? Some of them run in their own separate browser. That's safer for some jobs, but you lose your logins. Browse works inside your own browser, and because it's an MCP server, it isn't locked to one app. Now some honest
limitations. First, this is version 0.1.0. It's early, so expect changes. Second, it uses your real browser, which means your real accounts. A web page can hide text that tries to trick your
agent. That's called prompt injection. So use the allow list and think about a separate browser profile with only the accounts that task needs. Third, some websites are good at spotting automated browsing, so some sites may still block
it. So how do you get started? Go to opencodellc.ai and find the browse page. The easiest route is to install the browser extension first. It walks you through the rest. If you like the command line,
the page also has one line installs for Mac and Linux, Windows PowerShell, npm, and Bun. And the code is open source on GitHub under anomalico/browse. Once it's set up, start small. Give your agent one simple job on a page you're
already logged into. Then build from there. Here's the takeaway. Browser tools for AI agents used to be heavy. Now this one is a few megabytes and works inside your real browser. Here's the thing. There's a window right now
where most business owners haven't figured this out yet, and that window won't stay open forever. Learning these tools early gives you a real head start. If you want to get ahead, join the AI Profit Boardroom. You get daily
tutorials so you keep learning new AI tools as they come out. You get four coaching calls every week where you can bring your questions and get unstuck. There's a prompt library so you're not writing every prompt from scratch, and
find other members in the community. Link in the description or go to aiprofitboardroom.com. If you want the full process, the SOPs, and over 100 AI use cases like this one, join the AI Success Lab. It's our free
community. Links in the comments and description. You'll get all the video notes from this episode plus access to 95,300 members. The notes cover everything from today, from what changed in browse 0.1.0
to how to set it up, so you don't need to pause and write anything down. Just come in, grab the notes, and learn alongside everyone else. If this video helped, go join the AI Success Lab now. I'll see you inside.
