---
title: "Another Rust Tool: OpenCode Browse 0.1.0 Is Out"
description: "OpenCode Browse 0.1.0 replaces Node.js and Playwright with a single Rust binary—25x less idle memory and 23x smaller. Built on the same local relay + extension pattern as Kimi WebBridge, here is what changed and four things to watch out for."
url: https://codingpass.ai/blog/opencode-browse-0-1-0-rust-rewrite
language: en
updated: 2026-11-17
---
# Another Rust Tool: OpenCode Browse 0.1.0 Is Out

Swapping Node.js and Playwright for a multi-megabyte Rust binary drops idle relay memory from hundreds of megabytes to a few. Handing your real logged-in browser to an agent still comes with trade-offs worth examining.

[CodingPass team](https://codingpass.ai/about) Published Nov 17, 2026 Updated Nov 17, 2026 5 min read

On November 17, the OpenCode team released [OpenCode Browse 0.1.0](https://x.com/opencode/status/2122377687968678258). The CLI, local relay, and MCP server have been rewritten in Rust, dropping both Node.js and Playwright.

The headline numbers are straightforward: 25x less memory, a 23x smaller footprint, and browser operations exposed directly to your agent.

![Screenshot of OpenCode's announcement post on X for OpenCode Browse 0.1.0, listing the Rust rewrite, 25x less memory, 23x smaller size, Playwright removal, and direct browser operations for agents](https://codingpass.ai/assets/img/blog/opencode-browse-0-1-0-rust-rewrite/opencode-browse-tweet.webp)

*The OpenCode Browse 0.1.0 release post. Image: [@opencode](https://x.com/opencode/status/2122377687968678258), November 17, 2026*

OpenCode Browse 0.1.0 replaces a heavy Node and Playwright runtime with a compact native Rust binary so coding agents can drive your actual browser. The relay itself now idles at a few megabytes, though Chrome still takes whatever RAM your tabs need—and giving an agent access to active logins means paying attention to permission boundaries.

## What Actually Changed in 0.1.0

Unlike headless-browser tools, [OpenCode Browse](https://opencode.ai/product/browse) pairs a local MCP server with a Chromium extension so agents work inside your everyday browser (Chrome, Edge, Brave, Arc, Helium, Vivaldi, Opera, or Chromium).

Agent tabs open in the background inside collapsed tab groups. When an agent hits a login screen, 2FA prompt, or payment flow, it hands the tab back to you and waits until you click **Continue**.

![OpenCode Browse architecture diagram showing the agent terminal calling browse on the left, the Rust relay in the middle, and the user's browser on the right](https://codingpass.ai/assets/img/blog/opencode-browse-0-1-0-rust-rewrite/browse-architecture.webp)

*The MCP server starts the local relay on demand (`127.0.0.1:19988`), and the extension executes commands over WebSocket via `chrome.debugger`. Image: [anomalyco/browse](https://github.com/anomalyco/browse)*

Based on the [v0.1.0 release notes](https://github.com/anomalyco/browse/releases/tag/v0.1.0), four architectural shifts define this release:

| Area | Before 0.1.0 | In 0.1.0 |
| --- | --- | --- |
| Runtime & Dependencies | Node.js + Playwright; relay idled at hundreds of MB | Single native Rust binary of a few MB; idles at a few MB |
| Primary Handle | Session-based workflow | Sessions removed; tab IDs (`tab`) are the handle |
| OpenCode Tooling | Wrapped inside script execution | Direct plain tools (`navigate`, `snapshot`, `click`, `fill`, etc.) |
| Process Model | One instance per project directory | One shared `browse` relay across all OpenCode projects |

Setup is a single command that installs the binary, configures your MCP clients, and walks you through pairing the extension:

```
curl -fsSL https://opencode.ai/browse/install | bash
```

Despite the name, `browse install` ships built-in config support for over 30 MCP clients, including Claude Code, Codex, Cursor, Windsurf, Cline, Zed, and Gemini CLI.

Architecturally, it follows the same playbook as Kimi WebBridge (the Kimi Browser Extension): a local relay paired with a Chromium extension driving `chrome.debugger` over MCP, so agents reuse your logged-in browser instead of spinning up a headless instance. OpenCode Browse 0.1.0 packages the relay and MCP server into a single Rust binary with embedded QuickJS, adds collapsed tab groups, Handoffs, and `allowedOrigins` guardrails, and stays purely an agent backend without adding a browser sidebar.

## Four Takeaways From Reading the Release and Architecture

### 1. The relay saves 25x memory, and Chrome will gladly eat it back

Cutting the relay's idle footprint from hundreds of megabytes down to a few megabytes is a real win for startup speed and background overhead.

That said, we think it is easy to misread that number as low total RAM usage. Browse drives your real Chrome instance. Once an agent starts opening tabs, capturing full-page screenshots, recording tabs, and logging network traffic, Chrome's renderer processes still dominate your machine's memory. What Rust buys you is zero Node/Playwright bloat in the middle layer.

### 2. If Playwright is gone, why do the docs still mention Playwright

A common point of confusion is seeing "removed dependency on playwright" in the announcement while the README still refers to a Playwright-style `page` API.

Both statements are accurate at different layers. Under the hood, Playwright and Node.js are completely gone—the Rust relay speaks the Chrome DevTools Protocol (CDP) directly to the extension. At the tool layer, non-OpenCode clients (such as Claude Code, Codex, and Cursor) receive an `execute` tool backed by an embedded **QuickJS** engine inside the relay. That sandbox exposes a **Playwright-style** `page` API (`snapshot()`, `ref()`, `handoff()`) so models already fluent in Playwright idioms work without relearning a new syntax. OpenCode itself uses Code Mode, so it gets plain browser tools directly.

### 3. Handing an agent your logged-in browser cuts both ways

The biggest frustration with headless browser automation is hitting login walls, CAPTCHAs, and bot checks—leaving you to manually take screenshots and paste them back into your agent chat. Using your real browser with existing sessions eliminates that friction.

At the same time, web pages and emails are untrusted input. When an agent operates inside a browser where you are signed into GitHub, cloud consoles, and work email, prompt injection hidden on a page could translate into real clicks.

In its [security model](https://github.com/anomalyco/browse#security), 0.1.0 puts solid guardrails in place:

- **Local authentication**: The relay binds to `127.0.0.1` only, checks a local token on every call, pairs via one-time codes with ECDH key exchange, and accepts only official extension IDs.
- **CDP guardrails**: Agents are blocked from clearing cookies or site data, closing the browser, changing site permissions, or opening `chrome://` and `file://` URLs. Cookie and storage access is scoped to the tab's own host.
- **Human-only handoffs**: Only a real click on the extension card or toolbar button finishes a handoff, preventing page scripts from faking confirmation.

Even so, we would keep two caveats in mind: `allowedOrigins` and `readOnly` tab flags are opt-in, and the docs explicitly note that the QuickJS `execute` runtime is "sandboxed, not a boundary" ("Treat code an agent runs as code running as you"). For open-ended tasks, pass `allowedOrigins` or run Browse in a separate Chrome profile rather than your primary profile holding banking and production admin sessions.

### 4. Human-like input pacing and watching for lookalike extensions

Browse enables human-like input by default—curved mouse paths, paced typing, and gliding scrolls—to stay quiet against bot detection. That makes page interactions feel slightly slower than raw headless scripts. If you are testing local apps where stealth does not matter, set `OPENCODE_BROWSER_HUMAN_INPUT=0` for full speed.

Two final notes: only Chromium-based browsers are supported today (no Firefox support yet), and spam lookalike extensions have already started appearing in the Chrome Web Store. Always install the extension via the **Add to Chrome** link on [opencode.ai/product/browse](https://opencode.ai/product/browse) or from the [GitHub repository](https://github.com/anomalyco/browse).

Written by CodingPass team

We run CodingPass and test each guide against the latest stable release of the tool before we publish it. Spotted something out of date? Write to [support@codingpass.ai](mailto:support@codingpass.ai).

## Related reading.

Guide

### [OpenCode Setup Guide](https://codingpass.ai/tools/opencode)

Provider configuration in opencode.json, model IDs by tier, and troubleshooting common errors.

Guide

### [OpenCode 2 Works Great, Until Claude Returns 400](https://codingpass.ai/blog/opencode-claude-third-party-400)

What changed in OpenCode 2.0 and how third-party clients trigger the extra usage 400 error.

Models

### [All Models](https://codingpass.ai/models)

Every model ID, required plan tier, and monthly allowance.
