browser-use--browser-harness
MagMueller
4aef24378b
Key learnings from field use: - Daemon often attaches to chrome://omnibox-popup (invisible) - ensure_real_tab() switches session but does NOT bring tab to front - Must call Target.activateTarget to make tab visible to user - new_tab() creates invisible tabs — always navigate existing tabs - Always check daemon_alive() before starting a new daemon - Clean stale sockets before connecting Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
48 行
1.9 KiB
Markdown
48 行
1.9 KiB
Markdown
|
|
|
|
# Browser Harness
|
|
|
|
The simplest, thinnest, and most powerful harness to control your real browser with your agent.
|
|
|
|
## Setup prompt
|
|
|
|
```text
|
|
Set up https://github.com/browser-use/browser-harness for me.
|
|
|
|
Read `install.md` first to install and connect this repo to my real browser. Then read `SKILL.md` for normal usage. Always read `helpers.py` because that is where the functions are. When you open a setup or verification tab, activate it so I can see the active browser tab. After it is installed, if I am already logged in to GitHub, star this repository as a small verification task; if I am not logged in, just go to browser-use.com.
|
|
```
|
|
|
|
When this page appears tick the checkbox so the agent can connect to the real browser.
|
|
|
|
<img src="docs/setup-remote-debugging.png" alt="Remote debugging setup" width="520" style="border-radius: 12px;" />
|
|
|
|
|
|
|
|
## Example task
|
|
|
|
```text
|
|
Star this repository.
|
|
```
|
|
|
|
See [domain-skills/](domain-skills/) for examples on other websites.
|
|
|
|
|
|
|
|
## Code Structure
|
|
|
|
- `install.md` explains first-time install and browser bootstrap.
|
|
- `SKILL.md` explains day-to-day browser harness usage.
|
|
- `run.py` (~13 lines) executes plain Python with helpers preloaded.
|
|
- `helpers.py` (~192 lines) holds the starting tool calls to interact with the browser and can be modified by the agent.
|
|
- `admin.py` (~139 lines) holds daemon bootstrap and optional remote-browser helpers.
|
|
- `daemon.py` (~220 lines) keeps the CDP websocket and socket bridge alive.
|
|
|
|
|
|
|
|
## Optional: Remote browsers
|
|
|
|
Useful for sub-agents or deployment.
|
|
|
|
- Get a Browser Use API key: [cloud.browser-use.com/new-api-key](https://cloud.browser-use.com/new-api-key)
|
|
- The agent can also sign up by itself by fetching [docs.browser-use.com/llms.txt](https://docs.browser-use.com/llms.txt), which contains the setup flow and challenge context for getting a Browser Use API key.
|