You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<imgsrc="./assets/web-ui.png"alt="Browser Use Web UI"width="full"/>
2
2
3
-
## Background
3
+
<br/>
4
4
5
-
This project builds upon the foundation of the [browser-use](https://github.com/browser-use/browser-use), which is designed to make websites accessible for AI agents. We have enhanced the original capabilities by providing:
1.**A Brand New WebUI:** We offer a comprehensive web interface that supports a wide range of `browser-use` functionalities. This UI is designed to be user-friendly and enables easy interaction with the browser agent.
10
+
This project builds upon the foundation of the [browser-use](https://github.com/browser-use/browser-use), which is designed to make websites accessible for AI agents.
8
11
9
-
2.**Expanded LLM Support:** We've integrated support for various Large Language Models (LLMs), including: Gemini, OpenAI, Azure OpenAI, Anthropic, DeepSeek, Ollama etc. And we plan to add support for even more models in the future.
12
+
We would like to officially thank [WarmShao](https://github.com/warmshao) for his contribution to this project.
10
13
11
-
3.**Custom Browser Support:**You can use your own browser with our tool, eliminating the need to re-login to sites or deal with other authentication challenges. This feature also supports high-definition screen recording.
14
+
**WebUI:**is built on Gradio and supports a most of `browser-use` functionalities. This UI is designed to be user-friendly and enables easy interaction with the browser agent.
12
15
13
-
4.**Customized Agent:** We've implemented a custom agent that enhances `browser-use` with Optimized prompts.
16
+
**Expanded LLM Support:** We've integrated support for various Large Language Models (LLMs), including: Gemini, OpenAI, Azure OpenAI, Anthropic, DeepSeek, Ollama etc. And we plan to add support for even more models in the future.
14
17
15
-
<videosrc="https://github.com/user-attachments/assets/58c0f59e-02b4-4413-aba8-6184616bf181"controls="controls"width="500"height="300" >Your browser does not support playing this video!</video>
18
+
**Custom Browser Support:** You can use your own browser with our tool, eliminating the need to re-login to sites or deal with other authentication challenges. This feature also supports high-definition screen recording.
16
19
17
-
**Changelog**
18
-
-[x]**2025/01/06:** Thanks to @richard-devbot, a New and Well-Designed WebUI is released. [Video tutorial demo](https://github.com/warmshao/browser-use-webui/issues/1#issuecomment-2573393113).
20
+
<videosrc="https://github.com/user-attachments/assets/56bc7080-f2e3-4367-af22-6bf2245ff6cb"controls="controls" >Your browser does not support playing this video!</video>
19
21
22
+
## Installation Guide
20
23
21
-
## Environment Installation
24
+
Read the [quickstart guide](https://docs.browser-use.com/quickstart#prepare-the-environment) or follow the steps below to get started.
22
25
23
-
1.**Python Version:** Ensure you have Python 3.11 or higher installed.
24
-
2.**Install `browser-use`:**
25
-
```bash
26
-
pip install browser-use
27
-
```
28
-
3. **Install Playwright:**
29
-
```bash
30
-
playwright install
31
-
```
32
-
4. **Install Dependencies:**
33
-
```bash
34
-
pip install -r requirements.txt
35
-
```
36
-
5. **Configure Environment Variables:**
37
-
- Copy `.env.example` to `.env` and set your environment variables, including API keys for the LLM.
38
-
- **If using your own browser:**
39
-
- Set `CHROME_PATH` to the executable path of your browser (e.g., `C:\Program Files\Google\Chrome\Application\chrome.exe` on Windows).
40
-
- Set `CHROME_USER_DATA` to the user data directory of your browser (e.g.,`C:\Users\<YourUsername>\AppData\Local\Google\Chrome\User Data`).
26
+
> Python 3.11 or higher is required.
27
+
28
+
First, we recommend using [uv](https://docs.astral.sh/uv/) to setup the Python environment.
29
+
30
+
```bash
31
+
uv venv --python 3.11
32
+
```
33
+
34
+
and activate it with:
35
+
36
+
```bash
37
+
source .venv/bin/activate
38
+
```
39
+
40
+
Install the dependencies:
41
+
42
+
```bash
43
+
uv pip install -r requirements.txt
44
+
```
45
+
46
+
Then install playwright:
47
+
48
+
```bash
49
+
playwright install
50
+
```
41
51
42
52
## Usage
43
53
@@ -50,3 +60,35 @@ This project builds upon the foundation of the [browser-use](https://github.com/
50
60
- Close all chrome windows
51
61
- Open the WebUI in a non-Chrome browser, such as Firefox or Edge. This is important because the persistent browser context will use the Chrome data when running the agent.
52
62
- Check the "Use Own Browser" option within the Browser Settings.
63
+
64
+
## (Optional) Configure Environment Variables
65
+
66
+
Copy `.env.example` to `.env` and set your environment variables, including API keys for the LLM. With
67
+
68
+
```bash
69
+
cp .env.example .env
70
+
```
71
+
72
+
**If using your own browser:** - Set `CHROME_PATH` to the executable path of your browser and `CHROME_USER_DATA` to the user data directory of your browser.
73
+
74
+
You can just copy examples down below to your `.env` file.
- [x] **2025/01/06:** Thanks to @richard-devbot, a New and Well-Designed WebUI is released. [Video tutorial demo](https://github.com/warmshao/browser-use-webui/issues/1#issuecomment-2573393113).
0 commit comments