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
docs: add missing links and fix consistency in Linux Desktop docs
- Link unexplained terms (XFCE, VNC, Next.js App Router, OpenAI Computer Use API, scrot)
- Remove unnecessary CodeGroup wrapper from project structure
- Add missing xorg package to Python template to match TypeScript version
Copy file name to clipboardExpand all lines: docs/template/examples/desktop.mdx
+2-1Lines changed: 2 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,7 +9,7 @@ The template includes:
9
9
-**Ubuntu 22.04** with XFCE desktop environment
10
10
-**VNC streaming** via [noVNC](https://novnc.com/) for browser-based access
11
11
-**Pre-installed applications**: LibreOffice, text editors, file manager, and common utilities
12
-
-**Automation tools**: [xdotool](https://github.com/jordansissel/xdotool) and scrot for programmatic desktop control
12
+
-**Automation tools**: [xdotool](https://github.com/jordansissel/xdotool) and [scrot](https://github.com/resurrecting-open-source-projects/scrot) for programmatic desktop control
Copy file name to clipboardExpand all lines: docs/use-cases/linux-desktop.mdx
+4-6Lines changed: 4 additions & 6 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -33,10 +33,9 @@ Full source code is available in the [E2B Surf repository](https://github.com/e2
33
33
34
34
## Project Structure
35
35
36
-
This starter project follows a standard Next.js App Router structure with additional directories for AI services, utilities, and type definitions. The separation keeps concerns modular and makes the codebase easy to navigate.
36
+
This starter project follows a standard [Next.js App Router](https://nextjs.org/docs/app) structure with additional directories for AI services, utilities, and type definitions. The separation keeps concerns modular and makes the codebase easy to navigate.
37
37
38
-
<CodeGroup>
39
-
```typescript JavaScript & TypeScript
38
+
```text Project Structure
40
39
surf-starter/
41
40
├── app/
42
41
│ ├── api/chat/
@@ -63,7 +62,6 @@ surf-starter/
63
62
├── package.json // Dependencies
64
63
└── tsconfig.json // TypeScript configuration
65
64
```
66
-
</CodeGroup>
67
65
68
66
---
69
67
@@ -72,9 +70,9 @@ surf-starter/
72
70
This application creates an autonomous AI loop that enables natural language control of a virtual Linux desktop:
73
71
74
72
1.**User Input** - You send a natural language command like "Open Firefox and search for AI news"
75
-
2.**Sandbox Creation** - E2B spins up an Ubuntu 22.04 desktop environment (if not already running)
73
+
2.**Sandbox Creation** - E2B spins up an Ubuntu 22.04 desktop with [XFCE](https://xfce.org/) and [VNC](https://en.wikipedia.org/wiki/Virtual_Network_Computing) streaming for remote viewing (if not already running)
76
74
3.**Visual Analysis** - The AI receives a screenshot of the current desktop state
77
-
4.**Action Planning** - OpenAI Computer Use API analyzes the screenshot and decides what action to take
75
+
4.**Action Planning** - [OpenAI Computer Use API](https://platform.openai.com/docs/guides/computer-use) analyzes the screenshot and decides what action to take
78
76
5.**Action Execution** - The action (click, type, scroll, etc.) is executed on the desktop via E2B SDK
79
77
6.**Feedback Loop** - A new screenshot is taken and sent back to the AI
80
78
7.**Iteration** - The loop continues until the task is complete (maximum 15 iterations)
0 commit comments