page-agent 1.2.0 β†’ 1.3.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (3) hide show
  1. package/README.md +24 -27
  2. package/dist/iife/page-agent.demo.js +33 -33
  3. package/package.json +5 -5
package/README.md CHANGED
@@ -1,4 +1,4 @@
1
- # PageAgent πŸ€–πŸͺ„
1
+ # Page Agent
2
2
 
3
3
  <picture>
4
4
  <source media="(prefers-color-scheme: dark)" srcset="https://img.alicdn.com/imgextra/i4/O1CN01qKig1P1FnhpFKNdi6_!!6000000000532-2-tps-1280-256.png">
@@ -19,18 +19,16 @@ The GUI Agent Living in Your Webpage. Control web interfaces with natural langua
19
19
 
20
20
  ## ✨ Features
21
21
 
22
- - **🎯 Easy Integration**
23
- - No python. No headless browser. No browser extension. Just in-page scripts.
24
- - **πŸ” Client-Side Processing**
25
- - **🧠 DOM Extraction**
26
- - **πŸ’¬ Natural Language Interface**
27
- - **🎨 UI with Human in the loop**
28
-
29
- And πŸ˜‰
30
-
31
- - **πŸ§ͺ `cross-page` control with an experimental chrome extension** - `packages/extension`
32
-
33
- πŸ‘‰ [**πŸ—ΊοΈ Roadmap**](https://github.com/alibaba/page-agent/issues/96)
22
+ - **🎯 Easy integration**
23
+ - No need for `browser extension` / `python` / `headless browser`.
24
+ - Just in-page javascript. Everything happens in your web page.
25
+ - The best tool for your agent to control web pages.
26
+ - **πŸ“– Text-based DOM manipulation**
27
+ - No screenshots. No OCR or multi-modal LLMs needed.
28
+ - No special permissions required.
29
+ - **🧠 Bring your own LLMs**
30
+ - **🎨 Pretty UI with human-in-the-loop**
31
+ - **πŸ™ Optional [chrome extension](https://alibaba.github.io/page-agent/#/docs/features/chrome-extension) for multi-page tasks.**
34
32
 
35
33
  ## πŸš€ Quick Start
36
34
 
@@ -39,19 +37,15 @@ And πŸ˜‰
39
37
  Fastest way to try PageAgent with our free Demo LLM:
40
38
 
41
39
  ```html
42
- <script
43
- src="https://cdn.jsdelivr.net/npm/page-agent@1.2.0/dist/iife/page-agent.demo.js"
44
- crossorigin="true"
45
- ></script>
40
+ <script src="{URL}" crossorigin="true"></script>
46
41
  ```
47
42
 
48
- > - **⚠️ For technical evaluation only.** Demo LLM has rate limits and usage restrictions. May change without notice.
49
- > - **🌷 Bring your own LLM API.**
50
-
51
43
  | Mirrors | URL |
52
44
  | ------- | ---------------------------------------------------------------------------------- |
53
- | Global | https://cdn.jsdelivr.net/npm/page-agent@1.2.0/dist/iife/page-agent.demo.js |
54
- | China | https://registry.npmmirror.com/page-agent/1.2.0/files/dist/iife/page-agent.demo.js |
45
+ | Global | https://cdn.jsdelivr.net/npm/page-agent@1.3.0/dist/iife/page-agent.demo.js |
46
+ | China | https://registry.npmmirror.com/page-agent/1.3.0/files/dist/iife/page-agent.demo.js |
47
+
48
+ > **⚠️ For technical evaluation only.** Demo LLM has rate limits and usage restrictions. Slow. May change without notice.
55
49
 
56
50
  ### NPM Installation
57
51
 
@@ -72,18 +66,21 @@ const agent = new PageAgent({
72
66
  await agent.execute('Click the login button')
73
67
  ```
74
68
 
69
+ For more programmatic usage, see [πŸ“– Documentations](https://alibaba.github.io/page-agent/#/docs/introduction/overview).
70
+
75
71
  ## πŸ—οΈ Structure
76
72
 
77
73
  PageAgent adopts a simplified monorepo structure:
78
74
 
79
75
  ```
80
76
  packages/
81
- β”œβ”€β”€ core/ # ** Core agent logic without UI(npm: @page-agent/core) **
82
- β”œβ”€β”€ page-agent/ # Exported agent and demo(npm: page-agent)
77
+ β”œβ”€β”€ core/ # ** Core agent logic (npm: @page-agent/core) **
83
78
  β”œβ”€β”€ llms/ # LLM client (npm: @page-agent/llms)
84
- β”œβ”€β”€ page-controller/ # DOM operations & Visual Mask (npm: @page-agent/page-controller)
85
- β”œβ”€β”€ ui/ # Panel & i18n (npm: @page-agent/ui)
86
- └── website/ # Demo & Documentation site
79
+ β”œβ”€β”€ page-controller/ # DOM operations (npm: @page-agent/page-controller)
80
+ β”œβ”€β”€ ui/ # Panel UI (npm: @page-agent/ui)
81
+ β”œβ”€β”€ page-agent/ # Entry class and iife builds(npm: page-agent)
82
+ β”œβ”€β”€ extension/ # Chrome extension for multi-page tasks
83
+ └── website/ # Website & Documentation site
87
84
  ```
88
85
 
89
86
  ## 🀝 Contributing