Skip to content

Commit

Permalink
docs: update comparing section (#308)
Browse files Browse the repository at this point in the history
  • Loading branch information
yuyutaotao authored Jan 22, 2025
1 parent 6c188d0 commit 35bf713
Show file tree
Hide file tree
Showing 4 changed files with 53 additions and 13 deletions.
22 changes: 16 additions & 6 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -32,11 +32,11 @@ Midscene.js is an AI-powered automation SDK with the abilities to control the pa
| Use JS code to drive task orchestration, collect information about Jay Chou's concert, and write it into Google Docs | <video src="https://github.com/user-attachments/assets/75474138-f51f-4c54-b3cf-46d61d059999" height="300" /> |


## New open-source model choice - UI-TARS 📢
## 📢 New open-source model choice - UI-TARS

From version v0.10.0, we support a new open-source model named [`UI-TARS`](https://github.com/bytedance/ui-tars). Read more about it in [Choose a model](https://midscenejs.com/choose-a-model).

## Features 💡
## 💡 Features

- **Natural Language Interaction 👆**: Describe the steps, and let Midscene plan and control the user interface for you
- **Understand UI, Answer in JSON 🔍**: Provide prompts regarding the desired data format, and then receive the expected response in JSON format.
Expand All @@ -45,13 +45,23 @@ From version v0.10.0, we support a new open-source model named [`UI-TARS`](https
- **Visualized Report for Debugging 🎞️**: With our visualized report file, you can easily understand and debug the whole process.
- **Totally Open Source! 🔥**: Experience a whole new world of automation development. Enjoy!

## Models ✨
## ✨ Model Choices

- You can use general-purpose LLMs like `gpt-4o`, it works well for most cases. And also, `gemini-1.5-pro`, `qwen-vl-max-latest` are supported.
- You can also use [`UI-TARS`](https://github.com/bytedance/ui-tars) model, which is an **open-source model** dedicated for UI automation. You can deploy it on your own server, and it will dramatically improve the performance and data privacy.
- Read more about [Choose a model](https://midscenejs.com/choose-a-model)

## Resources 📄
## 👀 Comparing to ...

There are so many UI automation tools out there, and each one seems to be all-powerful. What's special about Midscene.js?

* Debugging Experience: You will soon find that debugging and maintaining automation scripts is the real challenge point. No matter how magic the demo is, you still need to debug the process to make it stable over time. Midscene.js offers a visualized report file, a built-in playground, and a Chrome Extension to debug the entire process. This is what most developers really need. And we're continuing to work on improving the debugging experience.

* Open Source, Free, Deploy as you want: Midscene.js is an open-source project. It's decoupled from any cloud service and model provider, you can choose either public or private deployment. There is always a suitable plan for your business.

* Integrate with Javascript: You can always bet on Javascript 😎

## 📄 Resources

* [Home Page: https://midscenejs.com](https://midscenejs.com/)
* [Quick Experience By Chrome Extension](https://midscenejs.com/quick-experience.html), this is where you should get started
Expand All @@ -64,12 +74,12 @@ From version v0.10.0, we support a new open-source model named [`UI-TARS`](https
* [Choose a model](https://midscenejs.com/choose-a-model.html)
* [Config Model and Provider](https://midscenejs.com/model-provider.html)

## Community
## 🤝 Community

* [Discord](https://discord.gg/AFHJBdnn)
* [Follow us on X](https://x.com/midscene_ai)
* [Lark Group](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=291q2b25-e913-411a-8c51-191e59aab14d)

## License
## 📝 License

Midscene.js is [MIT licensed](https://github.com/web-infra-dev/midscene/blob/main/LICENSE).
22 changes: 16 additions & 6 deletions README.zh.md
Original file line number Diff line number Diff line change
Expand Up @@ -33,11 +33,11 @@ Midscene.js 是一个由 AI 驱动的自动化 SDK,能够使用自然语言对



## 支持了新的开源模型 - UI-TARS 📢
## 📢 支持了新的开源模型 - UI-TARS

从 v0.10.0 版本开始,我们支持了新的开源模型 [`UI-TARS`](https://github.com/bytedance/ui-tars)。更多信息请查看 [选择 AI 模型](https://midscenejs.com/zh/choose-a-model)

## 特性 💡
## 💡 特性

- **自然语言互动 👆**:只需描述你的步骤,Midscene 会为你规划和操作用户界面
- **理解UI、JSON格式回答 🔍**:你可以提出关于数据格式的要求,然后得到 JSON 格式的预期回应。
Expand All @@ -46,13 +46,23 @@ Midscene.js 是一个由 AI 驱动的自动化 SDK,能够使用自然语言对
- **用可视化报告来调试 🎞️**:通过我们的测试报告和 Playground,你可以轻松理解和调试整个过程。
- **完全开源 🔥**:体验全新的自动化开发体验,尽情享受吧!

## 模型
## ✨ 选择 AI 模型

- 你可以使用通用的 LLM 模型,如 `gpt-4o`,它适用于大多数情况。同时,`gemini-1.5-pro``qwen-vl-max-latest`(千问)也是支持的。
- 你也可以使用 [`UI-TARS` 模型](https://github.com/bytedance/ui-tars) ,这是一个专为 UI 自动化设计的大模型。你可以私有化部署,以提高性能和数据隐私。
- 更多信息请查看 [选择 AI 模型](https://midscenejs.com/zh/choose-a-model)

## 资源 📄
## 👀 与其他工具比较

业界的 UI 自动化工具层出不穷,每个 Demo 都看起来很科幻。Midscene.js 有什么特别之处?

* 调试体验:你很快就会发现,调试和维护自动化脚本才是真正的痛点。无论模型多么强大,你仍然需要调试过程以确保其保持长期稳定。Midscene.js 提供了可视化报告、内置的 Playground 和 Chrome 插件,以调试整个运行过程。这是大多数开发者真正需要的特性,我们也在持续努力改进调试体验。

* 开源、免费、部署灵活:Midscene.js 是一个开源项目。它与云服务和模型提供商解耦,你可以选择公共或私有部署。总会有一个适合你的计划。

* 与 Javascript 集成:你可以永远相信 Javascript 😎

## 📄 资源

* [官网首页: https://midscenejs.com](https://midscenejs.com/zh)
* [使用 Chrome 插件体验](https://midscenejs.com/zh/quick-experience.html),请从这里开始体验 Midscene
Expand All @@ -65,7 +75,7 @@ Midscene.js 是一个由 AI 驱动的自动化 SDK,能够使用自然语言对
* [选择 AI 模型](https://midscenejs.com/zh/choose-a-model.html)
* [配置模型和服务商(e.g. 使用千问模型)](https://midscenejs.com/zh/model-provider.html)

## 社区
## 🤝 社区

* [飞书交流群](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=291q2b25-e913-411a-8c51-191e59aab14d)
* [Discord](https://discord.gg/AFHJBdnn)
Expand All @@ -74,6 +84,6 @@ Midscene.js 是一个由 AI 驱动的自动化 SDK,能够使用自然语言对
<img src="https://github.com/user-attachments/assets/211b05c9-3ccd-4f52-b798-f3a7f51330ed" alt="lark group link" width="300" />


## 授权许可
## 📝 授权许可

Midscene.js 遵循 [MIT 许可协议](https://github.com/web-infra-dev/midscene/blob/main/LICENSE)
12 changes: 11 additions & 1 deletion apps/site/docs/en/index.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -73,6 +73,16 @@ You can also use the open-source model named `UI-TARS`, which is an end-to-end G

Read more about it in [Choose a model](./choose-a-model).

## 👀 Comparing to ...

There are so many UI automation tools out there, and each one seems to be all-powerful. What's special about Midscene.js?

* Debugging Experience: You will soon find that debugging and maintaining automation scripts is the real challenge point. No matter how magic the demo is, you still need to debug the process to make it stable over time. Midscene.js offers a visualized report file, a built-in playground, and a Chrome Extension to debug the entire process. This is what most developers really need. And we're continuing to work on improving the debugging experience.

* Open Source, Free, Deploy as you want: Midscene.js is an open-source project. It's decoupled from any cloud service and model provider, you can choose either public or private deployment. There is always a suitable plan for your business.

* Integrate with Javascript: You can always bet on Javascript 😎

## Just you and model provider, no third-party services

All data gathered from pages will be sent directly to OpenAI or the custom model provider according to your configuration. Therefore, no third-party platform will access the data.
Expand All @@ -81,7 +91,7 @@ For more details, please refer to [Data Privacy](./data-privacy).

## Follow us

* [GitHub - give us a star](https://github.com/web-infra-dev/midscene)
* [GitHub - give us a star!](https://github.com/web-infra-dev/midscene)
* [Twitter](https://x.com/midscene_ai)
* [Discord](https://discord.gg/AFHJBdnn)
* [Lark](https://applink.larkoffice.com/client/chat/chatter/add_by_link?link_token=291q2b25-e913-411a-8c51-191e59aab14d)
10 changes: 10 additions & 0 deletions apps/site/docs/zh/index.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -60,6 +60,16 @@ Midscene 同时支持通用 LLM 和开源模型。你可以使用通用的 LLM

更多详情请参考 [选择 AI 模型](./choose-a-model)

## 与其他工具比较

业界的 UI 自动化工具层出不穷,每个 Demo 都看起来很科幻。Midscene.js 有什么特别之处?

* 调试体验:你很快就会发现,调试和维护自动化脚本才是真正的痛点。无论模型多么强大,你仍然需要调试过程以确保其保持长期稳定。Midscene.js 提供了可视化报告、内置的 Playground 和 Chrome 插件,以调试整个运行过程。这是大多数开发者真正需要的特性,我们也在持续努力改进调试体验。

* 开源、免费、部署灵活:Midscene.js 是一个开源项目。它与云服务和模型提供商解耦,你可以选择公共或私有部署。总会有一个适合你的计划。

* 与 Javascript 集成:你可以永远相信 Javascript 😎

## 直连模型端,无需三方服务

Midscene 运行在用户的自有环境中,所有从页面收集的数据会依照用户的配置,直接传送到 OpenAI 或指定的自定义模型。因此,任何第三方平台均无法获取这些数据。
Expand Down

0 comments on commit 35bf713

Please sign in to comment.