![](src/assets/logo-cover.png)
Chat with ALL AI Bots Concurrently, Discover the Best
Deutsch | English | Español | Français | 日本語 | 한국어 | Tiếng Việt | 简体中文
Large Language Models (LLMs) based AI bots are amazing. However, their behavior can be random and different bots excel at different tasks. If you want the best experience, don't try them one by one. ChatALL (Chinese name: 齐叨) can send prompt to several AI bots concurrently, help you to discover the best results. All you need to do is download, install and ask.
Typical users of ChatALL are:
- 🤠Gurus of LLMs, who want to find the best answers or creations from LLMs.
- 🤓Researchers of LLMs, who want to intuitively compare the strengths and weaknesses of various LLMs in different fields.
- 😎Developers of LLM applications, who want to quickly debug prompts and find the best-performing foundation models.
AI Bots | Web Access | API | Notes |
---|---|---|---|
ChatGPT | Yes | Yes | Web Browsing included |
Bing Chat | Yes | No API | No login required |
Baidu ERNIE | No | Yes | |
Bard | Yes | Coming soon | |
Poe | Yes | Coming soon | |
MOSS | Yes | No API | |
Tongyi Qianwen | Yes | Coming soon | |
Dedao Learning Assistant | Coming soon | No API | |
iFLYTEK SPARK | Yes | Coming soon | |
Alpaca | Yes | No API | No Login required |
Vicuna | Yes | No API | No Login required |
ChatGLM | Yes | No API | No Login required |
Claude | Yes | No API | No Login required |
Gradio | Yes | No API | For Hugging Face space/self-deployed models |
HuggingChat | Yes | No API | |
QianWen | Yes | Coming soon |
More is coming. Upvote your favorite bots in these issues.
- Quick-prompt mode: send the next prompt without waiting for the previous request to complete
- Store chat history locally, protect your privacy
- Highlight the response you like, delete the bad
- Automatically keep ChatGPT session alive
- Enable/disable any bots at any time
- Switch between one, two, or three-column view
- Supports multiple languages (Chinese, English, German, French, Russian, Vietnamese, Korean)
- Supports Windows, macOS and Linux
Planned features:
You are welcome to contribute to these features.
- Dark mode
- Multi-chats
- Deploy front-end to GitHub Pages
- LangChain integration
ChatALL is a client, not a proxy. Therefore, you must:
- Have working accounts and/or API tokens for the bots.
- Have reliable network connections to the bots.
- If you are using a VPN, it must be set as system/global proxy.
Download from https://github.com/sunner/ChatALL/releases
Just download the *-win.exe file and proceed with the setup.
For Apple Silicon Mac (M1, M2 CPU), download the *-mac-arm64.dmg file.
For other Macs, download *-mac-x64.dmg file.
If the system prompts that it cannot check whether the software is malicious, follow the Apple official guide to proceed.
Download the .AppImage file, make it executable, and enjoy the click-to-run experience.
If you encounter any problems while using ChatALL, you can try the following methods to resolve them:
- Refresh - press
Ctrl + R
orCmd + R
. - Restart - exit ChatALL and run it again.
- Re-login - click the settings button in the upper right corner, then click the corresponding login/logout link in the pop-up window to log in to the website again.
- Clear all messages - click the broom button in the upper right corner.
If none of the above methods work, you can try resetting ChatALL. Note that this will delete all your settings and message history.
You can reset ChatALL by deleting the following directories:
- Windows:
C:\Users\<user>\AppData\Roaming\ChatALL\
- Linux:
/home/<user>/.config/ChatALL/
- macOS:
/Users/<user>/Library/Application Support/ChatALL/
If the problem persists, please submit an issue.
The guide may help you.
Node.js must be v16.x
npm install
npm run electron:serve
Build for your current platform:
npm run electron:build
Build for all platforms:
npm run electron:build -- -wml --x64 --arm64
- GPT-4 contributed much of the code
- ChatGPT, Bing Chat and Google provide many solutions (ranked in order)
- Inspired by ChatHub. Respect!
If you like this project, please consider: