👼 smol menubar

This is a smol menubar app that helps you quickly access the full webapps of ChatGPT (defaults to "GPT4.5"!!), Claude 2, Perplexity.ai, Bing and more (see below) with a single keyboard shortcut (Cmd+Shift+G).

we also support Bard, Phind, Together.ai, and local/GGML models like LLaMA and Vicuna (via OobaBooga) but hide by default bc they aren't as good!

(click for video demo)

Whatever is typed at the bottom is entered into all web apps simultaneously, however if you wish to explore one further than the other you can do so independently since they are just webviews. See video demo

Oh so this is like nat.dev?

Yes and no:

SOTA functionality is often released without API (eg: ChatGPT Code Interpreter, Bing Image Creator, Bard Multimodal Input, Claude Multifile Upload). We insist on using webapps so that you have full access to all functionality on launch day. We also made light/dark mode for each app, just for fun (Cmd+Shift+L)
This is a menubar app that can be invoked with a keyboard shortcut (Cmd+Shift+G). Feels a LOT faster than having it live in a browser window somewhere and is easy to pull up/dismiss during long generations.
Supports local models like LLaMa and Vicuna via OobaBooga.
No paywall, build from source.

Supported LLM Providers

Provider (default in bold)	Notes
ChatGPT	Defaults to GPT 4 Code Interpreter
Claude 2	Login Tip: Use manual email login and remember to type (not paste) the login code! (#56)
HuggingChat	Offers Llama2, OpenAssistant
Perplexity	Search + Chat
Bing	Microsoft's best. It's not the same as GPT-4!
Bard	Google's best. Bard's updates are... flaky
Local/GGML Models (via OobaBooga)	Requires Local Setup
Phind	Developer focused chat
OpenAssistant	Coming Soon — Submit a PR!
Quora Poe	Coming Soon — Submit a PR!
Vercel Chat	Coming Soon — Submit a PR!
Claude	Requires Beta Access
... What's Else?	Submit a New Issue!

Features and Usage

Keyboard Shortcuts:
- Use Cmd+Shift+G for quick open and Cmd+Enter to submit.
- Customize these shortcuts (thanks @davej!):
  - Quick Open
  - Submit can be toggled to use Enter (faster for quick chat replies) vs Cmd+Enter (easier to enter multiline prompts)
- Cmd+Shift+L to toggle light/dark mode (not customizable for now)
- Remember you can customize further by building from source!
Window Resizing:
- Resize the window by clicking and dragging.
- Use Cmd+1/2/3/A/+/- or drag to resize the internal webviews.
  - Cmd + and Cmd - are especially useful if you have a lot of chats enabled!
Model Toggle:
- Enable/disable providers by accessing the context menu from the menubar icon (right-click and choose from the list). The choice is saved for future sessions.
- Supported models: ChatGPT, Bing, Bard, Claude 1/2, and more (see Supported LLM Providers above)
Support for oobabooga/text-generation-webui:
- Initial support for oobabooga/text-generation-webui has been added.
- Users need to follow the process outlined in the text-generation-webui repository, including downloading models (e.g. LLaMa-13B-GGML).
- Run the model on http://127.0.0.1:7860/ before running it inside of the smol menubar.
- The UI only supports one kind of prompt template. Contributions are welcome to make the templating customizable (see the Oobabooga.js provider).
Starting New Conversations:
- Use Cmd+R to start a new conversation with a simple window refresh.

video demo

original version https://youtu.be/jrlxT1K4LEU
Jun 1 version https://youtu.be/ThfFFgG-AzE
https://twitter.com/swyx/status/1658403625717338112
https://twitter.com/swyx/status/1663290955804360728?s=20
July 11 version https://twitter.com/swyx/status/1678944036135260160

Download and Setup

You can download the precompiled binaries for MacOS: https://github.com/smol-ai/menubar/releases/latest (sometimes Apple marks these as untrusted/damaged, just open them up in Applications and right-click-open to run it. Or run it from source (instructions below)

The first run creates a desktop shortcut. After the initial setup, you can simply use the generated desktop file to start the application in the future.

When you first run the app:

log into your Google account (once you log into your google account for chatgpt, you'l also be logged in to Bard).
For Bing, after you log in to your Microsoft account, you'll need to refresh to get into the Bing Chat screen. It's a little finnicky at first try but it works.
Login for Anthropic via Google SSO is broken right now - it requires a popup which is blocked at least in my testing. For now just use manual email + login token, it works fine (dont include the extra space at the end from their email!!). If you are familiar with Electron and Webviews, would welcome a PR to fix, we can't figure it out so far.

seeking contributors!

please see https://github.com/smol-ai/menubar/blob/main/CONTRIBUTING.md

build from source

If you want to build from source, you will need to clone the repo and open the project folder:

Clone the repository and navigate to the project folder:

git clone https://github.com/smol-ai/menubar.git
cd menubar
npm install
# On Windows, you may also need Squirrel:
# npm install electron-squirrel-startup

Generate binaries:
```
npm run make # or npm run build. # npm run buildAndSign is for swyx to publish the official codesigned and notarized releases
```
The outputs will be located in the /out/make directory. Note that it will start minimized in your taskbar; you'll need to click the icon to use it:

windows/linux builds

by default we're mac only - i only have a mac sorry. (we are seeking a "Windows Maintainer"! and someone to help make this work on Arch Linux)

for Windows i think you can run

electron-forge make --platform=win32 --arch=ia32,x64

and it might work? (Update: confirmed works).

why use/make this?

Google dropped its waitlist for Bard recently, so now there is some reason to try it out.

People have bad first impressions on Bard, but in May 2023 it has been receiving some positive feedback:

these folks aren't neutral, but its clear of course that Bard will be better for some things than others, and we might as well lower the barrier for trying them out.

then anthropic dropped 100k context, and at that point i was convinced i need to be A/B testing all 3 to get the benefits/get an intuition of what they each are best at.

Related project

I only later heard about https://github.com/sunner/ChatALL which is cool but I think defaulting to a menbuar/webview experience is better - you get to use full features like Code Interpreter and Claude 2 file upload when they come out, without waiting for API

smol-ai / menubar