Witsy

What is Witsy?

Witsy, developed by nbonamy, is a versatile desktop AI assistant designed to enhance productivity and interaction with AI models through a user-friendly interface. It operates as a BYOK (Bring Your Own Keys) application, meaning you need to have API keys from your preferred LLM (Large Language Model) providers. Alternatively, you can run models locally using Ollama without any cost. Witsy supports a wide range of AI models, including those from OpenAI, Anthropic, Google, and more, enabling users to perform tasks such as chat completions, text-to-image/video generation, and transcription.

How to Use Witsy

To get started with Witsy, download the application and ensure you have the necessary API keys for your chosen AI models. Once set up, you can utilize Witsy's features by interacting with its user interface. Key functionalities include:

Prompt Anywhere: Generate content directly in any application by hitting the shortcut (Shift+Control+Space) and entering your prompt in the pop-up window.
AI Commands: Enhance productivity by selecting text in any application, using the AI command shortcut (Alt+Control+Space), and choosing a suitable command to automate tasks.
Scratchpad: Experiment and interactively create content with various models to find the best output.
Document Interaction: Connect chats with document repositories to provide relevant context to AI models.

Witsy also allows you to chat with local files, transcribe audio to text, and use voice mode for real-time conversations. Customize your experience by setting up experts and commands based on your needs.

Key Features of Witsy

Wide Model Support: Compatible with multiple AI model providers, including OpenAI, Anthropic, Google, and others.
Content Generation: Supports text-to-image/video creation and chat completions with vision model capabilities.
Interactive Tools: Features like Scratchpad and AI Commands facilitate creative and productive interactions with AI.
Document Integration: Incorporates document repositories to enhance AI responses with relevant data.
Speech and Audio Processing: Offers transcription and dictation capabilities for converting speech to text.
Customization and Expertise: Allows the creation of custom commands and experts to tailor AI interactions.
Real-time Interaction: Voice mode for instant communication with AI models.
Convenient Export Options: Export conversations as PDFs and copy generated code to the clipboard.
Accessibility Across Applications: Use Prompt Anywhere and AI Commands in any application for seamless integration.

Witsy empowers users to leverage AI technology effectively, providing a comprehensive suite of tools for diverse applications, all while maintaining a user-friendly experience.

Witsy Desktop AI Assistant Version Badge Downloads Badge Test Badge Coverage Badge

Downloads

Download Witsy from witsyai.com or from the releases page.

What is Witsy?

Witsy is a BYOK (Bring Your Own Keys) AI application: it means you need to have API keys for the LLM providers you want to use. Alternatively, you can use Ollama to run models locally on your machine for free and use them in Witsy. Non-exhaustive feature list:

OpenAI, Ollama, Anthropic, MistralAI, Google, xAI, OpenRouter, DeepSeek, Groq and Cerebras models supported
Connect other providers (together, siliconflow, fireworks...) through OpenAI compatibility layer
Chat completion with vision models support (describe an image)
Text-to-image and text-to video with OpenAI, HuggingFace and Replicate
Scratchpad to interactively create the best content with any model!
Prompt anywhere allows to generate content directly in any application
AI commands runnable on highlighted text in almost any application
Experts prompts to specialize your bot on a specific topic
LLM plugins to augment LLM: execute python code, search the Internet...
Long-term memory plugin to increase relevance of LLM answers
Read aloud of assistant messages (requires OpenAI or ElevenLabs API key)
Read aloud of any text in other applications (requires OpenAI or ElevenLabs API key)
Chat with your local files and documents (RAG)
Transcription/Dictation (Speech-to-Text)
Realtime Chat aka Voice Mode
Anthropic Computer Use support
Local history of conversations (with automatic titles)
Formatting and copy to clipboard of generated code
Conversation PDF export
Image copy and download

Prompt Anywhere

Generate content in any application:

From any editable content in any application
Hit the Prompt anywhere shortcut (Shift+Control+Space / ^⇧Space)
Enter your prompt in the window that pops up
Watch Witsy enter the text directly in your application! On Mac, you can define an expert that will automatically be triggered depending on the foreground application. For instance, if you have an expert used to generate linux commands, you can have it selected if you trigger Prompt Anywhere from the Terminal application!

AI Commands

AI commands are quick helpers accessible from a shortcut that leverage LLM to boost your productivity:

Select any text in any application
Hit the AI command shorcut (Alt+Control+Space / ⌃⌥Space)
Select one of the commands and let LLM do their magic! You can also create custom commands with the prompt of your liking! Commands inspired by [).

Experts

From [).

Scratchpad

Chat with your documents (RAG)

You can connect each chat with a document repository: Witsy will first search for relevant documents in your local files and provide this info to the LLM. To do so:

Click on the database icon on the left of the prompt
Click Manage and then create a document repository
OpenAI Embedding require on API key, Ollama requires an embedding model
Add documents by clicking the + button on the right hand side of the window
Once your document repository is created, click on the database icon once more and select the document repository you want to use. The icon should turn blue

Transcription / Dictation (Speech-to-Text)

You can transcribe audio recorded on the microphone to text. Transcription can be done using OpenAI Whisper online model (requires API key) or using local Whisper model (requires download of large files). Once the text is transcribed you can:

Copy it to your clipboard
Insert it in the application that was running before you activated the dictation

Anthropic Computer Use

Setup

You can download a binary from from witsyai.com, from the releases page or build yourself:

npm install
npm start

Prerequisites

To use OpenAI, Anthropic, Google or Mistral AI models, you need to enter your API key:

OpenAI
Anthropic
xAI
Google
MistralAI
DeepSeek
OpenRouter
Groq
Cerebras To use Ollama models, you need to install Ollama and download some models. To use text-to-speech, you need an OpenAI API key. To use Internet search you need a Tavily API key.

TODO

Proper database (SQLite3) storage (??)

WIP

DONE

How to Use

To use the witsy, follow these steps:

Visit https://github.com/nbonamy/witsy
Follow the setup instructions to create an account (if required)
Connect the MCP server to your Claude Desktop application
Start using witsy capabilities within your Claude conversations

Additional Information

Created

April 25, 2024

Company

nbonamy

Related MCP Servers

Start building your own MCP Server

Interested in creating your own MCP Server? Check out the official documentation and resources.

Learn More

Witsy

What is Witsy?

How to Use Witsy

Key Features of Witsy

Downloads

What is Witsy?

Prompt Anywhere

AI Commands

Experts

Scratchpad

Chat with your documents (RAG)

Transcription / Dictation (Speech-to-Text)

Anthropic Computer Use

Setup

Prerequisites

TODO

WIP

DONE

How to Use

Additional Information

Created

Company

Related MCP Servers

Chato

Pdf Tools MCP

Mcpvr

Start building your own MCP Server