Witsy

What is Witsy about?

Witsy delivers a universal Model Context Protocol (MCP) client for desktop environments, letting users interact with any OpenAI‑compatible LLM as well as native services like Ollama, Anthropic, Gemini, Groq, MistralAI, DeepSeek, and many others. It centralises chat, image/video creation, speech‑to‑text, text‑to‑speech, web search, and document‑based retrieval in a single Electron‑based UI.

How to use Witsy?

Install – download a binary from the website, via Homebrew (brew install --cask witsy), or build from source with npm install && npm start.
Add API keys – open Settings and paste keys for the providers you plan to use (OpenAI, Anthropic, Google Gemini, etc.).
Select a model – choose any installed or cloud model from the model picker.
Interact – start a chat, invoke Prompt Anywhere (Shift+Ctrl+Space), trigger AI Commands (Alt+Ctrl+Space), or enable Realtime Voice.
Extend – create custom experts, commands, or document repositories for RAG.

Key features of Witsy

Multi‑provider chat with vision support (describe images).
Generative media: text‑to‑image, text‑to‑video, image‑to‑image, image‑to‑video.
Speech: real‑time dictation, transcription, text‑to‑speech (OpenAI, ElevenLabs, etc.).
Prompt Anywhere – inject generated text into any foreground application via a global shortcut.
AI Commands – quick actions on selected text (code generation, summarisation, translation, etc.).
Experts – pre‑defined prompt bundles for specific domains; auto‑switch based on active app (macOS).
Scratchpad – interactive multi‑step reasoning with tool usage.
RAG / Document repositories – attach local files, embed them, and let the LLM retrieve context.
Plugins – web search (Tavily, Brave, Exa, local Google), Python code execution, YouTube link handling, etc.
History & export – automatic conversation titles, PDF export, local storage, dark mode, tray icon, auto‑update.

Use cases of Witsy

Scenario	How Witsy helps
Developer assistance	Generate code snippets, run Python plugins, fetch docs, and paste directly into IDEs.
Content creation	Produce images, videos, and audio narrations for blogs or social posts without leaving the desktop.
Research & analysis	Attach PDFs, DOCX, or codebases, let the assistant summarise, extract insights, and answer questions.
Productivity shortcuts	Transform highlighted text into commands (e.g., generate Linux commands, rewrite emails, translate on‑the‑fly).
Accessibility	Real‑time speech‑to‑text dictation and text‑to‑speech playback for hands‑free interaction.
Multi‑model experimentation	Switch between OpenAI, Anthropic, Ollama, Groq, etc., to compare outputs instantly.

FAQ from the Witsy community

Q: Do I need to pay for every provider? A: Only the services you enable require a paid API key. Ollama runs locally for free.

Q: Can I run Witsy offline? A: Yes, with locally hosted models via Ollama (including embeddings) and Whisper for STT.

Q: How does Witsy store my data? A: All conversation history, settings, and document repositories are saved locally in a SQLite‑based store (future work) and can be backed up or restored via the UI.

Q: Is there a way to create my own custom command? A: Open Settings → Commands, add a new entry, define the prompt template, and assign a shortcut.

Q: What platforms are supported? A: macOS (including Homebrew cask), Windows, and Linux via the downloadable binaries.

Important Accouncement

Witsy’s Next Chapter: New Stewardship and License Update #386

Downloads

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

On macOS you can also brew install --cask witsy.

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.

It is the first of very few (only?) universal MCP clients:Witsy allows you to run MCP servers with virtually any LLM!

Supported AI Providers

Capability	Providers
Chat	OpenAI, Anthropic, Google (Gemini), xAI (Grok), Meta (Llama), Ollama, LM Studio, MistralAI, DeepSeek, OpenRouter, Groq, Cerebras, Azure OpenAI, any provider who supports the OpenAI API standard
Image Creation	OpenAI (DALL-E), Google (Imagen), xAI (Grok), Replicate, fal.ai, HuggingFace, Stable Diffusion WebUI
Video Creation	Replicate, fal.ai
Text-to-Speech	OpenAI, ElevenLabs, Groq
Speech-to-Text	OpenAI (Whisper), fal.ai, Fireworks.ai, Gladia, Groq, nVidia, Speechmatics, Local Whisper, Soniox (realtime and async) any provider who supports the OpenAI API standard
Search Engines	Tavily, Brave, Exa, Local Google Search
MCP Repositories	Smithery.ai
Embeddings	OpenAI, Ollama

Non-exhaustive feature list:

Chat completion with vision models support (describe an image)
Text-to-image and text-to video
Image-to-image (image editing) and image-to-video
LLM plugins to augment LLM: execute python code, search the Internet...
Anthropic MCP server support
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
Long-term memory plugin to increase relevance of LLM answers
Read aloud of assistant messages
Read aloud of any text in other applications
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 https://the.fibery.io/@public/Public_Roadmap/Roadmap_Item/AI-Assistant-via-ChatGPT-API-170.

Experts

From https://github.com/f/awesome-chatgpt-prompts.

Scratchpad

https://www.youtube.com/watch?v=czcSbG2H-wg

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 a variety of state of the art speech to text models (which require API key) or using local Whisper model (requires download of large files).

Currently Witsy supports the following speech to text models:

GPT4o-Transcribe
Gladia
Speechmatics (Standards + Enhanced)
Groq Whisper V3
Fireworks.ai Realtime Transcription
fal.ai Wizper V3
fal.ai ElevenLabs
nVidia Microsoft Phi-4 Multimodal

Witsy supports quick shortcuts, so your transcript is always only one button press away.

Once the text is transcribed you can:

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

Anthropic Computer Use

https://www.youtube.com/watch?v=vixl7I07hBk

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:

To use Ollama models, you need to install Ollama and download some models.

To use text-to-speech, you need an

To use Internet search you need a Tavily API key.

TODO

Implement Soniox for STT
Workspaces / Projects (whatever the name is)
Proper database (SQLite3) storage (??)

WIP

DONE

Login Required

Please log in to share your review and rating for this MCP.

Witsy Overview

What is Witsy about?

How to use Witsy?

Key features of Witsy

Use cases of Witsy

FAQ from the Witsy community

Witsy's README

Important Accouncement

Downloads

What is Witsy?

Supported AI Providers

Prompt Anywhere

AI Commands

Experts

Scratchpad

Chat with your documents (RAG)

Transcription / Dictation (Speech-to-Text)

Anthropic Computer Use

Setup

Prerequisites

TODO

WIP

DONE

Witsy Reviews

Login Required

Actions

Witsy's Information

Related MCP Servers

Atlassian

Oterm

Office PowerPoint MCP Server

Office Word MCP Server

Gmail

Google Calendar

Tome

Pandoc

Todoist