Witsy

What is Witsy about?

Witsy provides a universal client for Model Context Protocol (MCP) servers, enabling users to interact with any LLM through a single desktop application. It supports a broad range of AI capabilities—chat, vision, image/video generation, text‑to‑speech, speech‑to‑text, internet search, embeddings, and document‑based retrieval—while keeping all API keys under the user's control (BYOK).

How to use Witsy?

Install – download the binary from https://witsyai.com, via Homebrew (brew install --cask witsy on macOS), or build from source:
```
npm install
npm start
```
Configure providers – open Settings and paste the API keys for the services you want (OpenAI, Anthropic, Gemini, Ollama, etc.).
Launch – the app runs in the system tray; invoke the global shortcuts (e.g., Shift+Ctrl+Space for Prompt Anywhere or Alt+Ctrl+Space for AI Commands).
Interact – type or speak prompts, attach files, enable RAG by linking a document repository, and let the selected model generate responses.

Key Features of Witsy

Multi‑provider chat: OpenAI, Anthropic, Google Gemini, Mistral, DeepSeek, Groq, Ollama, OpenRouter, and any OpenAI‑compatible API.
Vision & multimodal: chat with images, generate/edit images, create videos via Replicate/fal.ai.
Audio: text‑to‑speech (OpenAI, ElevenLabs, Groq) and speech‑to‑text (Whisper, Gladia, Speechmatics, etc.).
Prompt Anywhere: inject generated text into any active application via a global shortcut.
AI Commands: context‑aware shortcuts for code generation, summarization, translation, etc.; fully customizable.
Experts: pre‑saved prompt templates for specific domains (e.g., Linux commands, marketing copy).
Scratchpad & RAG: attach local documents, perform similarity search with embeddings, and let the LLM reference them.
Plugins: Python code execution, internet search (Tavily, Brave, Exa), YouTube, download content, etc.
Long‑term memory: optional plugin to retain conversational context across sessions.
Export & import: conversation PDF export, backup/restore of settings and data.
Cross‑platform UI: Electron/Vue3 interface with dark mode, tray integration, customizable shortcuts.

Use Cases of Witsy

Developer productivity: generate code snippets, refactor code, run Python scripts, and insert results directly into IDEs.
Content creation: produce blog drafts, marketing copy, social media posts, and accompanying images or videos.
Research & summarization: ingest PDFs, DOCX, PPTX, and ask the model to summarise or extract key points.
Multilingual support: translate, transcribe, and read aloud content in many languages.
Automation: create AI Commands that trigger workflows (e.g., fetch data, run CLI tools) from any application.
Local model usage: run Ollama or other self‑hosted models for privacy‑first scenarios.

FAQ from Witsy

Q: Do I need to pay for the models? A: Only for the providers you enable. Ollama can run locally for free; all other services require their own API keys.

Q: Can I use Witsy offline? A: Yes, with locally hosted models via Ollama or any OpenAI‑compatible server you run yourself.

Q: How are my API keys stored? A: Keys are saved locally in encrypted form and never transmitted to any third‑party server.

Q: Is there a macOS notarization? A: Yes, the macOS binary is notarized and can be installed via Homebrew.

Q: How do I add a new AI Command? A: Open Settings → AI Commands → "Add", define the prompt template and assign a shortcut.

Q: What is the difference between Experts and Prompts? A: Experts are editable prompt collections that can be auto‑selected based on the foreground app; they replace the older "Prompt" terminology.

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 Witsy

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

Similar MCP Servers like Witsy

Zed

Everything

Git

Time

Cline

Continue

Context7 MCP

Framelink Figma MCP Server

GitMCP