witsy
installs/mo · npmstarsforks
How to install witsy?
kochava-studios/witsy
$git clone https://github.com/Kochava-Studios/witsy</div>
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 | <img src="assets/icon.png" width="128" alt="Witsy Logo"> |
| 4 | <div><b>Witsy</b></div> |
| 5 | <div>Desktop AI Assistant<br/>Universal MCP Client</div> |
| 6 | |
| 7 | </div> |
| 8 | |
| 9 | <p></p> |
| 10 | <div align="center"> |
| 11 | |
| 12 | <!-- [](https://github.com/Kochava-Studios/witsy/releases) --> |
| 13 | [](https://tooomm.github.io/github-release-stats/?username=Kochava-Studios&repository=witsy) |
| 14 | [](https://github.com/Kochava-Studios/witsy/blob/main/.github/workflows/test.yml) |
| 15 | <!-- [](https://gist.github.com/Kochava-Studios/fee06adf8df838e499209254e61da7f6) --> |
| 16 | |
| 17 | </div> |
| 18 | |
| 19 | ## Downloads |
| 20 | |
| 21 | Download Witsy from the [releases](https://github.com/Kochava-Studios/witsy/releases) page. |
| 22 | |
| 23 | On macOS you can also `brew install --cask witsy`. |
| 24 | |
| 25 | |
| 26 | ## What is Witsy? |
| 27 | |
| 28 | 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, |
| 29 | you can use [Ollama](https://ollama.com) to run models locally on your machine for free and use them in Witsy. |
| 30 | |
| 31 | It is the first of very few (only?) universal MCP clients:<br/>***Witsy allows you to run MCP servers with virtually any LLM!*** |
| 32 | |
| 33 | ## Supported AI Providers |
| 34 | |
| 35 | | Capability | Providers | |
| 36 | |------------|-----------| |
| 37 | | **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 (together.ai for instance)| |
| 38 | | **Image Creation** | OpenAI, Google, xAI, Replicate, fal.ai, HuggingFace, Stable Diffusion WebUI | |
| 39 | | **Video Creation** | OpenAI, Google, Replicate, fal.ai | |
| 40 | | **Text-to-Speech** | OpenAI, ElevenLabs, Groq, fal.ai | |
| 41 | | **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 | |
| 42 | | **Search Engines** | Perplexity, Tavily, Brave, Exa, Local Google Search | |
| 43 | | **MCP Repositories** | Smithery.ai |
| 44 | | **Embeddings** | OpenAI, Ollama | |
| 45 | |
| 46 | Non-exhaustive feature list: |
| 47 | - Chat completion with vision models support (describe an image) |
| 48 | - Text-to-image and text-to video |
| 49 | - Image-to-image (image editing) and image-to-video |
| 50 | - LLM plugins to augment LLM: execute python code, search the Internet... |
| 51 | - Anthropic MCP server support |
| 52 | - Scratchpad to interactively create the best content with any model! |
| 53 | - Prompt anywhere allows to generate content directly in any application |
| 54 | - AI commands runnable on highlighted text in almost any application |
| 55 | - Experts prompts to specialize your bot on a specific topic |
| 56 | - Long-term memory plugin to increase relevance of LLM answers |
| 57 | - Read aloud of assistant messages |
| 58 | - Read aloud of any text in other applications |
| 59 | - Chat with your local files and documents (RAG) |
| 60 | - Transcription/Dictation (Speech-to-Text) |
| 61 | - Realtime Chat aka Voice Mode |
| 62 | - Anthropic Computer Use support |
| 63 | - Local history of conversations (with automatic titles) |
| 64 | - Formatting and copy to clipboard of generated code |
| 65 | - Conversation PDF export |
| 66 | - Image copy and download |
| 67 | |
| 68 | <p align="center"> |
| 69 | <img src="doc/main1.jpg" height="250" /> |
| 70 | <img src="doc/main2.jpg" height="250" /> |
| 71 | <img src="doc/studio.jpg" height="250" /> |
| 72 | </p> |
| 73 | |
| 74 | ## Setup |
| 75 | |
| 76 | You can download a binary from from the [releases](https://github.com/Kochava-Studios/witsy/releases) page or build yourself: |
| 77 | |
| 78 | ``` |
| 79 | npm ci |
| 80 | npm start |
| 81 | ``` |
| 82 | |
| 83 | ## Prerequisites |
| 84 | |
| 85 | To use OpenAI, Anthropic, Google or Mistral AI models, you need to enter your API key: |
| 86 | - [OpenAI](https://platform.openai.com/ |
People who liked this also viewed
6 picksType
- odoo-mcp-proAI connector for Odoo ERP | Connect Claude, ChatGPT, Cursor and other AI tools to Odoo via MCPMCP ServersJul 2026
- omnigentUniversal autonomous agent framework with ReAct loop, multi-provider LLM routing, reasoning graph, and MCP integration, domain-agnostic for building specialized AI agents.MCP ServersFeb 2026
- arxiv-mcp-serverAn MCP server that enables interacting with the arXiv API using natural languageMCP ServersAug 2025
- United States WeatherProvide real-time and forecast weather information for locations in the United States using natural language queries. Access current conditions, multi-day and hourly forecasts, weather alerts, and nearby weather stations without requiring aMCP Serversrecently
- mcp-server-demoDemo of MCP Server in Python using FastMCPMCP ServersAug 2025
- mcp-serverlearn to make some mcp serversMCP ServersMay 2025
