# Kochava-Studios/witsy

Witsy: desktop AI assistant / universal MCP client

Repository: https://github.com/Kochava-Studios/witsy
Canonical: https://ross.abutalabs.com/products/witsy
Language: TypeScript
License: AGPL-3.0
License Family: copyleft
Topics: anthropic, genai, groq, ollama, ollama-gui, openai, electron-app, electronjs, vuejs, vuejs3, deepseek, gemini, googleai, mistral, mistralai, openrouter, mcp, mcp-client
Last push: 2026-04-23T17:32:21+00:00

## Health v2 (maintenance only)
Score: 69/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 78, release rhythm 61, longevity 61
- inputs: {"age_days": 860, "days_push": 132, "days_rel": 182, "gap_med": 2, "n_releases_24m": 132}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2024, forks 166 (observed 2026-08-28T04:06:06.678167+00:00)

## What it is
Witsy is a cross-platform desktop AI assistant built with Electron and Vue 3 that lets users chat with many LLM providers using their own API keys or local Ollama models. It doubles as a universal MCP client, allowing MCP servers to be used with virtually any LLM, and includes image/video generation, speech features, and prompt-anywhere commands.

## Use cases
- chat with multiple llm providers from one desktop app
- run mcp servers with any llm
- use ollama models locally in a chat gui
- generate images and videos from text prompts
- dictate speech to text and read answers aloud
- run ai commands on highlighted text in any application
- bring your own api keys byok assistant
- search the web with llm augmented answers

## When to choose
- you want one desktop app for OpenAI, Anthropic, Gemini, Mistral, Groq and more
- you need MCP tool support with models that lack native MCP
- you prefer local models via Ollama or LM Studio
- you want speech-to-text, TTS, and image generation alongside chat

## When to avoid
- you need a headless or server-side API rather than a GUI app
- you want a fully managed service without supplying your own API keys
- you only need a lightweight terminal or CLI chat client

## Facets
- artifact type: application
- maturity: active
- function: chatbot, llm-inference, mcp, rag, speech-recognition, tts, image-processing, search-engine, agent-framework
- domain: artificial-intelligence, large-language-models, chatbots, desktop-applications, developer-tools
- platform: windows, cross-platform
- tags: byok, mcp-client, ollama, multi-provider, electron-app, ai-assistant, prompt-anywhere, text-to-image, text-to-speech, ai-agents, macos, linux, desktop, electron

## Member repositories
- Kochava-Studios/witsy (main) score 69

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:06.678167+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:59:48.746509+00:00, confidence not recorded.
  - readme: https://github.com/Kochava-Studios/witsy (fetched 2026-08-28T04:06:06.678167+00:00, sha 54fd2c533261)
- Data as of 2026-08-30T08:39:29.467469+00:00.