MindWorkAI/AI-Studio

MindWork AI Studio is a free, independent cross-platform desktop app for local and cloud LLMs across providers, built to democratize AI access.

MindWork AI Studio – What It Is

MindWork AI Studio is a free, cross‑platform desktop application (macOS, Windows, Linux) that gives you a single graphical interface for talking to many large‑language‑model (LLM) providers. You bring your own API key (OpenAI, Anthropic, Google Gemini, etc.) or connect to a locally‑hosted model (llama.cpp, Ollama, LM Studio, vLLM, …). The app then lets you chat, run “assistants” (pre‑built prompt‑less tools), and use AI‑driven tools such as web search, document retrieval, or Confluence lookup.

Core Features (as described in the README)

Category What the app does
Model access Supports dozens of cloud providers (OpenAI GPT‑6/5, Anthropic Claude, Google Gemini, Perplexity, Mistral, Groq, etc.) and self‑hosted back‑ends (llama.cpp, Ollama, LM Studio, vLLM, etc.).
Assistants Ready‑made “assistants” for common tasks (translation, summarisation, code help, etc.) that require no manual prompting.
Tool use Models can call external tools automatically: web search, read a web page, search Confluence, and future plugins.
Local RAG (beta) Indexes files/folders on your machine (via Qdrant) and lets the model retrieve relevant passages; includes semantic search.
Voice & transcription Record voice, have audio/video files transcribed using a selectable provider (including self‑hosted).
Export Chat answers can be saved as Word, OpenDocument, LaTeX, Markdown, or a web page; tables become spreadsheets.
Enterprise controls Central IT can roll out providers, assistants, templates, and policies; set data‑privacy levels, confidence thresholds, and lock settings.
Low‑resource friendly Claims to run on cheap hardware (e.g., a €100 Raspberry Pi) with modest memory usage.
Open‑source build Source can be compiled (see documentation/Build.md). The UI is built with Tauri v2 (a Rust‑based desktop framework).

Who Might Use It?

  • Individual power users who want a desktop “ChatGPT‑like” client that works with any model they have access to.
  • Small teams or families that need a free, cross‑platform AI chat tool without a subscription.
  • Enterprises that want to centrally manage AI providers, enforce data‑privacy policies, and distribute custom assistants.
  • Developers/researchers who like to experiment with local models (llama.cpp, Ollama) while still having a polished UI.

How It Works (high‑level)

  1. Configure a provider – add your API key or point to a local server.
  2. Pick a model – the UI shows each provider’s capabilities and context‑window size.
  3. Start a chat or an assistant – type or speak; the model may automatically invoke tools (search, document retrieval).
  4. Result handling – view the answer, see sources, export, or copy the whole conversation.
  5. Enterprise mode – admins push configuration bundles, set defaults, and lock down which tools are allowed.

License & Availability

  • Distributed under a functional source license (FSL‑1.1‑MIT) that permits free personal/commercial use but restricts creating a competing product. Two years after each release the license automatically converts to plain MIT.
  • Pre‑built installers are provided for macOS, Windows, and Linux; source code is available for building yourself.

Quick Takeaway

MindWork AI Studio is a genuine, feature‑rich desktop client that aggregates many LLM services, adds local retrieval‑augmented generation, voice transcription, and enterprise‑grade management. It is firmly in the AI‑application space rather than a simple tutorial list or a trivial demo.

Links (from README)

Related

  • Project
    different-ai/openwork

    OpenWork is an open‑source, cross‑platform desktop app that lets AI agents work on your local files. It supports any LLM (hosted APIs, custom keys, or local Ollama models) and provides a Model‑Control‑Plane (MCP) with tools for discovering and executing shared skills. Teams can manage access, publish plugins, and self‑host the optional OpenWork Den control plane. The core app is MIT‑licensed; the Den component is source‑available under an EE license (free for small teams, paid for larger orgs).

  • Project
    OpenCoworkAI/open-cowork

    Open Cowork is a free, open‑source desktop app that wraps Claude‑style (and other) LLMs into a local AI‑agent workspace. With one‑click installers for Windows/macOS, VM‑level sandboxing (WSL2/Lima), a built‑in “Skills” system for generating PPTX/DOCX/PDF/XLSX files, MCP connectors for browsers/Notion, and remote control via Feishu or Slack, it lets non‑technical users give natural‑language commands that read/write files, automate GUI apps, and produce professional documents—all running locally with optional VM isolation.

  • Project
    RoseKhlifa/Image-Studio

    Image Studio is an open‑source, cross‑platform desktop client (Windows/macOS/Linux/Android) built with Go + React (Wails) that lets you generate and edit images via any OpenAI‑compatible API. It supports streaming responses over SSE or WebSocket to avoid proxy timeouts, works with the standard Images API, offers batch img2img, custom aspect ratios, and integrates with a prompt‑import helper. Configuration is manual (base URL, API key, model ID) and the project is AGPL‑v3 licensed.

  • Project
    sybil-solutions/local-studio

    Local Studio is a desktop UI (fork of T3 Code) that lets you run and manage self‑hosted LLMs. It bundles a controller that discovers any OpenAI‑compatible inference server on your machine, re‑exports it via a unified gateway, and can link multiple machines over Tailscale so models on any host are reachable from the UI. Includes extra providers (Pi, Oh My Pi) and one‑click controller installation on Linux/macOS.

  • Project
    Pinvou/pinvou-agent

    Pinvou Agent is a cross‑platform desktop AI‑assistant that lets you work, design, or code with a conversational model. It provides persistent workspaces, file attachments, a local knowledge base, persona cards, and an extensible plug‑in system (Skills, MCP servers, CLI tools). The UI is built with React + Vite, wrapped by Tauri 2, while the Rust‑based CodeWhale engine handles model calls and tool execution. It runs with any OpenAI‑compatible endpoint or a local vLLM server, and all user data stays under `~/.pinvou3/`. MIT‑licensed and actively maintained.