Illustration of what pinokio does: A desktop launcher that installs and runs open-source AI projects with one click

pinokiocomputer /

pinokio

A desktop launcher that installs and runs open-source AI projects with one click

  • 8.3k stars
  • 100 stars since 3 Oct
  • JavaScript
  • Updated 2 months ago
  • Beginner friendly
  • Models & local AI
Open on GitHub (opens in a new tab) Website (opens in a new tab)

Trying an open-source project usually means cloning a repo, setting up Python or Node, installing dependencies and running commands in the right order. Pinokio wraps that into scripts you run from a graphical app, so you click instead of typing.

A Pinokio script is written in JSON and can run any command, download files and execute them. Think of it as a terminal with a UI. You can write your own scripts or install them from a Discover page of reviewed scripts.

Isolation is the main design idea. Apps live under ~/pinokio/api, and binaries from the built-in package managers (Conda, Homebrew, Pip, NPM) go under ~/pinokio/bin. A venv attribute keeps Python dependencies inside each app's folder. Scripts can still run anything, so read them before you run them.

What it does

  • One-click launcher

    Installs and runs open-source projects from scripts through a graphical interface instead of a raw terminal.

  • Isolated by default

    Apps, binaries and dependencies are kept under ~/pinokio. The path and venv attributes keep commands and Python packages inside each app's folder.

  • Readable JSON scripts

    Scripts are JSON, so people and tools can check them. They must come from public git repositories, and the install screen shows the source URL.

  • Reviewed Discover page

    Featured scripts come from verified publishers, live in the Pinokio Factory GitHub organization, and are reviewed and tested by the admin before listing.

  • Built-in package managers

    Conda, Homebrew, Pip and NPM install into the Pinokio home folder by default.

What you could build

  • Install and run a local open-source AI app without configuring Python environments yourself.
  • Write a JSON script that sets up and launches your own project for others to run.
  • Browse the Discover page to find reviewed scripts for open-source tools.
  • Keep experimental projects and their dependencies contained in one folder, away from your system setup.
  • Review a script's commands and source repository before deciding to run it.

Get started

The README gives no install commands. Get the app from the project homepage at pinokio.co, then pick a script from the Discover page and run it, checking the source URL on the install screen.

Commands are copied from the project's README. Read it on GitHub for the full setup.

More in Models & local AI

See all
transformers Shared model definitions for text, vision, audio and multimodal AI models 168k open-webui Self-hosted chat interface for Ollama and OpenAI-compatible models, with RAG and plugins 156.5k2.7k odysseus Self-hosted workspace for AI chat, agents, research, documents, email and calendar 94.2k5.8k minimind Train a tiny 64M-parameter language model from scratch on one consumer GPU 64.3k1.2k Kronos Pre-trained Transformer models that forecast candlestick (K-line) price data 43.2k3.4k airllm Run very large open language models on a small GPU by loading one layer at a time 40.4k5.1k Vane Self-hosted AI answer engine that searches the web and cites its sources 37.7k681 timesfm Pretrained Google model that forecasts time series without training on your data 34.7k668 Unlimited-OCR Open OCR model that turns images and multi-page PDFs into structured text in one pass 28.2k1.6k gallery Android and iOS app for running open LLMs offline on your phone 25.1k252

    ↑↓ to move, Enter to open, Esc to close