OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Data & Analytics

Pretzel

Pretzel is an open-source fork of Jupyter that adds AI code generation and editing, inline code completion, sidebar chat and error fixing to notebook work.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Pretzel — OpenViST project profile in AI Data & Analytics.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Pretzel when you want coding assistance alongside an existing Jupyter notebook workflow, particularly for data exploration and visualization.

Who it is for

  • Jupyter users who want AI assistance while writing or revising notebook code.
  • Data analysts and explorers who work in notebooks and create visualizations.

Documented uses

  • Draft code from an instruction in a notebook cell.
  • Revise a full cell or selected code with AI assistance.
  • Get inline code completions while typing.
  • Ask questions or generate code through a sidebar chat.
  • Seek help fixing notebook code errors.
Before you choose

Requirements & limits

The README describes a hosted version at pretzelai.app and local installation with pip; it also provides Docker setup instructions. It calls the hosted version free.

  • Cell prompts can generate code or edit existing code, with selection-based editing for a narrower change.
  • Pretzel’s README says it retains Jupyter configuration, settings, keybindings and extensions.
  • The default inline-completion model is identified as Mistral Codestral; the README lists OpenAI, Anthropic/Claude, Ollama and Groq for using a personal model.
  • Collaboration, standalone SQL tooling and dashboard creation are presented as roadmap items, not current features.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install and open Pretzel with pip

Install Pretzel locally and start its notebook web interface.

Before you start

  • Python environment with pip; the README also describes installing pip through conda.
  • On systems where the PyStemmer build fails, the README lists required build tools for Windows, Ubuntu/Debian and macOS.

Steps

  1. Install Pretzel with the command below.

    Documented command
    pip install pretzelai

  2. Run pretzel lab.

  3. Open the interface at the URL provided by the command.

Expected outcome

The Pretzel notebook interface opens in a web browser.

Guide limitations

  • The guide does not specify a supported Python version for the pip installation.
  • The README gives separate build-tool advice for a reported PyStemmer installation error.
Documentation 1 ↗
Source-based practical guide

Generate or edit code in a notebook cell

Use Pretzel’s cell-level AI prompt to draft code or revise existing code.

Before you start

  • An open Pretzel notebook with a cell to work in.

Steps

  1. In a cell, press Cmd+K on Mac or Ctrl+K on Windows/Linux, or choose Ask AI.

  2. Enter an instruction for code generation or editing.

  3. To focus an edit, select the relevant code first; type @ to choose a session variable for the prompt context.

  4. Review the response and accept or reject it, or revise the prompt.

Expected outcome

Pretzel returns a code suggestion for the cell or selected code, which the user can review.

Guide limitations

  • The README says relevant code from the current notebook is sent as context to the AI.
  • The guide describes generating and editing code, not running or validating the resulting code.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
17 October 2026
Original website title
pretzelai/pretzelai · Official homepage title · retained in its source language
How we review sourcesSuggest a correction