Skip to main content

Jupyter AI Claude Code

Jupyter AI integration with Claude Code persona for enhanced development capabilities.

Features

  • Claude Code Integration: Full Claude Code persona for Jupyter AI
  • Continuous Conversation: Maintains conversation context across multiple messages
  • Development Tools: Access to Claude Code's built-in development tools
  • Seamless Integration: Works with existing Jupyter AI workflow
  • Template Management: Interactive task progress tracking and updates

Setup

This project uses pixi.sh for dependency management and environment setup.

Prerequisites

Install pixi.sh:

curl -fsSL https://pixi.sh/install.sh | bash

Installation

  1. Clone the repository:
git clone <repository-url>
cd jupyter-ai-claude-code
  1. Enter the pixi shell environment:
pixi shell

Usage

Start JupyterLab

pixi run start

This will start JupyterLab with the Jupyter AI extension and Claude Code persona available.

Using Claude Code Persona

  1. Open JupyterLab
  2. Open the Jupyter AI chat panel
  3. Select "Claude" persona
  4. Interact with Claude Code's development tools

Continuous Conversation

The Claude Code persona now supports continuous conversation, which maintains context across multiple messages in a chat session. This allows Claude to:

  • Remember previous questions and answers
  • Build upon earlier context in the conversation
  • Provide more coherent multi-turn interactions

Session Management:

The persona automatically manages conversation sessions. Each time you send a message, it's added to the ongoing conversation context.

How it works:

  • The first message automatically creates a new ClaudeSDKClient session.
  • Subsequent messages reuse the same client to maintain conversation context.
  • The client persists until you start a new session in the chat window.

Build the Package

The package is automatically installed in editable mode during pixi shell. To manually build:

pixi run python -m build

Development

The package source code is located in src/jupyter_ai_claude_code/.

Dependencies

  • JupyterLab: Latest stable version from conda-forge
  • Jupyter AI: Version 3.0.0b5 from PyPI
  • Claude Code SDK: For Claude Code integration
  • Python: >=3.8

License

Revised BSD

Metadata

Release files for jupyter-ai-claude-code 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for jupyter-ai-claude-code 0.0.1
File Size Uploaded Provenance Actions
jupyter_ai_claude_code-0.0.1.tar.gz 45.1 kB Without provenance Details for jupyter_ai_claude_code-0.0.1.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for jupyter-ai-claude-code 0.0.1
File Interpreter ABI Platform Actions
jupyter_ai_claude_code-0.0.1-py3-none-any.whl Python 3 none any Details for jupyter_ai_claude_code-0.0.1-py3-none-any.whl

Total release size: 57.8 kB

Release files / jupyter_ai_claude_code-0.0.1.tar.gz

Download URL jupyter_ai_claude_code-0.0.1.tar.gz
Size 45.1 kB
Tags Source
SHA-256 checksum
How to use checksums
802a0e26362c745b30575876002929a0b8406836914ea81605a69402afa23ae3
BLAKE2b-256 checksum
How to use checksums
db944e7c23b92234a088bad4b18a2a4a48a42186d1a37bfa36bbf46389db6043
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.2.0 CPython/3.12.12

Release files / jupyter_ai_claude_code-0.0.1-py3-none-any.whl

Download URL jupyter_ai_claude_code-0.0.1-py3-none-any.whl
Size 12.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
ea8b6e746f2c4fd0032e76e77471ce5972c9d66223fae1a92c7288f38be719d5
BLAKE2b-256 checksum
How to use checksums
579562a70b50b578a72ef124c748687b1d9342de16c5560251fbcc6b6b371d43
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/6.2.0 CPython/3.12.12

Security for jupyter-ai-claude-code 0.0.1

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

0.0.1 This release

2 release files No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page