🚀 JupyterHub-Pilot
Agentic AI coding partner for JupyterHub and IPython.
JupyterHub-Pilot solves two major problems for data teams running JupyterHub:
- Isolated execution & State Persistence: A custom SSH spawner teleports each user's notebook server onto isolated EC2 workers, wraps it in cgroup resource limits, and tracks all sessions in SQLite.
- AI Magic Commands: An IPython extension adds
%do,%fix,%review, and%reworkmagic commands that speak to any LLM backend (Ollama, OpenAI, Claude, Gemini, or MCP servers) to inject clean Python directly into your next cell.
Installation
You can install JupyterHub-Pilot and its specific components via pip:
# Install core package
pip install jupyterhub-pilot
# Install Hub-side dependencies
pip install jupyterhub-pilot[hub]
# Install Worker-side dependencies
pip install jupyterhub-pilot[worker]
# Install AI features (for users)
pip install jupyterhub-pilot[ai]
Documentation & Full Setup Guide
For full documentation, architecture diagrams, and automated AWS EC2 deployment guides, please visit our GitHub repository:
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file jupyterhub_pilot-0.2.1.tar.gz.
File metadata
- Download URL: jupyterhub_pilot-0.2.1.tar.gz
- Upload date:
- Size: 47.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
48ed554be74a48609dcc12ebda4d719f2e57c9479ecd73d21f493280bd44789d
|
|
| MD5 |
ae83f601e2daa104047d6973b6857252
|
|
| BLAKE2b-256 |
cb6a6d06c865eccefe7bc1663854c3db21be6e93d6baf386f9c368e367fc9415
|
File details
Details for the file jupyterhub_pilot-0.2.1-py3-none-any.whl.
File metadata
- Download URL: jupyterhub_pilot-0.2.1-py3-none-any.whl
- Upload date:
- Size: 30.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.13
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
dc5d71d216fc8ea5c9c5ee8f2cbf606a5031e14929ba45ac1106b93af936abf4
|
|
| MD5 |
f55f16bc0fabaa85358194d41294d6d8
|
|
| BLAKE2b-256 |
b50fe98232a722947cfc1a7427cf195c0e73a01cfd6d4bb2f2ac74d5fb20f3cd
|