jupyter-ai-magics
Jupyter AI magics Python package. Not published on NPM.
Decision gist · record as of 2026-08-14
Yes, if you use JupyterLab and want to integrate AI agents into your notebooks. The package is actively maintained, has low install friction, carries a permissive BSD license, and supports current Python versions (3.9–3.12). It has no known vulnerabilities and offers genuine value for collaborative AI-assisted development. Install it alongside your chosen agent provider (langchain-community includes many options) to get started.AI-flagged interpretation of the facts on this page — verify before relying
Before you install
- Requires JupyterLab to be installed and running; agents are auto-detected only when their dependencies (e.g., langchain-community providers) are also installed.
- Low install friction with a pure Python wheel distribution.
- The package is actively maintained with recent commits and sits in the top 15000 PyPI packages by download volume, indicating established adoption.
License · maintenance · safety
permissive license (permissive) — BSD 3-Clause License permits commercial and private use with minimal restrictions; you must retain copyright notices and disclaimers in source and binary distributions.
last release 2025-11-25 (262 days) · last repo commit 2026-08-14 · 4,370 stars
0 known vulnerabilities (OSV.dev, 2026-08-14) · 126,245 downloads/mo, #11,784 on PyPI
Alternatives
Verify before relying
pip install jupyter-ai-magics
from jupyter_ai_magics import register_magics
register_magics()- Whether the package works with JupyterLab versions prior to a specific release.
- Performance characteristics when running multiple concurrent agent chats.
- Whether custom MCP servers require additional system dependencies beyond Python packages.
What it is and what it does
Jupyter AI Magics is a JupyterLab extension that brings agentic AI capabilities directly into computational notebooks. It provides a native chat interface where you can interact with frontier AI agents—including Claude, Codex, GitHub Copilot, Gemini, and others—all integrated through the Agent Client Protocol. Agents are automatically detected when their dependencies are installed, so setup is as simple as installing Jupyter AI and your chosen agent.
The extension gives agents the ability to read and write files, run terminal commands, and interact with notebooks through a built-in Jupyter MCP server. A permission system lets you control agent actions—agents request approval before writing files or executing commands. You can create multiple concurrent chats, drag and drop files or notebook cells as context, and collaborate in real time with other users on the same server. The design emphasizes flexibility and extensibility: you can add custom MCP servers to give agents domain-specific tools and resources, and developers can build custom AI personas using entry points.
Use it for
- Collaborate with AI agents to write, debug, and refactor code directly in notebooks without leaving your development environment.
- Use agents to analyze data and generate insights by giving them access to notebook cells and files through the MCP protocol.
- Build domain-specific AI assistants by registering custom MCP servers that expose specialized tools and resources to agents.
- Pair-program with frontier AI models in real time while maintaining control over file writes and command execution via the permission system.
- Integrate multiple AI agents into a single notebook session for comparative analysis or specialized task delegation.
Worth the install?
AI-flagged interpretation of the facts on this page. Verify before relying on it.
Yes, if you use JupyterLab and want to integrate AI agents into your notebooks.
The package is actively maintained, has low install friction, carries a permissive BSD license, and supports current Python versions (3.9–3.12). It has no known vulnerabilities and offers genuine value for collaborative AI-assisted development. Install it alongside your chosen agent provider (langchain-community includes many options) to get started.
Install
jupyter-ai-magics on PyPI
Before you install
Low install friction with a pure Python wheel distribution. The package is actively maintained with recent commits and sits in the top 15000 PyPI packages by download volume, indicating established adoption.
Requires JupyterLab to be installed and running; agents are auto-detected only when their dependencies (e.g., langchain-community providers) are also installed.
License in practice
BSD 3-Clause License permits commercial and private use with minimal restrictions; you must retain copyright notices and disclaimers in source and binary distributions.
Quickstart
pip install jupyter-ai-magics
from jupyter_ai_magics import register_magics
register_magics()Verify before relying
- Whether the package works with JupyterLab versions prior to a specific release.
- Performance characteristics when running multiple concurrent agent chats.
- Whether custom MCP servers require additional system dependencies beyond Python packages.
Package facts
| License | permissive license permissive |
| Python support | Supports the current Python release >=3.9 |
| Install friction | Low. Pure-Python wheel |
| Runtime dependencies | 7 packagesclickimportlib-metadataipythonjsonpath-nglangchain-communitylangchainpydantic |
| Maintenance | Actively maintained 262 days since the last release |
| Last repo commit | |
| First released | |
| Downloads | 126,245 / month, #11,784 on PyPI 30-day window, as of 2026-08-14 |
| Known vulnerabilities | None known OSV.dev, checked 2026-08-14 |
| Classifiers | Framework :: JupyterLicense :: OSI Approved :: BSD LicenseProgramming Language :: PythonProgramming Language :: Python :: 3Programming Language :: Python :: 3.10Programming Language :: Python :: 3.11Programming Language :: Python :: 3.12Programming Language :: Python :: 3.9 |
Evidence: jupyter_ai_magics-2.31.7-py3-none-any.whl
Tags
Let your AI agent find packages like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 14,416 PyPI packages by what they can do, searchable in plain language.
wish › “claude copilot in jupyter”
- jupyter-ai-magicsJupyter AI Magics provides a JupyterLab extension that integrates AI…
- jupyter-ai-acp-clientProvides a JupyterLab extension that integrates Agent Client Protocol…
- detect_agentDetects whether code is running in an AI agent or automated…
Give your agent the search over MCP, or paste the wish link into any chat.
More Artificial Intelligence packages
LiteLLM provides a unified Python interface to call 100+ LLM providers (OpenAI, Anthropic, Gemini, Bedrock, Azure, and others) using OpenAI-compatible API format, available as both a Python SDK and a self-hosted AI Gateway proxy server.
Install it if you need to work with multiple LLM providers or want to centralize LLM routing in your organization.
Client library and CLI tool for downloading, uploading, and managing models, datasets, and repositories on the Hugging Face Hub platform.
Install it if you work with Hugging Face Hub models or datasets.
LangChain provides a framework for building agents and LLM-powered applications by composing language models, tools, and memory through a unified API that abstracts over multiple model providers.
hf-xet provides chunk-based deduplication and efficient file transfer for the Hugging Face Hub, enabling faster uploads and downloads of large files with local disk caching.
Tokenizers converts raw text into token sequences for NLP models, with support for training custom vocabularies and using pre-built tokenizers (BPE, WordPiece) optimized for speed via Rust.
Transformers provides a unified framework for loading, fine-tuning, and running state-of-the-art pretrained models across text, vision, audio, video, and multimodal tasks using PyTorch, JAX, or TensorFlow.
Install it if you need to run or train any transformer-based model for NLP, vision, audio, or multimodal tasks.
See also jupyter-ai · jupyter-ai-acp-client · jupyter-ai-tools · emr-notebooks-magics · jupyterlab-commands-toolkit · jupyter-mcp-tools · jupyter-mcp-server · jupyter-ai-chat-commands · microsoft-agents-copilotstudio-client · jupyter-server-mcp