nteract
nteract is a free local notebook environment for Jupyter workflows involving people and AI agents.
What nteract is
nteract is a free local notebook environment for Jupyter workflows involving people and AI agents. Its desktop app opens notebooks and bundles the notebook interface, runt CLI, and runtimed daemon for macOS, Windows, and Linux. It detects project environments from pyproject.toml, pixi.toml, and environment.yml and supports uv, conda, and pixi. Dependencies can be stored in notebook metadata, with approval required before installation. The CLI and MCP server let agents create and manage notebooks, run code, read outputs, and manage dependencies; setup instructions cover Claude Code and Codex. Persistent Python sessions and shared live notebooks support collaboration. nteract includes a DataFrame explorer for Python data, navigable tracebacks, a live notebook outline, and secret-looking environment-value redaction. Notebooks, outputs, and environments remain on the user’s filesystem, and no account is required. Anonymous daily telemetry can be disabled. The headless installer works per user on Linux and macOS without root access.
Good
- Free local notebook environment
- Desktop support for three operating systems
- CLI and MCP agent workflows
- Interactive DataFrame explorer
- No account required; files stay local
Watch out
- Telemetry raw pings retained 400 days
- Nightly channel installs side-by-side
- Notebook dependency installation requires approval
- Execution is local
Who it suits
nteract suits developers, data practitioners, and AI-agent users who want local Jupyter notebooks with Python workflows and collaboration. It supports macOS, Windows, Linux, and headless Linux or macOS setups.
Verdict
nteract combines a native Jupyter workspace with agent tooling, environment detection, collaboration, and data exploration. Its local storage and no-account model suit users who prefer filesystem-based notebooks.
The facts
Each one read from nteract's own pages, with the date it was checked.
What it does
- Agent integrations
- The official agent setup describes plugins for Claude Code and Codex that provide notebook-backed Python sessions with persistent variables and rich outputs.checked 5 Oct 2026
- Data exploration
- The product offers an interactive DataFrame explorer with crossfiltering for Python data including pandas, polars, datasets, narwhals, and duckdb.checked 5 Oct 2026
- Headless installation
- A per-user headless installer is offered for Linux and macOS and sets up the app, CLI, daemon, and a user service without root access.checked 5 Oct 2026
- Local data
- The security page says notebooks, outputs, and environments live on the user's filesystem and that no account is required.checked 4 Oct 2026
- Maintainer
- The telemetry page says nteract is maintained under NumFOCUS, a nonprofit, and is a NumFOCUS sponsored project.checked 4 Oct 2026
- Markdown and TeX
- nteract 2.6 added improved Markdown rendering and renders bare TeX environments as math.checked 5 Oct 2026
- MCP
- The nteract MCP server lets AI assistants run code, read and write cells, manage dependencies, and work with people on the same live notebook.checked 5 Oct 2026
- MCP and CLI
- The nteract CLI and MCP server let agents create and manage notebooks, run code, read outputs, and manage dependencies.checked 4 Oct 2026
- Notable limit
- The installer page documents stable and nightly channels, with nightly installed side-by-side using channel-suffixed commands.checked 5 Oct 2026
- Notebook dependencies
- Users can store dependencies in notebook metadata, and nteract requires approval before installing them.checked 4 Oct 2026
- Notebook editing
- Users can navigate long notebooks with a live outline and manage packages from a left rail.checked 5 Oct 2026
- Notebook workflows
- The desktop app opens Jupyter notebooks and includes the notebook, the runt CLI, and the runtimed daemon.checked 4 Oct 2026
- Output isolation
- The security page says notebook outputs render in an opaque-origin iframe that cannot access the parent app's DOM, localStorage, or Tauri APIs.checked 4 Oct 2026
- Package safety
- nteract says it checks for typosquatting in popular PyPI packages and warns users about suspected package typos.checked 4 Oct 2026
- Product
- nteract describes itself as a local-first notebook environment where people, kernels, and AI agents can work with the same live document.checked 5 Oct 2026
- Runtime environments
- nteract detects project environments from pyproject.toml, pixi.toml, and environment.yml, and supports uv, conda, and pixi.checked 4 Oct 2026
- Secret redaction
- nteract can scrub secret-looking environment values from outputs before they are written to disk or shown to an agent, and this feature can be disabled in settings.checked 5 Oct 2026
- Telemetry
- The maker says telemetry is an anonymous daily heartbeat with six build-related fields, can be disabled, and does not include notebook contents or cell outputs.checked 5 Oct 2026
- Telemetry retention
- The telemetry page says raw pings are retained for 400 days and daily aggregate counts are retained indefinitely.checked 5 Oct 2026
- Tracebacks
- Python errors can render as structured, navigable tracebacks that link to the cell that raised the error.checked 5 Oct 2026
Where it runs
- Desktop app
- The desktop app bundles the notebook, the runt CLI, and the runtimed daemon, and is available for macOS, Windows, and Linux.checked 5 Oct 2026
Alternatives to nteract
- 1
Paperspace Notebooks
Free planWebAPILinuxmacOS7.7From $8 a month - 2
Pluto.jl
Free planOpen sourceAndroidWebAPILinux7.7Free plan - 3
Datalore
Free planWebAPILinuxSelf-hosted7.6From $29.17 a month - 4
Google Colab
Free planWebAPIExtensionSelf-hosted7.6Free plan - 5
JupyterLab
Free planOpen sourceWebAPILinuxmacOS7.6Free plan - 6
Deepnote
Free planWebAPIExtensionLinux7.2From $3,920 a month