nteract

Free plan LinuxMacSelf-hostedWindows

What nteract is

nteract is a free, local notebook environment for working with Jupyter notebooks and AI agents. Its desktop app includes the notebook, the runt CLI and the runtimed daemon, and is available for Linux, macOS and Windows. A per-user headless installer for Linux and macOS sets up the app, CLI, daemon and user service without root access. The app detects project environments from pyproject.toml, pixi.toml and environment.yml, and supports uv, conda and pixi. Dependencies can be recorded in notebook metadata, but users must approve their installation. For agent workflows, the CLI and MCP server can create and manage notebooks, run code, read outputs and handle dependencies; setup instructions cover Claude Code and Codex. People and agents can work in the same live notebook with persistent Python sessions. Additional tools include an interactive DataFrame explorer, structured tracebacks linked to the cell that raised an error, and an outline for navigating long notebooks. Notebook files, outputs and environments remain on the user's filesystem, and no account is required.

Who it suits

nteract suits people who work with Jupyter notebooks locally, including those who want AI assistants to run code or manage notebook content. Its headless installer is an option for Linux and macOS users who need a per-user setup without root access.

What it does well

Free, with no account required
Desktop app supports Linux, macOS and Windows
CLI and MCP server support notebook and code operations
Dependencies require approval before installation
Notebook files and outputs stay on the user's filesystem

What to know first

Headless installer is offered for Linux and macOS
Anonymous daily telemetry is enabled unless disabled

Getting started

Visit https://www.nteract.io/
Choose the desktop app for Linux, macOS, or Windows, or the headless installer for Linux or macOS
Open a Jupyter notebook in the desktop app
Use the CLI or MCP server for agent workflows, following the setup guidance for Claude Code or Codex
Select a project environment or configure dependencies in notebook metadata, approving installation when prompted

Verdict

nteract brings local notebook work and agent workflows together, with user approval for dependency installation and no account requirement. Its telemetry can be turned off, though users should know raw pings are retained for 400 days.

Questions

How much does nteract cost?

nteract is free and has a free plan.

Which platforms does it support?

The desktop app is available for Linux, macOS, and Windows. A per-user headless installer is offered for Linux and macOS.

Does nteract require an account?

No account is required. Notebooks, outputs, and environments are stored on the user's filesystem.

Can AI agents work with nteract?

Yes. Its CLI and MCP server support creating and managing notebooks, running code, reading and writing cells, and managing dependencies. Setup guidance is provided for Claude Code and Codex.

Which notebook format does it support?

The listed notebook format is Jupyter Notebook (.ipynb).

Can nteract install notebook dependencies automatically?

Dependencies can be stored in notebook metadata, and nteract requires approval before installing them.

Facts from nteract's own pages

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. · nteract.io, 5 Oct 2026
Data exploration: The product offers an interactive DataFrame explorer with crossfiltering for Python data including pandas, polars, datasets, narwhals, and duckdb. · nteract.io, 5 Oct 2026
Desktop app: The desktop app bundles the notebook, the runt CLI, and the runtimed daemon, and is available for macOS, Windows, and Linux. · nteract.io, 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. · nteract.io, 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. · nteract.io, 4 Oct 2026
Maintainer: The telemetry page says nteract is maintained under NumFOCUS, a nonprofit, and is a NumFOCUS sponsored project. · nteract.io, 4 Oct 2026
Markdown and TeX: nteract 2.6 added improved Markdown rendering and renders bare TeX environments as math. · nteract.io, 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. · github.com, 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. · github.com, 4 Oct 2026
Notable limit: The installer page documents stable and nightly channels, with nightly installed side-by-side using channel-suffixed commands. · nteract.io, 5 Oct 2026
Notebook dependencies: Users can store dependencies in notebook metadata, and nteract requires approval before installing them. · nteract.io, 4 Oct 2026
Notebook editing: Users can navigate long notebooks with a live outline and manage packages from a left rail. · nteract.io, 5 Oct 2026
Notebook workflows: The desktop app opens Jupyter notebooks and includes the notebook, the runt CLI, and the runtimed daemon. · nteract.io, 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. · nteract.io, 4 Oct 2026
Package safety: nteract says it checks for typosquatting in popular PyPI packages and warns users about suspected package typos. · nteract.io, 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. · github.com, 5 Oct 2026
Runtime environments: nteract detects project environments from pyproject.toml, pixi.toml, and environment.yml, and supports uv, conda, and pixi. · nteract.io, 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. · nteract.io, 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. · nteract.io, 5 Oct 2026
Telemetry retention: The telemetry page says raw pings are retained for 400 days and daily aggregate counts are retained indefinitely. · nteract.io, 5 Oct 2026
Tracebacks: Python errors can render as structured, navigable tracebacks that link to the cell that raised the error. · nteract.io, 5 Oct 2026

Where nteract stands on Freedom251

Notebook Software#17 of 25