What is Tine?
Tine is an AI notebook runtime that lets developers run, branch, and share data experiments with AI agents in a single local workspace. Built for data scientists and developers who work with AI agents, Tine replaces linear notebooks with a tree-native model: each experiment contains branches, and each branch contains cells, so you can explore multiple approaches in parallel without overwriting prior work.
The runtime is written in Rust and runs entirely on your machine, starting a local server at http://127.0.0.1:9473 that both your browser UI and any connected AI agent share simultaneously. Because the Web UI and agent always see the same state, logs, and outputs, there is no sync lag between what you see and what the agent executes. This makes Tine a practical AI notebook for developers who want a deterministic, reproducible experimentation environment rather than a cloud-hosted black box.
Tine is MCP-native out of the box. You can connect it to VS Code, Cursor, or Claude as an agent host by running a single command — tine mcp register --host vscode — which writes the configuration directly into your host's standard config location. The tool is open source under the Apache 2.0 license and installable via pip install tine or a signed desktop bundle (.dmg for macOS, .msi for Windows) that ships with its own private Python runtime, removing any system Python dependency.
What is Tine used for?
Tine is used for running branching data science and AI experiments locally, with native MCP support that lets AI agents connect to the same runtime as the developer's notebook UI. It is also used to build reproducible, parallel experiment workflows without relying on cloud-based notebook services.
How much does Tine cost?
Open Source
Fully free and open source under the Apache 2.0 license. Install via pip or download the signed desktop app for macOS or Windows.
Pros and cons
Pros
- Branching notebook model lets you run multiple experiment paths in parallel without overwriting earlier results
- MCP-native: one command registers Tine as a tool server in VS Code, Cursor, or Claude
- Local-first Rust runtime — no cloud dependency, sub-second response times for notebook execution
- Desktop bundle ships with a private Python runtime, so no system Python install is required
- Open source under Apache 2.0 — self-hostable with no vendor lock-in
Cons
- Early-stage project (version 0.2.x) with a small community (7 GitHub stars)
- No cloud-hosted option — requires local installation via pip or desktop app
- No collaborative multi-user mode documented
- Windows support is x86_64 only; no ARM Windows build available
Questions about Tine
What is Tine used for?
Tine is used for running data science and AI experiments in a branching notebook environment. Developers and data scientists use it to explore multiple experiment paths in parallel on a fast local runtime that AI agents can also connect to via MCP. It is particularly suited to workflows where an AI agent and a human need to share the same execution context.
Is Tine free?
Yes, Tine is completely free and open source under the Apache 2.0 license. You can install it with pip install tine or download a signed desktop app for macOS or Windows. There is no paid tier or subscription — the full feature set is available at no cost.
How does Tine work?
Tine starts a local server on your machine (default port 9473) that serves both a browser-based notebook UI and an MCP API endpoint. Notebooks are organized as experiments containing branches, each with their own cells. Because both the UI and any connected AI agent share the same local runtime, they always see identical state, logs, and outputs in real time.
How do I connect Tine to an AI agent like Claude or VS Code Copilot?
Tine is MCP-native. After starting the local server, run tine mcp register --host claude (or --host vscode or --host cursor) to write the MCP configuration directly into your agent host's standard config file. The desktop app also shows an MCP port button in the title bar that copies the correct connection command.
What makes Tine different from Jupyter Notebook?
Unlike Jupyter, Tine uses a tree-native branching model rather than a single linear notebook. Each experiment can have multiple parallel branches, so you can test different hypotheses side by side without duplicating files. Tine is also built in Rust for a faster local runtime and is designed from the ground up to connect AI agents via MCP.
What are the best alternatives to Tine?
Reviews
Sign in to rate and review Tine.
Sign in to reviewNo reviews yet. Be the first to review Tine!