Quickstart

Install Tau, connect a model, and run your first coding session.

This page takes you from nothing to your first Tau session. It should take a few minutes.

1. Install Tau

Tau is a Python tool requiring Python 3.12 or newer. Its installer uses uv to create an isolated environment and installs uv first when it is not already available.

On macOS or Linux, run:

curl -LsSf https://twotimespi.dev/install.sh | sh

On Windows, run in PowerShell:

irm https://twotimespi.dev/install.ps1 | iex

The installer announces before installing uv, never uses sudo, verifies the installed tau command, and tells you if you need to restart your shell for a PATH update. To review code before executing it, download and inspect install.sh or install.ps1 first.

Check it worked:

tau --version

Upgrade Tau

For a normal install, let Tau detect and reuse the installer that owns its environment:

tau update

Tau reuses uv or pipx when their environment receipt is present. For uv tools, it installs the latest stable version explicitly so an older version pin cannot block the update. For ordinary Python installs, standard package metadata tells Tau whether to use uv or pip, and Tau targets the exact Python environment running it. It stops instead of switching installers for editable, direct-URL, Conda/Pixi, or unrecognized installations.

If you installed a local checkout with uv tool install --editable ., run the install command again after pulling changes:

uv tool install --editable --force .

Editable installs expose source changes immediately, but installed package metadata (including the version), dependencies, and entry points are refreshed only when uv reinstalls the tool.

2. Connect a model

Tau needs an AI model to talk to. A provider is the service that hosts the model (OpenAI, Anthropic, …). Start Tau and use /login to connect one:

tau

Then run one of these inside Tau:

/login              # choose a provider
/login openai       # save an OpenAI API key
/login openai-codex # authenticate a Codex/ChatGPT subscription

Tau ships with built-in entries for OpenAI, Anthropic, OpenAI Codex, OpenRouter, and Hugging Face. See Providers & models for switching models or adding a custom/local OpenAI-compatible endpoint.

3. Start a session

Run Tau from inside the project you want to work on:

cd my-project
tau

This opens the interactive terminal UI. Type a request and press Enter:

explain what this project does

Tau streams its response, and when it needs to, it reads files and runs commands to answer you. Try something that changes code:

add a docstring to every function in src/utils.py

You’ll see each tool call (read, edit, bash) as it happens.

4. Come back later

Tau saves every session. List them:

tau sessions

Resume the most recent one for this directory, or pick from a list:

tau --session <session-id>

…or open the picker inside the TUI with /resume. See Sessions for resuming, branching, and exporting.

One-shot mode

Don’t need the UI? Run a single prompt and get the result on stdout — handy for scripts and pipes:

tau -p "summarize the changes in the last commit"

More in Print mode & scripting.

Where to go next

• Core concepts — understand what’s actually happening.
• The interactive session — get fluent in the TUI.
• Providers & models — switch models, add providers, use local models.