> ## Documentation Index
> Fetch the complete documentation index at: https://docs.userjourneys.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# CLI

> Install uj, sign in, and set the project every study command needs.

`uj` is the UserJourneys command-line interface: a thin client over the same MCP tools the AI assistants use. It is built for people at a terminal and for agents that shell out to it, so every command keeps its result on stdout and everything else (progress, guides, errors) on stderr.

## Install

```bash Install theme={null}
curl -fsSL https://app.userjourneys.ai/install/uj | sh
```

`uj upgrade` replaces the binary in place; `uj version` prints the installed version.

## Sign in

```bash Sign in theme={null}
uj auth login
```

The browser opens for OAuth and the CLI stores a token locally. `uj auth status` shows who you are signed in as; `uj auth logout` forgets the token.

## Project scope

Every study, interview and analytics command runs against one project. Pick a default once, or pass it on each call:

```bash Choose a project theme={null}
uj project list
uj project set "Acme"
uj studies --project "Acme"
```

Precedence is `--project <name|id>`, then the `UJ_PROJECT` environment variable, then the stored default.

## Next

[Study Manager commands](/cli/study-manager) covers `uj studies`: triage your studies, read a study and its ledger, list what changed, and message the study's agent. `uj help <command>` prints the same page offline.