---
title: "Quickstart"
description: "Use when you want the shortest path from nothing to a first cited answer, with one book added and your agent reading it."
url: https://docs.heytrove.ai/quickstart
updated: 2026-10-06
---

# Quickstart

> Load this page when: you are setting up Trove for the first time and want to see a cited answer working

## For agents

- Confirm sign-in with `trove auth whoami` before any other command.
- Add a book with `trove items add <file>`, then wait with `trove items status <id> --wait`.
- If `trove` is not found, open a new terminal or run `source ~/.trove/env.sh`.

You can go from [install](https://docs.heytrove.ai/install.md) to a cited answer in a few steps. You need a terminal, a coding agent and one PDF, EPUB or Markdown file.

## Install and sign in

1. Run the installer in your terminal. It downloads `trove`, adds it to your PATH and opens browser sign-in.
2. Sign in in the browser window.

```terminal
curl -fsSL https://heytrove.ai/install.sh | sh
```

You do these two steps one time. After that, you tell your agent what to do, and your agent runs Trove.

## Add your first book

Start a new session in your coding agent (Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI or Grok). Ask it to add your file:

```text
Add ./book.pdf to my Trove library and tell me when it is ready.
```

The agent adds the file, waits until Trove has processed it, and tells you the title and the status.

No file to hand? Ask your agent for a [marketplace book](https://docs.heytrove.ai/concepts/marketplace.md) instead. The agent adds a book only when you say yes, and the book then becomes an item in your [library](https://docs.heytrove.ai/concepts/library-and-books.md).

```text
Find a book about Postgres in the Trove marketplace and add it to my library if I say yes.
```

## Ask your first cited question

In the same session, ask: "Search my Trove library for what my books say about connection pooling." Your agent starts the [librarian](https://docs.heytrove.ai/subagents/librarian.md), which picks the books and pages. The librarian starts the [readers](https://docs.heytrove.ai/subagents/item-reader.md), and they open the listed pages. You get an answer with [citations](https://docs.heytrove.ai/concepts/citations.md) such as (*Title*, pp. 10-12), followed by a Trove box that summarizes what was read.

## Ask explicitly when the answer matters

The most reliable way to get knowledge from Trove today is to tell your agent to search your library. For example: "Search my Trove library for how we handle retries." That starts the librarian. The librarian picks the books and pages, and it starts the readers on its own. You do not start readers yourself.

Trove also has automatic checks. They run while your agent plans and before non-trivial coding ([Auto mode and plan mode](https://docs.heytrove.ai/concepts/plan-and-auto-mode.md)). We are working to make the librarian start automatically and reliably. For now, do not rely on it. When the answer matters, ask explicitly.

To see the setting, ask your agent: "Check that Trove Auto mode is on." If it is off, the agent turns it on and tells you to start a new session. See [Plan mode and auto mode](https://docs.heytrove.ai/concepts/plan-and-auto-mode.md).

Want your agent to follow Trove best practices? Ask it: "Read How to Use Trove in my Trove library and follow it."

## Check it worked

| Symptom | Fix |
| --- | --- |
| `trove: command not found` | Open a new terminal, or run `source ~/.trove/env.sh`. |
| Not signed in | Run `trove auth login`. To check which account you use, run `trove auth whoami`. |
| A book is stuck processing | Ask your agent: "Check the status of my new Trove book." If it failed, ask your agent to reprocess the book. |
| The agent does not consult Trove | Ask it explicitly to search your Trove library. If it still does not, run `trove setup --status`, then start a new session. |

## Direct CLI

Your agent runs these through the `trove` command. You can run them yourself in a terminal, but asking your agent is the recommended way: it picks the right flags, waits for processing and checks the result.

| Task | Command |
| --- | --- |
| Check who you are signed in as | `trove auth whoami` |
| Add a file | `trove items add ./book.pdf` |
| Wait for processing | `trove items status <id> --wait` |
| List your books | `trove items list` |
| Search the marketplace | `trove marketplace browse --search "postgres"` |
| Add a marketplace book | `trove marketplace subscribe <listing-id>` |
| Check the Auto mode setting | `trove config get skill.planMode` |
| Turn Auto mode on | `trove config set skill.planMode always` |

See the [CLI reference](https://docs.heytrove.ai/reference/cli.md).

## Next

- [Set up your library](https://docs.heytrove.ai/usage/set-up-your-library.md) fills a new library fast: turn your existing skills into books, then add marketplace books.
- [Best practices](https://docs.heytrove.ai/best-practices.md) says what to add, what to keep out, and how to keep answers trustworthy.
- [How Trove works](https://docs.heytrove.ai/how-trove-works.md) explains what happens between your question and the answer.
- [Usage](https://docs.heytrove.ai/usage.md) has step-by-step guides for common jobs.
- [Concepts](https://docs.heytrove.ai/concepts.md) covers libraries, shelves, manuscripts and the rest.
