# Hive documentation

Hive runs multi-step work as a **folder-as-agent pipeline**: each task moves
through stage folders, an AI agent does the work at each stage, and a daemon
advances it in the background, asking for answers only when it needs them. Its
flagship **`coding`** workflow turns a rough idea into a merge-ready pull
request — but `coding` is one of several workflows. Hive also ships `content`
(research) and lets you author your own. These docs cover installing it, the
ideas behind it, configuring it, the command surface, and running it as a
service.

## Start here

- **[Getting started](https://hivecli.sh/docs/getting-started/)** — install, `hive init`, and your first task in the TUI.
- **[Concepts](https://hivecli.sh/docs/concepts/)** — folder-as-agent, the stage state machine, and the marker protocol.
- **[Configuration](https://hivecli.sh/docs/configuration/)** — project config, patrol mode, reviewers, agent profiles, and the daemon.
- **[Command reference](https://hivecli.sh/docs/commands/)** — every user-facing `hive` command.
- **[Custom workflows](https://hivecli.sh/docs/custom-workflows/)** — the engine is generic: author your own per-project pipeline in YAML.
- **[Operating](https://hivecli.sh/docs/operating/)** — daemon, bot, and babysitter as services.

## Looking for the source?

Hive is open source (MIT) on [GitHub](https://github.com/ivankuznetsov/hive).
The full engineering wiki lives in the repo; these docs are the curated,
user-facing subset.

## Workflows from private repositories

See [Installing private workflows](/docs/private-workflows/) for repository
access, Git authentication, exact-revision imports and runtime setup. This
feature is unreleased; the guide explains how to check CLI availability.