> For the complete documentation index, see [llms.txt](https://docs.trycaliber.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.trycaliber.ai/caliber-station-plugin.md).

# Caliber station plugin

What the Caliber station plugin and bundle are, what they unlock, and how to deploy them.

The **Caliber station plugin** is how Caliber runs on people’s machines. The fleet installer (the **Caliber bundle**) deploys Caliber Code and Caliber Analysis together so your org gets attribution, optional transcript governance, and (for **Claude Team** licenses) the usage analytics Anthropic’s APIs do not expose.

## What it is

| Component            | What it does                                                                                                 |
| -------------------- | ------------------------------------------------------------------------------------------------------------ |
| **Caliber Code**     | Writes AI authorship notes to `refs/notes/ai` in your repos (no Caliber credentials on the laptop for notes) |
| **Caliber Analysis** | Claude Code plugin that ships **redacted** transcripts to Caliber for enrolled users                         |

One org-scoped ingest token from **Settings → Integrations → Caliber Analysis (MDM)** drives Analysis enrollment. Caliber Code does not need that token.

## What it gives you

* **Line-level AI code attribution** when GitHub is connected (percent AI-assisted)
* **Redacted transcript / governance signals** for enrolled users
* **Claude Team analytics path**: when you are on Claude Team (no Anthropic org analytics API), the station plugin is how Caliber collects the usage analytics you need

## Capabilities unlocked after deploy

| Capability                         | Needs                                                                                                                                  |
| ---------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------- |
| Percent AI-assisted on code        | Caliber Code on machines + [GitHub](/connect-your-providers/github.md)                                                                 |
| Analysis / transcript surfaces     | Caliber Analysis enrolled (bundle or self-serve)                                                                                       |
| Claude Team usage coverage on Home | Station plugin installed broadly enough for your fleet                                                                                 |
| Claude Enterprise API analytics    | Separate: [Anthropic (Claude)](/connect-your-providers/anthropic-claude.md) API keys (station plugin still useful for Code + Analysis) |

## How to deploy

1. Read [What the bundle includes](/caliber-station-plugin/what-the-bundle-includes.md).
2. Prefer fleet rollout: [Deploy with MDM](/caliber-station-plugin/deploy-with-mdm.md) (Jamf, Kandji, Intune).
3. Or start smaller: [Self-serve install](/caliber-station-plugin/self-serve-install.md).

Live public MDM guide (also in-app): <https://app.trycaliber.ai/docs/mdm-bundle>

{% hint style="danger" %}
Run installers as the **signed-in user**, not as root. Identity and Claude login context break when the wrong user runs the script.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.trycaliber.ai/caliber-station-plugin.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.