> 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/trust/what-caliber-collects.md).

# What Caliber collects

Data streams Caliber can ingest and what each one stores.

Caliber only receives data from integrations and installs **you** enable. Nothing below is collected until the matching connector or device path is turned on.

```mermaid
flowchart LR
  providers[Provider_APIs] --> caliber[Caliber]
  station[Caliber_station_plugin] --> caliber
  github[GitHub_metadata_and_notes] --> caliber
  caliber --> dash[Dashboard_and_alerts]
```

| Stream                                                                                                           | When it turns on                      | What is stored                                                                                   |
| ---------------------------------------------------------------------------------------------------------------- | ------------------------------------- | ------------------------------------------------------------------------------------------------ |
| Provider APIs (Anthropic Admin/Analytics, Cursor, OpenAI, ChatGPT, Jira, Entra, Langfuse, LangSmith, Bedrock, …) | You connect the integration           | Usage, cost, seats, issues, directory, traces as allowed by that connector                       |
| Caliber station plugin (Claude Team usage path)                                                                  | Org ingest + plugin / MDM on machines | Model, tokens, estimated cost, email/session identifiers from device usage events                |
| Caliber Analysis                                                                                                 | Bundle or Analysis plugin + org token | Redacted transcript messages (user/assistant/tool I/O) after client-side secret redaction        |
| Caliber Code + GitHub                                                                                            | Code on devices + GitHub connected    | Commit/PR metadata and AI authorship notes (`refs/notes/ai`); notes live in **your** git hosting |
| Slack                                                                                                            | Slack connected                       | Outbound alert posts and DMs only                                                                |
| Salesforce / Mixpanel / Snowflake                                                                                | Connected                             | Credentials today; deeper sync later                                                             |

## Important distinctions

* **Claude Enterprise** analytics come from Anthropic’s APIs when you connect Admin / Analytics keys.
* **Claude Team** usage analytics require the Caliber station plugin; Anthropic does not expose an org analytics API for Team.
* **Analysis transcripts are opt-in** via fleet/plugin enrollment. They are not silent capture of every app on the laptop.
* **GitHub** connect UI states Caliber does not read file contents/source through that connector.
* Company Brain (when enabled for an org) proxies to a bound knowledge upstream; it is gated and not part of every tenant’s default experience.

Details on encryption and retention: [Security and privacy](/trust/security-and-privacy.md).


---

# 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/trust/what-caliber-collects.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.