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

# Context

> context add, list, remove: ingesting files as searchable context

## context add

```bash theme={null}
memloom context add <path...>
```

Ingest files or folders as searchable context (`.md .txt .pdf`; folders recurse). Chunks are
embedded into the same recall as memories, and each chunk carries its breadcrumb (file,
heading path, PDF page), so results always say where they came from.

Documents are mirrors of the files they came from:

* Re-adding an unchanged file is a no-op.
* A changed file replaces its chunks.
* When memloom's extraction pipeline improves, the pipeline version bumps and `context add`
  re-ingests files whose bytes didn't change.

<Note>
  A file can enter memloom two ways: linked from disk (this command, stays in sync on re-add)
  or uploaded as a snapshot (the viewer's upload). Linking is the stronger identity: linking a
  file that was previously uploaded absorbs the upload into the link, and uploading a file
  that is already linked is refused with a pointer to the existing document.
</Note>

## context list

```bash theme={null}
memloom context list
```

List ingested documents with their ids and chunk counts.

## context remove

```bash theme={null}
memloom context remove <id>
```

Delete a document and its chunks from the store. The file on disk is untouched.