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

# Populating entities

> Four ways to add entities to a brain, all landing in one validated store.

There are four ways to populate a brain, and they all write through the same
validated store that honors each doc\_type's storage policy.

<Steps>
  <Step title="Manual / agent">
    Write JSON directly, or open Claude Code in the folder and let it call
    `put_entity` / `create_doc_type` over MCP.
  </Step>

  <Step title="Bulk import">
    Import a file directly, or let an agent write a batch in one call with `put_entities`.
  </Step>

  <Step title="Connectors">
    `connectors/*.py` pull from an MCP server on a `schedule`; run with
    `open-index ingest <name>` or `open-index run`.
  </Step>

  <Step title="Agent write-back">
    A Stop hook that records learnings via `put_entity` — the "continuously
    improving" loop.
  </Step>
</Steps>

## Bulk import

```bash theme={null}
open-index import issues.csv --doc-type issue --asserted-by import:jira
open-index import export.jsonl --dry-run        # validate first, write nothing
```

JSON arrays, JSONL, and CSV all work:

* Bare slugs are qualified (`checkout` → `product:checkout`).
* CSV scalars are coerced to their declared types.
* A `related_to` column takes `target|meaning` pairs separated by `;`.
* A bad row is reported and skipped — the rest still land.
* `--asserted-by` / `--confidence` attribute the whole batch once instead of per row.

## Ways to create entities

<AccordionGroup>
  <Accordion title="Manual entry / upload from the UI">
    Create a JSON object representing the entity you want to store, and add it from
    the explorer.
  </Accordion>

  <Accordion title="Through an agent over CLI / MCP">
    Talk to an agent connected to the brain; it validates and writes for you.
  </Accordion>

  <Accordion title="Webhook / API trigger">
    A script on your end pushes entities into the brain.
  </Accordion>

  <Accordion title="Recurring cron">
    A connector defined in the brain configuration runs on a schedule.
  </Accordion>
</AccordionGroup>

## Distilling from unstructured documents

To extract or distill information from unstructured documents into entities:

* **Git repo knowledge bases** — connect an agent to the brain via an MCP server and
  prompt it to extract information from the repo.
* **Commercial tools** (Notion, Confluence, …) — connect an agent to both the brain
  (via MCP) and the source tool (via MCP server / CLI).
* **Scripted** — use a script that connects to the brain via an API and extracts
  information from documents.

<Tip>
  For distilled knowledge from an existing knowledge base, the recommendation is to
  connect that source's MCP server to a Claude Code instance also connected to the brain.
</Tip>

## Next

Read [Entity management](/guides/entity-management) for guidance on cadence, scale,
and decay — the difference between a brain that stays sharp and one that fills with
noise.