Files
hassio-addons/karakeep
2026-01-11 16:53:12 +01:00
..
2026-01-11 16:31:21 +01:00
2026-01-11 16:31:21 +01:00
2026-01-11 16:31:21 +01:00
2026-01-11 16:33:36 +01:00
2026-01-11 16:33:36 +01:00
2026-01-11 16:31:21 +01:00

Home assistant add-on: Karakeep

I maintain this and other Home Assistant add-ons in my free time: keeping up with upstream changes, HA changes, and testing on real hardware takes a lot of time (and some money). I use around 5-10 of my >110 addons so regularly I install test machines (and purchase some test services such as vpn) that I don't use myself to troubleshoot and improve the addons

If this add-on saves you time or makes your setup easier, I would be very grateful for your support!

Buy me a coffee Donate via PayPal

Addon informations

Version Ingress Arch

Codacy Badge GitHub Super-Linter Builder

Thanks to everyone having starred my repo! To star it click on the image below, then it will be on top right. Thanks!

Stargazers repo roster for @alexbelgium/hassio-addons

About

Karakeep is a bookmark-everything app with a touch of AI for the data hoarders out there. It stores content, screenshots, and metadata with search powered by Meilisearch.

This addon is based on the official Karakeep Docker image.

Configuration

Webui can be found at <your-ip>:3000.

Options

Option Type Default Description
NEXTAUTH_SECRET password Secret key for authentication (auto-generated if left blank).
NEXTAUTH_URL str Public URL used by NextAuth (optional).
DISABLE_SIGNUPS bool false Disable new account signups.
MAX_ASSET_SIZE_MB int 4 Max asset upload size.
OCR_LANGS str OCR language codes (comma-separated).
OCR_CONFIDENCE_THRESHOLD int OCR confidence threshold (0-100).
OPENAI_BASE_URL str Custom OpenAI base URL.
OPENAI_API_KEY password OpenAI API key.
OLLAMA_BASE_URL str Ollama base URL.
INFERENCE_TEXT_MODEL str Text inference model name.
INFERENCE_IMAGE_MODEL str Image inference model name.
EMBEDDING_TEXT_MODEL str Embedding model name.
INFERENCE_CONTEXT_LENGTH int Inference context length.
INFERENCE_LANG str Language used for inference.
INFERENCE_JOB_TIMEOUT_SEC int Timeout for inference jobs.
CRAWLER_DOWNLOAD_BANNER_IMAGE bool true Download banner image during crawl.
CRAWLER_STORE_SCREENSHOT bool false Store screenshot during crawl.
CRAWLER_FULL_PAGE_SCREENSHOT bool false Capture full-page screenshots.
CRAWLER_FULL_PAGE_ARCHIVE bool false Store full-page archive.
CRAWLER_JOB_TIMEOUT_SEC int Crawler job timeout.
CRAWLER_NAVIGATE_TIMEOUT_SEC int Navigation timeout.
CRAWLER_VIDEO_DOWNLOAD bool Enable video downloads.
CRAWLER_VIDEO_DOWNLOAD_MAX_SIZE int Max video size (MB).
CRAWLER_VIDEO_DOWNLOAD_TIMEOUT_SEC int Video download timeout.
CRAWLER_ENABLE_ADBLOCKER bool true Enable ad blocking in the crawler.
CHROME_EXTENSIONS_DIR str /usr/src/chrome/extensions Extensions directory for headless Chromium.
MEILI_MASTER_KEY password Meilisearch master key (auto-generated if left blank).
MEILI_ADDR str Meilisearch URL.
BROWSER_WEB_URL str Chromium remote debugging URL.
DATA_DIR str Data directory (leave default).
TZ str Etc/UTC Timezone.

Extensions for headless Chromium

This add-on loads extensions in headless Chromium with the --headless=new flag. The defaults are downloaded automatically during the image build and refreshed each time the add-on starts into /usr/src/chrome/extensions (non-persistent).

You can override the base folder with the CHROME_EXTENSIONS_DIR option to point to a host-mounted directory if you prefer to manage extensions manually. Any missing extension folder is skipped at runtime.

Custom Scripts and Environment Variables

This addon supports custom scripts and environment variables through the addon_config mapping:

Installation

The installation of this add-on is pretty straightforward and not different in comparison to installing any other Hass.io add-on.

  1. Add my Hass.io add-ons repository to your Hass.io instance. Add repository on my Home Assistant
  2. Install this add-on.
  3. Click the Save button to store your configuration.
  4. Start the add-on (secrets are auto-generated if left blank).
  5. Check the logs of the add-on to see if everything went well.
  6. Open the webUI and complete the onboarding.

Support

Create an issue on GitHub if you need support.