7,363 open-source and SaaS tools, with GitHub stats refreshed every day.

Marginalia Search

Open source

Experimental search engine and crawler focused on text-oriented, small, and independent websites, which can run on modest hardware or as a white-label engine.

marginalia-search.com
Marginalia Search homepage screenshot
GitHub stars
2.2k
Last commit
yesterday
Repository age
3 years
Version
v24.10.0
Licence
Custom
Self-hosted
Yes

About Marginalia Search

Marginalia Search is the source code of an independent internet search engine that indexes the small, old, and unusual parts of the web. The project describes itself as an experimental workshop as much as a public service, developing alternative ways to discover content and elevating the more human, non-commercial side of the Internet. It is written in Java, and the input lists its license only as other.

A side goal is to run the operation on affordable hardware with minimal operational overhead instead of datacenters. The system can run as a copy of Marginalia itself or as a white-label search engine over your own data, whether crawled or side-loaded, though its logic is not yet very configurable and reflects the project's goals. Setup uses run/setup.sh to download supplementary model data, and a local test environment is described in the repository.

The long-term plan is to be funded through grants, donations, and commercial API licenses, while non-commercial share-alike use remains free. Documentation is at docs.marginalia.nu and a public instance runs at marginalia-search.com. It suits people who value the small web and developers curious about building a search engine.

Key features

  • Search index of small, text-focused websites
  • Custom crawler and indexer
  • Runs on affordable hardware
  • White-label mode for your own data
  • Public instance at marginalia-search.com
  • Open documentation and setup scripts

Good fit for

  • →Discovering independent, non-commercial sites
  • →Running a custom search engine over your own crawl
Built with
Java
Tags
search-engine
small-web
crawler
indexer
java
self-hostable
independent
open-source

Marginalia Search: questions and answers

What is Marginalia Search used for?
Marginalia Search is an experimental search engine and crawler focused on text-oriented, small, and independent websites, which can run on modest hardware or as a white-label engine. It is a good fit for discovering independent, non-commercial sites; and running a custom search engine over your own crawl.
Is Marginalia Search open source?
Yes. Marginalia Search is open source under a custom licence. Its source code is on GitHub at MarginaliaSearch/MarginaliaSearch and is written mainly in Java.
Is Marginalia Search free?
Yes. Marginalia Search is open source, so the software itself is free to use under the terms of its own licence. A managed cloud version is also available.
Can I self-host Marginalia Search?
Yes. Marginalia Search can be self-hosted on your own server or infrastructure.
What is Marginalia Search an alternative to?
Marginalia Search is an open-source alternative to Mojeek, Brave Search, Kagi and Google Search. Other open-source alternatives to Mojeek include Mwmbl and YaCy.
Is Marginalia Search actively maintained?
Yes. The most recent commit to Marginalia Search was on 1 October 2026, and the latest release is v24.10.0, published on 14 October 2024. The project has 2.2k stars on GitHub.

Open-source alternatives to Marginalia Search

See all

SaaS alternatives to Marginalia Search

See all