Gorse review
A self-hosted recommender with multiple methods, a REST API and no license cost.
Reviewed by iTechGuides Editors · Editorial team · Updated Oct 2026
Gorse is an open-source recommender system engine written in Go for teams integrating recommendations into online services. Applications import users, items and interaction data; Gorse trains models and generates recommendations. Its methods include collaborative filtering with matrix factorization, item-to-item similarity based on embeddings, tags or users, user-to-user recommendations, configurable non-personalized recommendations and external API recommenders. It is suited to developers who want to operate a recommender in their own environment rather than buy a hosted service.
The range of methods is a key distinction: teams can combine personalized and non-personalized approaches and edit recommendation pipelines in the dashboard. The dashboard also supports data management, while REST APIs handle data management and recommendation requests. Online evaluation lets teams assess recommendation performance. Gorse lists Redis, MySQL, PostgreSQL, MongoDB and ClickHouse integrations; deployment documentation covers binary, Docker and Kubernetes options. This makes it a fit for teams prepared to own deployment and connect recommendation requests to their application.
Gorse is open source and has a free plan, so its published pricing model carries no license cost. That does not remove the work of running it: self-hosting and importing interaction data are part of the operating model. Documentation is the listed support channel, so teams seeking vendor-led support should consider alternatives. Choose Gorse if you need a flexible set of recommendation methods, API access and control over deployment; look elsewhere if you need a managed service or more direct support.
Gorse pros and cons
- Where it wins
- Offers collaborative, item-to-item, user-to-user and non-personalized methods
- Includes a REST API and dashboard for data and recommendation pipelines
- Supports Redis, MySQL, PostgreSQL, MongoDB and ClickHouse
- Where it doesn't
- Requires teams to deploy and run it in their own environment
- Setup involves importing users, items and interaction data
- Support channels listed are limited to documentation
Gorse fact sheet, pricing and score →
Advertiser disclosure: iTechGuides is reader-supported. Vendors can pay for top positions in our rankings and for a place on other products' pages, and we may earn a commission when you click some links. Bought places stand at the number bought; this page and our disclosure say so. Paying vendors may get a fuller, more detailed review from our editors, and that review can change their score. How we rank.
Last updated · How we research and update