gorse-io /gorse

AI powered open source recommender system engine supports classical/LLM rankers and multimodal content via embedding

★ 9,925⑂ 928👁 63⑃ 934● 416▤ 54
GoApache-2.0Created 2018-08-14gorse.io
Download: v0.5.11v0.5.11 ↓0.5.112026-07-14
+2
Daily
9,925
stars
928
forks
63
watchers
934
prs
416
issues
54
releases

README

Gorse Open-source Recommender System Engine



!






Gorse is an AI powered open-source recommender system written in Go. Gorse aims to be a universal open-source recommender system that can be quickly integrated into a wide variety of online services. By importing items, users, and interaction data into Gorse, the system will automatically train models to generate recommendations for each user. Project features are as follows.

!

- Multi-source: Recommend items from latest, user-to-user, item-to-item, collaborative filtering and etc.
- Multimodal: Support multimodal content (text, image, videos, etc.) via embedding.
- AI-powered: Support classical recommenders, reranker APIs, and Decision APIs.
- GUI Dashboard: Provide GUI dashboard for recommendation pipeline editing, system monitoring, and data management.
- RESTful APIs: Expose RESTful APIs for data CRUD and recommendation requests.

 Quick Start

The playground mode has been prepared for beginners. Just set up a recommender system for GitHub repositories by the following commands.

bash
docker run -p 8088:8088 zhenghaoz/gorse-in-one --playground


The playground mode will download data from GitRec and import it into Gorse. The dashboard is available at http://localhost:8088.

!

After the "Generate item-to-item recommendation" task is completed on the "Tasks" page, try to insert several feedbacks into Gorse. Suppose Bob is a developer who interested in LLM related repositories. We insert his star feedback to Gorse.

bash
read -d '' JSON 

 Contributors


  


Any contribution is appreciated: report a bug, give advice or create a pull request. Read CONTRIBUTING.md for more information.

 Acknowledgments

gorse is inspired by the following projects:

- Guibing Guo's librec
- Nicolas Hug's Surprise
- Golang Samples's gopher-vector

Top issues

Discussions

Latest release

v0.5.11 v0.5.11 2026-07-14
Features

- Support item search in ClickHouse (1332).

 Fix

- Match any search token in search items (1325).
- Ignore embeddings if no embedding index (1333).

Snapshot: 2026-11-16T09:23:14Z · Data license Apache-2.0 · JSON