Ross ROSS = Recommend OSS · open-source software intelligence for agents

gorse-io/gorse

AI powered open source recommender system engine supports classical/LLM rankers and multimodal content via embedding observed · 2026-08-28

github.com/gorse-io/gorse · homepage · Go · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

97/100

  • Activity 99
  • Release rhythm 93
  • Longevity 100
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 25
  • age_days: 2941
  • days_rel: 50
  • days_push: 8
  • n_releases_24m: 14

Full methodology

Adoption not part of the score

9808 stars · 912 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

Gorse is an AI-powered open-source recommender system engine written in Go that ingests items, users, and interaction feedback and automatically trains models to generate personalized recommendations. It supports classical recommenders (collaborative filtering, item-to-item, factorization machines) and LLM-based rankers, multimodal content via embeddings, a GUI dashboard, and RESTful APIs with SDKs in many languages.

Use cases

  • add personalized recommendations to my website or app
  • recommend similar items to users based on their history
  • build a collaborative filtering recommender without writing ML code
  • rerank recommendation lists with an LLM
  • recommend content using text and image embeddings
  • self-host a recommendation engine with a dashboard
  • track user feedback and evaluate recommendation quality

When to choose

  • you need a ready-made, self-hosted recommender system with REST APIs and multi-language SDKs
  • you want both classical collaborative filtering and LLM-based ranking in one engine
  • you need multimodal recommendations over text, images, or video via embeddings
  • you want a GUI dashboard for editing recommendation pipelines and monitoring performance

When to avoid

  • you need a lightweight in-process recommendation library embedded in your application rather than a separate service
  • you require fully custom recommendation algorithms beyond the supported recommender types
  • you cannot operate additional infrastructure (databases like Redis, MySQL, Postgres, MongoDB, or ClickHouse)
  • your project needs a permissive-free commercial arrangement beyond Apache-2.0 terms

Facets

service · maturity active

machine-learning search-engine api-framework monitoring data-visualization machine-learning artificial-intelligence large-language-models analytics self-hosted self-hosted go windows recommender-system collaborative-filtering llm-reranker multimodal-embeddings personalization restful-api docker kubernetes linux macos

10 sources

Member repositories

RepositoryRoleHealth v2
gorse-io/gorsemain97

For agents

markdown · JSON · MCP: product_card(name="gorse-io/gorse")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem