# SeldonIO/seldon-server

Machine Learning Platform and Recommendation Engine built on Kubernetes

Repository: https://github.com/SeldonIO/seldon-server
Canonical: https://ross.abutalabs.com/products/seldon-server
Homepage: https://www.seldon.io/
Language: Java
License: Apache-2.0
License Family: permissive
Topics: machine-learning, deep-learning, deployment, kubernetes, docker, microservices, spark, kafka, kafka-streams, tensorflow, python, java, cloud, aws, gcp, azure, seldon, recommender-system, recommendation-engine, prediction
Last push: 2020-04-12T12:00:18+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 4221, "days_push": 2334, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1477, forks 298 (observed 2026-08-28T04:04:50.334794+00:00)

## What it is
Seldon Server is an open-source machine learning platform and recommendation engine that runs on Kubernetes, providing Predict and Recommend APIs for deploying supervised models and content-based recommendations at scale. The project is archived and no longer maintained; its successor is Seldon Core, which focuses purely on serving ML models in production.

## Use cases
- deploy machine learning models to production on kubernetes
- build a content recommendation engine for my app
- serve tensorflow and xgboost models behind a rest api
- run a/b tests on recommendation algorithms
- set up real-time analytics dashboards for model predictions
- deploy ml microservices on aws or gcp

## When to choose
- you need a full legacy ML platform with recommendation algorithms out of the box and can maintain it yourself
- you want the historical Seldon Server architecture as a reference

## When to avoid
- you want active maintenance or support - the project is archived
- you only need model serving on Kubernetes - use Seldon Core instead
- you need modern Kubernetes-native ML deployment tooling

## Facets
- artifact type: service
- maturity: abandoned
- function: machine-learning, deployment, microservices, api-framework, monitoring, message-queue
- domain: machine-learning, artificial-intelligence, data-science, cloud-computing, microservices
- platform: cloud, self-hosted, python, jvm
- tags: recommendation-engine, model-serving, prediction-api, ab-testing, grpc, kafka-streams, tensorflow, archived, superseded-by-seldon-core, containers, recommendation, kubernetes, docker

## Member repositories
- SeldonIO/seldon-server (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:50.334794+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:34:23.122693+00:00, confidence not recorded.
  - readme: https://github.com/SeldonIO/seldon-server (fetched 2026-08-28T04:04:50.334794+00:00, sha 5417934883ca)
- Data as of 2026-08-30T08:39:29.467469+00:00.