# SeldonIO/seldon-core

An MLOps framework to package, deploy, monitor and manage thousands of production machine learning models

Repository: https://github.com/SeldonIO/seldon-core
Canonical: https://ross.abutalabs.com/products/seldon-core
Homepage: https://www.seldon.io/solutions/core/
Language: Go
License: NOASSERTION
License Family: other
Topics: kubernetes, machine-learning, deployment, serving, mlops, aiops, machine-learning-operations, production-machine-learning
Last push: 2026-03-23T11:39:54+00:00

## Health v2 (maintenance only)
Score: 72/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 73, release rhythm 55, longevity 100
- inputs: {"age_days": 3178, "days_push": 163, "days_rel": 222, "gap_med": 59, "n_releases_24m": 8}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4778, forks 867 (observed 2026-08-28T04:08:59.552622+00:00)

## What it is
Seldon Core 2 is an MLOps and LLMOps framework for deploying, managing, and scaling machine learning models and modular AI applications on Kubernetes. It provides pipelines with Kafka-based streaming, autoscaling, multi-model serving, and experiment routing for A/B tests and shadow deployments.

## Use cases
- deploy machine learning models to production on kubernetes
- serve thousands of models with shared inference servers
- run A/B tests and shadow deployments between model versions
- build composable real-time AI pipelines with kafka
- autoscale model inference based on custom metrics
- deploy and serve LLMs in production
- detect drift and outliers on production models

## When to choose
- you need production-grade model serving on kubernetes at scale
- you want to consolidate many models on shared infrastructure to cut costs
- you need pipeline orchestration with realtime streaming between ML components
- you require A/B testing, shadow deployments, or experiment routing for models

## When to avoid
- you deploy only a handful of models without kubernetes
- you need a fully permissive open-source license since it uses the Business Source License
- you want a simple serverless inference endpoint without cluster operations
- your team has no kubernetes expertise

## Facets
- artifact type: framework
- maturity: active
- function: machine-learning, deployment, monitoring, streaming, llm-inference, microservices, container-orchestration
- domain: machine-learning, large-language-models, artificial-intelligence
- platform: cloud, self-hosted, go
- tags: mlops, model-serving, llmops, inference, autoscaling, ab-testing, kafka, multi-model-serving, kubernetes, devops, docker

## Member repositories
- SeldonIO/seldon-core (main) score 72

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:59.552622+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 2026-08-29T18:18:44.853230+00:00, confidence not recorded.
  - readme: https://github.com/SeldonIO/seldon-core (fetched 2026-08-28T04:08:59.552622+00:00, sha 313509bcee1d)
- Data as of 2026-08-30T08:39:29.467469+00:00.