AI Connect | Data Science Connect
AI ConnectExplore the 2027 portfolio

ML Operations

Seldon

MLOps platform for deploying, monitoring and explaining ML models on Kubernetes

Visit website ↗See if it’s a matchRequest an introduction

About Seldon

Seldon, based in London, develops tools for deploying ML models at scale, including inference servers, deployment patterns such as canary and shadow, and drift and outlier detection. It combines open source components with commercial enterprise offerings.

Common use cases

  • Kubernetes model serving
  • Safe model rollouts
  • Drift alerting
  • Regulatory explainability

Products and services

Seldon Core

Kubernetes-based model serving, source-available under BSL 1.1.

MLServer

Inference server released under Apache 2.0.

Alibi Explain / Alibi Detect

Explainability and drift-detection libraries under BSL 1.1.

Core+ and Enterprise Platform

Commercially licensed offerings.

Pricing and editions. Per Seldon's licensing FAQ, MLServer is Apache 2.0, Core and Alibi are BSL 1.1 (free for non-production, paid for production), and Core+ and the Enterprise Platform are commercial only.

Recent product updates

  • April 2025: released Seldon Core 2.9 and MLServer 1.7 with improved autoscaling, streaming results for GenAI models and usability changes.

Key features

  • Inference servers
  • Canary and shadow deployments
  • A/B testing
  • Drift detection
  • Outlier detection
  • Explainability

Integrations

  • Kubernetes
  • Istio
  • Prometheus
  • MLflow
  • Kafka

Seldon alternatives

FAQs

Where is Seldon based?

London, UK (registered address on its site).

Is it open source?

It maintains open source components alongside commercial products.

Does it support drift detection?

Yes, with drift and outlier alerts.

Work at Seldon? Request updates to this profile. Update this profile

Compare with similar providers

All ML Operations providers