MLOps framework to package, deploy, monitor and manage thousands of production machine learning models.
Cortex
Cortex provides cloud infrastructure for deploying, managing, and scaling machine learning models in production.
About Cortex
Cortex provides cloud infrastructure for deploying, managing, and scaling machine learning models in production. It supports realtime, async, and batch workloads, with cluster autoscaling across CPU and GPU instances, spot instance use, and multiple cluster environments.
Clusters are provisioned with declarative configuration or a Terraform provider, with metrics and logs sent to external monitoring tools. Cortex runs on EKS and deploys into a VPC on the user's AWS account with IAM integration. The homepage states the project is joining Databricks.
Key features
- Realtime workloads that autoscale on in-flight request volumes
- Async processing that autoscales on request queue length
- On-demand distributed fault-tolerant batch processing jobs
- Cluster autoscaling with CPU and GPU instances
- Provision clusters with declarative config or Terraform provider
- Deploy clusters into VPC on user's AWS account with IAM integration
Best for: Teams that deploy and scale machine learning models on AWS.
Good for
- Supports realtime, async, and batch workload types
- Runs on EKS and deploys into a VPC on the user's AWS account
- Works with Terraform, Grafana dashboards, CloudWatch, and IAM
Watch out for
- Built for AWS and EKS; no other cloud provider is stated
Cortex at a glance
- Website
- cortex.dev
- Type
- Online tool
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Cortex alternatives
Tools and sites you could use instead, ranked by how closely they match.
CoreWeave presents cloud infrastructure for AI and machine learning, with deployment and scaling for production models.
Espresso AI uses machine learning to optimize Snowflake and Databricks data warehouses and reduce query and infrastructure costs.
Kubeflow provides a machine learning toolkit for deploying workflows on Kubernetes.
Open source
24 alternativesInfer.NET runs Bayesian inference in graphical models for a range of machine learning problems.
Build machine learning applications with Delta, an open-source framework implemented in Rust.
Open source
24 alternativesPopular in AI Infrastructure & MLOps
Well-known listings from the same topic.
Guild AIguild.aiFlow AIflow-ai.comsystemprompt.iosystemprompt.ioKili Technologykili-technology.comAPI docsdocs.x.aiEyePop.aieyepop.ai
Cortex FAQ
What types of workloads can Cortex run?
Realtime workloads that autoscale on in-flight requests, async processing that autoscales on queue length, and on-demand distributed batch jobs.
How does Cortex integrate with AWS?
It runs on EKS, deploys clusters into a VPC on your AWS account, and integrates with IAM for authentication and authorization.
How are clusters provisioned and observed?
Provisioning uses declarative configuration or a Terraform provider; metrics can go to monitoring tools or Grafana dashboards, and logs to log tools or CloudWatch.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.