# cortexlabs/cortex

Production infrastructure for machine learning at scale

Repository: https://github.com/cortexlabs/cortex
Canonical: https://ross.abutalabs.com/products/cortex
Homepage: https://cortexlabs.com/
Language: Go
License: Apache-2.0
License Family: permissive
Topics: machine-learning, infrastructure
Last push: 2024-06-12T19:34:23+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2778, "days_push": 812, "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 8011, forks 594 (observed 2026-08-28T04:10:11.643603+00:00)

## What it is
Cortex is an open-source platform for deploying, managing, and scaling machine learning models in production on AWS, built on top of EKS. It supports realtime, async, and batch inference workloads with autoscaling, spot instances, and observability integrations.

## Use cases
- deploy machine learning models to production on aws
- serve ml models with autoscaling on gpu instances
- run batch inference jobs at scale
- host realtime model inference endpoints
- reduce inference costs with spot instances
- set up mlops infrastructure with terraform

## When to choose
- you deploy models on AWS and want managed autoscaling inference
- you need realtime, async, and batch serving from one platform
- you want spot-instance cost savings with on-demand fallback

## When to avoid
- you need actively maintained software - the project is no longer maintained by its original authors
- you deploy outside AWS - Cortex is built specifically for AWS/EKS
- you want a fully managed service rather than self-managed clusters

## Facets
- artifact type: infra-config
- maturity: abandoned
- function: deployment, container-orchestration, infrastructure-as-code, monitoring, machine-learning, llm-inference
- domain: machine-learning, cloud-computing, infrastructure-as-code, microservices
- platform: cloud, go, self-hosted
- tags: model-serving, mlops, autoscaling, aws-eks, serverless-inference, gpu-inference, terraform-provider, devops, kubernetes, docker

## Member repositories
- cortexlabs/cortex (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:10:11.643603+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 2026-08-29T17:32:06.251965+00:00, confidence not recorded.
  - readme: https://github.com/cortexlabs/cortex (fetched 2026-08-28T04:10:11.643603+00:00, sha 9a223afeed72)
- Data as of 2026-08-30T08:39:29.467469+00:00.