Praesto is a lightweight, cloud-native Kubernetes operator that prepares, caches, and mounts AI model artifacts into workloads using reusable ModelCache resources, ReadWriteMany PVCs, downloader Jobs, and admission webhooks for automatic model injection.

6 stars 0 forks 6 watchers Go Apache License 2.0
helm kubernetes llm operator
3 Open Issues Need Help Last updated: Jun 30, 2026

Open Issues Need Help

View All on GitHub
documentation good first issue area/testing

Praesto is a lightweight, cloud-native Kubernetes operator that prepares, caches, and mounts AI model artifacts into workloads using reusable ModelCache resources, ReadWriteMany PVCs, downloader Jobs, and admission webhooks for automatic model injection.

Go
#helm#kubernetes#llm#operator
documentation good first issue area/testing

Praesto is a lightweight, cloud-native Kubernetes operator that prepares, caches, and mounts AI model artifacts into workloads using reusable ModelCache resources, ReadWriteMany PVCs, downloader Jobs, and admission webhooks for automatic model injection.

Go
#helm#kubernetes#llm#operator
documentation good first issue area/webhook

Praesto is a lightweight, cloud-native Kubernetes operator that prepares, caches, and mounts AI model artifacts into workloads using reusable ModelCache resources, ReadWriteMany PVCs, downloader Jobs, and admission webhooks for automatic model injection.

Go
#helm#kubernetes#llm#operator