GraphCanon updated today · GitHub synced today
Decision brief
OME is a Kubernetes operator tailored for LLM serving and management, focusing on tasks such as GPU scheduling and model lifecycle control, compatible with SGLang, vLLM, TensorRT-LLM, and Triton.
Good fit when
- If you need robust GPU scheduling alongside LLM serving
- For enterprises that wish to streamline the deployment of models like Qwen on Kubernetes
Avoid when
- In environments where a language other than Go for the operator's implementation is preferred
- When your infrastructure does not support or utilize Kubernetes for orchestration purposes
Observed Jul 16, 2026 · Source: enrich:decision_facts
Verify the decision
Maintenance and security
Full trust report- Maintenance
- Very active (0d since push)
- As of today
- Provenance
- Not a fork · Organization account
- As of today
- Security (OSV)
- No lockfile
- As of 1mo
Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.
Install
go get github.com/ome-projects/omeSimilar tools
Same-category neighbours. No typed graph edges are catalogued for this tool yet.
Evidence and technical details
Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.
Overview
OME is designed to handle LLM serving, GPU scheduling, and model lifecycle management through Kubernetes operations.
Capability facts
- Languages
- go
Source: github.language · Aug 25, 2026
Categories
Tags
README
Installation
Requires Kubernetes 1.28 or newer
Install OME CRDs
helm upgrade --install ome-crd oci://ghcr.io/moirai-internal/charts/ome-crd --namespace ome --create-namespace
Install OME resources
helm upgrade --install ome oci://ghcr.io/moirai-internal/charts/ome-resources --namespace ome
---
### Option 2: Install from Source
For development or customization:
```bash
---
# Install from local charts
helm install ome-crd charts/ome-crd --namespace ome --create-namespace
helm install ome charts/ome-resources --namespace ome
License
OME is licensed under the Apache License 2.0.
For agents
This page has a .md twin and JSON over the API.