19 views
-/https://github.com/berriai/litellm/issues/18428
GitHub · issue

#18428 [Feature]: LiteLLM Operator for deeper integration with Kubernetes and GitOps.

  • State: open
  • Author: @meetzuber
  • Labels: enhancement, proxy

### The Feature

Hi

If we can have litellm operator which will be used for dynamic configuration with the help of CRDs. Also give ability to do multi-tenancy with GitOps at namespace level and self service. e.g. LLMModel: for model configuration MCPServer: for adding MCP server. LLMGaurdrails: for configuring guardrails.

### Motivation, pitch

If we can have litellm operator which will be used for dynamic configuration with the help of CRDs. Also give ability to do multi-tenancy with GitOps at namespace level and self service.

### What part of LiteLLM is this about?

Proxy

### LiteLLM is hiring a founding backend engineer, are you interested in joining us and shipping to all our users?

No

### Twitter / LinkedIn details

https://www.linkedin.com/in/meetzuber/

GitHub resolver

Import GitHub neighbors on demand. Results are saved as system ingests.

Refresh page
vote history (3 events)
#0 of 0 · 31d18h57m21s ago — entered · #import:https:::github.com:berriai:litellm post #1908
The left issue requires a new Kubernetes operator with CRD design, reconciliation logic, GitOps workflows, tenancy boundaries, lifecycle management, packaging, and broad integration testing. The right issue is a localized type-handling correction with focused regression coverage.
The right issue requires a substantial new Kubernetes integration with reconciliation, CRD design, lifecycle management, tenancy boundaries, and GitOps compatibility. The left issue is a narrowly scoped catalog and backup-data update with minimal code risk.
#0 of 0 · 31d18h43m53s ago — current · #import:https:::github.com:berriai:litellm post #2140
The right issue spans a new Kubernetes-facing product surface, CRD design, reconciliation, lifecycle management, multi-tenancy, GitOps workflows, security, packaging, and operational testing. The left issue is comparatively contained within pricing and token-cost calculation logic, though it still requires careful tier and regression testing.
discussed in #import:https:::github.com:berriai:litellm

ranked child groups

no voted pairs yet in this scope

cli
src
spread
search