devtools

Deploy LLM services with rbg

Name: Deploy LLM services with rbg
Author: sgl-project

Deploy LLM inference services on Kubernetes with rbg, a workload for dev teams, with 229 GitHub stars

From the repo · “A workload for deploying LLM inference services on Kubernetes”

intermediate⏱ 30 minutes💵 Free + LLM API costs

309 stars+3★ this week85 forksGoGuide quality 9/10 · reviewed Jun 30Updated 10/23/2026100% free · open source

What it is

Helps you create and deploy AI-powered services on a Kubernetes cluster.

Real use case example

"A founder of a startup, Sarah, wants to quickly build a FAQ page where customers can ask questions and receive answers from her product knowledge base. She uses rbg to deploy a Kubernetes cluster, which makes it easy to deploy her AI model and scale it as needed."

When to use it

•When you need to deploy LLMs in a production environment with high scalability and reliability requirements
•When your development team requires a simplified workflow for deploying and managing AI services on Kubernetes
•When you want to leverage the benefits of Kubernetes for your AI workloads, such as automated rolling updates and self-healing

Ready-to-paste prompt

kubectl apply -f https://raw.githubusercontent.com/sgl-project/rbg/main/examples/llm-service.yaml

Heads up: Ensure you have a Kubernetes cluster with the necessary dependencies installed, such as the Kubernetes API server and the rbg custom resource definitions, before attempting to deploy the rbg workload

Saves to your device

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/rbg && curl -fsSL https://workflowstacks.com/api/skills/rbg/claude-skill -o ~/.claude/skills/rbg/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How Deploy LLM services with rbg works

Codeflow

Free to inspect

Deploy LLM services with rbg is a very large Go project (~94k lines across 454 code files, plus 106 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size

Very large codebase

~94k lines · 454 code files · days to read — use, don't read

Setup

Developer setup

A real software project. Use it via its install path; don't expect to read it all.

Runs on

Go · Docker

No API keys detected

Go 99%Shell 1%

Where to start reading

1
README.md
Start here — what it does and how to install it
2
cmd/cli/main.go
Where the program starts running
3
go.mod
Dependencies and the commands it exposes
4
pkg/component-discovery/component_discovery_test.go
Inside pkg/ — the main logic begins here
5
examples/basic/coordinated-policy/coordinated-rolling-update.yaml
A worked example — copy this to get going

What's in each folder

pkg/Core code — the actual logic169 files

internal/Core code — the actual logic20 files

api/Backend / API56 files

cmd/Command-line entry points18 files

examples/Examples you can copy76 files

doc/Documentation70 files

client-go/Folder183 files

keps/Folder44 files

READMEHas testsDocumentedCI checksDocker readyExamples includedApache-2.0 licenseUpdated this month

Use with Claude

New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install

Claude Code

mkdir -p ~/.claude/skills/rbg && curl -fsSL https://workflowstacks.com/api/skills/rbg/claude-skill -o ~/.claude/skills/rbg/SKILL.md

Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)

claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

Quick Actions

Details

Creator

sgl-project

Language

Do this with a working workflow

Pages we wrote and tested that put a skill like this to work — importable n8n templates, outcome guides and Claude Desktop configs.

Free n8n template

AI Support Agent (Chat)

A chat agent that answers customer questions from YOUR business info — with conversation memory. It never invents policies; anything it doesn't know, it hands to a human.