Replace <GITHUB_USERNAME> and ensure $GITHUB_PAT is set in your shell
Description
echo "${GITHUB_PAT}" | docker login ghcr.io -u <GITHUB_USERNAME> --password-stdin
Installation
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open the source below and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
README
LiteLLM Server Boilerplate (with LibreChat as UI)
**A lightweight LiteLLM server boilerplate** pre-configured with `uv` and `Docker` for hosting your own **OpenAI- and Anthropic-compatible endpoints.** Perfect with **LibreChat** as the web UI (a quick setup of which is included in this repository) or any other OpenAI / Anthropic API compatible client. Contains an example of a custom provider that stylizes responses (Yoda example) to serve as a starting point for your own custom providers (which you can think of as **your own AI agents and assistants**).
**⚠️ ATTENTION ⚠️** This `README` is intended for the [litellm-server-boilerplate](https://github.com/teremterem/litellm-server-boilerplate) repository.
Architecture 📝
OpenAI/Anthropic API compatible clients (LibreChat etc.)
↓
LiteLLM Server (Port 4000)
↓
Your custom agents
Quick Start ⚡
Prerequisites
- OpenAI API key 🔑 (or any other provider's API key that you're planning to use under the hood)
- Either Docker Desktop or uv (or both)
GPT-5 caveat
If you are going to use GPT-5 via API for the first time, **OpenAI may require you to verify your identity via Persona.** You may encounter an OpenAI error asking you to “verify your organization.” To resolve this, you can go through the verification process here:
Setup 🛠️
**Clone this repository, but use a special remote name (`boilerplate` instead of `origin`):**
The reason `git clone` below uses `boilerplate` as the remote name instead of the usual `origin` is because this will enable you to set up `origin` to point to YOUR OWN remote repository in the later steps of this guide.
git clone \ --origin boilerplate \ https://github.com/teremterem/litellm-server-boilerplate.git \ my-litellm-servercd my-litellm-server**NOTE:** You can replace `my-litellm-server` with a different name in both commands above.
**Rename `main` branch to `main-boilerplate` in your local repository:**
This will later allow you to use the local `main-boilerplate` branch to occasionally pull in bugfixes, new features, etc. from the original `litellm-server-boilerplate` repo **(see the `"Staying up to date with the Boilerplate"` section later in this `README`)**, while making room for YOUR OWN `main` branch, which you will modify as you please and push to YOUR OWN remote (see further steps).
git branch --move main main-boilerplate**Create YOUR OWN `main` branch in your local repository:**
Double-check that
Related Skills
Docker
---
DevOps Kubernetes
---
DevOps AWS Skills
AWS development with CDK best practices, cost optimization MCP servers, and serverless/event-driven architectu
DevOps Composio Split
Manage Split feature flags and experiments
DevOps **claude-code-router**
(25.3k ⭐) - Use Claude Code as the foundation for coding infrastructure, allowing you to decide how to interac
DevOps CLAUDE.md CI/CD Wiki
Community patterns for CLAUDE.md configuration in CI/CD pipelines.
DevOps