Home Projects llama-swap
llama-swap
Go

llama-swap

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

by mostlygeek · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
Likely
Self-hostable
golangllamallamacppMITGoSelf-hostable
View on GitHub
In plain words

Run different AI models on your computer and switch between them easily.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
llama-swap — GitHub preview card
📈 Star history
5.0k4.9k
2026-07-042026-08-31
📈 Track llama-swap

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

llama-swap has 5k stars on GitHub. It has been forked 377 times. llama-swap is written mainly in Go. It has been in active development since 2024. llama-swap is available under the MIT license. Its main topics are golang, llama, llamacpp, localllama.

Frequently asked questions

What is llama-swap?

Reliable model swapping for any local OpenAI/Anthropic compatible server - llama.cpp, vllm, etc

Is llama-swap open source?

llama-swap is an open-source project. It is released under the MIT license.

Is llama-swap free?

Yes. llama-swap is free and open source — you can use, modify and self-host it.

What license does llama-swap use?

llama-swap is available under the MIT license.

What language is llama-swap written in?

llama-swap is written mainly in Go.

🏅 Maintainer of this project?
olud.ai badge — llama-swap

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=mostlygeek-llama-swap)](https://olud.ai/project/mostlygeek-llama-swap.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.