slawoc/gollamas repository overview

⁠gollamas⁠

A per model "reverse proxy" which redirects requests to multiple ollama servers.

This is a reverse proxy for ollama, it accepts mainly chat and generation requests, it reads requests and transfers the payload to a server which has been specifically assigned to run the model reffered to in the request. Reffer to API⁠ for a list of endpoints currently supported.

⁠run on docker

Images are automatically built for amd64, arm, arm64, riscv64, s390x and ppc64le. Issues for other architectures are welcome.

Official images are automaticaly made available on docker hub and ghcr.io. You can run the latest image from either.

⁠from docker hub

The main images are on docker hub⁠.

docker run -it \
  -e GOLLAMAS_PROXIES="llama3.2-vision=http://server:11434,deepseek-r1:14b=http://server2:11434" \
  slawoc/gollamas:latest

⁠github

Alternatively images are published to ghcr.io⁠.

docker run -it \
  -e GOLLAMAS_PROXIES="llama3.2-vision=http://server:11434,deepseek-r1:14b=http://server2:11434" \
  ghcr.io/slawo/gollamas:latest