Self Host OllamaGateway

About OllamaGateway

OllamaGateway is built for private AI infrastructure. If you want API authentication, request auditing, virtual models, and team-friendly controls on top of Ollama, local deployment is the recommended way to run it.

MIT licensed Docker Pulls Website
Dashboard GitHub
Recommended
Run in Docker

First, install Docker. Then run the following commands in a Linux shell:

image=aiursoft/ollamagateway
appName=ollamagateway
sudo docker pull $image
sudo docker run -d --name $appName --restart unless-stopped -p 5000:5000 -v /var/www/$appName:/data $image

That will start a web server at http://localhost:5000 and you can test the app.

The default username is: admin@default.com, and the default password is: admin123.

Container Context
Property Value
Image aiursoft/ollamagateway
Ports 5000
Binary path /app
Data path /data
Config path /data/appsettings.json
Run in Ubuntu

The following script will install/update this app on your Ubuntu server. Supports Ubuntu 25.04.

curl -sL https://github.com/aiursoftweb/ollamaGateway/raw/master/install.sh | sudo bash

Or with a custom port:

curl -sL https://github.com/aiursoftweb/ollamaGateway/raw/master/install.sh | sudo bash -s 8080
Systemd /opt/apps
Why local deployment

Keep prompts, API keys, usage logs, and model routing inside your own infrastructure boundary.

This is especially useful when serving a team, internal tools, or autonomous agents over an OpenAI-compatible endpoint.

Development & Manual Run
Prerequisites
Run Manually
  1. Execute `npm install` at `wwwroot` folder to install the dependencies.
  2. Execute `dotnet run` to run the app.
  3. Visit http://localhost:5000.
Run in Visual Studio
  1. Open the `.sln` file in the project path.
  2. Press `F5` to run the app.