

Automatically translated from Japanese by AI
This is a tool that allows anyone to host an Ollama online inference server.
You can use spare PCs to perform inference through Ollama.
It's like a personal version of Google's Colab.
To host the server, run init_server.bat on Windows, or init_server.sh on other systems. If you have all the necessary components, you can set up the server immediately. Then you can share the URL with anyone who wants to access it, and they can access the chat screen. (It's compatible with the OpenAI API. When using it, add /v1 to the end of the provided URL.)
The server side basically does not send information. Additionally, chat history and parameter settings such as system prompts are not retained. If you want to reuse them, you can import/export JSON, so please manage them on the user side.
Token usage and other metrics are recorded in CSV format. This makes it easy to check if you want to charge for token usage or similar. You are permitted to modify this package or create billing flows. In that case, please follow all applicable laws and regulations. I assume no responsibility.
Feedback
Share your thoughts, bug reports, or suggestions directly with the developer
Log in to share your feedback
Log in to leave feedback