Oai2Ollama
A command-line tool that starts a local server exposing an Ollama-compatible API in front of any OpenAI-compatible API, for coding tools that only support Ollama as a custom model provider.
Oai2Ollama wraps an OpenAI-compatible API and re-exposes it as an Ollama-compatible API. This is useful for pointing coding agents that only accept Ollama as a custom provider, such as GitHub Copilot for VS Code, at a custom OpenAI-compatible model.
It runs through uvx or pipx, or as a Docker container, and is configured with an API key, base URL, host and port, either as command-line flags or a .env file. A capabilities option marks which capabilities a model supports (tools, vision, insert, embedding, thinking, completion), and a models option adds models that are not returned by the upstream models endpoint.