teabranch/open-responses-server

Wraps any OpenAI API interface as Responses with MCPs support so it supports Codex. Adding any missing stateful features. Ollama and Vllm compliant.

56
/ 100
Established

This project lets developers or researchers use OpenAI's coding assistant (Codex) and other OpenAI API clients with their own self-hosted language models like Ollama or vLLM. It takes requests designed for the OpenAI API and routes them to your chosen AI backend, while also managing features like stateful chat and tool calls. This is useful for those who want to experiment with different LLMs but maintain compatibility with existing OpenAI-dependent applications.

152 stars. Available on PyPI.

Use this if you want to run OpenAI's Coding Assistant or other OpenAI API-compatible tools against your own local or private large language models.

Not ideal if you solely use OpenAI's official APIs and do not need to integrate with self-hosted or alternative AI backends.

AI development LLM deployment API integration AI research coding assistant
Maintenance 6 / 25
Adoption 10 / 25
Maturity 24 / 25
Community 16 / 25

How are scores calculated?

Stars

152

Forks

20

Language

Python

License

MIT

Last pushed

Nov 05, 2025

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/mcp/teabranch/open-responses-server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.