gemini-web-to-api and gemini-openai-proxy

These are complements: the reverse-engineered Gemini web API (A) provides the backend that the OpenAI-to-Gemini protocol converter (B) can proxy requests to, enabling applications built for OpenAI's API format to route calls through Gemini.

gemini-web-to-api
54
Established
gemini-openai-proxy
53
Established
Maintenance 10/25
Adoption 9/25
Maturity 13/25
Community 22/25
Maintenance 2/25
Adoption 10/25
Maturity 16/25
Community 25/25
Stars: 94
Forks: 46
Downloads:
Commits (30d): 0
Language: Go
License: MIT
Stars: 724
Forks: 139
Downloads:
Commits (30d): 0
Language: Go
License: MIT
No Package No Dependents
Stale 6m No Package No Dependents

About gemini-web-to-api

ntthanh2603/gemini-web-to-api

✨Reverse-engineered API for Gemini web app. It can be used as a genuine API key from OpenAI, Gemini, and Claude.

This tool allows developers to integrate Google Gemini's advanced AI capabilities into their applications without needing a traditional API key. It converts the Gemini web interface into a standardized API, taking browser cookies as input and providing an OpenAI, Claude, or Gemini-compatible API endpoint as output. It is designed for developers who want to build applications that leverage Gemini's latest models for testing and development purposes.

AI-integration application-development LLM-tooling API-development

About gemini-openai-proxy

zhu327/gemini-openai-proxy

A proxy for converting the OpenAI API protocol to the Google Gemini Pro protocol.

This tool helps developers who have built applications using OpenAI's API to switch to Google Gemini Pro without rewriting their code. It acts as a translator, taking requests formatted for OpenAI's Chat Completion, Embeddings, or Model endpoints and converting them for Gemini Pro. This allows developers to seamlessly integrate Google's large language models into their existing OpenAI-compatible projects.

AI application development API integration Large language models Backend services Model deployment

Scores updated daily from GitHub, PyPI, and npm data. How scores work