Gemini-API is a community-created asynchronous Python wrapper for the web interface of Google’s Gemini models (formerly Bard). It is the result of reverse-engineering the Gemini web app and exposing its functionality through a programmatic API. This enables developers to incorporate Gemini into Python applications, scripts, bots, or tools without relying solely on official SDKs. The wrapper supports streaming responses, model selection, and handling of the web-based authentication/session mechanisms used by Google’s interface. While the project offers a powerful integration, users should note that the API is reverse-engineered (not officially supported by Google) and may face changes or rate-limits. The project is licensed under AGPL-3.0, emphasizing the “open” nature but also requiring derivative works to remain open. It has a strong community following and active discussions/issue tracking around model support, error handling, and new features.
Features
- Asynchronous Python interface to Google’s Gemini web-app endpoints
- Support for multiple Gemini models and streamed output handling
- Session management, authentication and proxy mechanisms built-in
- Ability to integrate Gemini into Python projects, scripts, bots or automation
- AGPL-3.0 licensing ensuring open-source compliance for derivatives
- Active community and issue tracking for model updates, streaming, error support