#74 · Primary category： LLM Application Frameworks
Gemini-API
✨ Reverse-engineered Python API for Google Gemini web app
Project last updated：08/27/26
GitHub Stars
3.5K
Forks
548
Contributors
19
License
AGPL-3.0
Why we included this project
If you'd rather not sign up for a paid API key just to get Gemini's chat into your own script or bot, this package exposes the web interface as an async Python API. It keeps your session cookies refreshed in the background, which matters for services that run around the clock, and it covers more than plain text: you can generate and edit images, produce video and audio, run the deep research workflow, and hook into Gemini extensions like YouTube and Gmail. The API surface mirrors Google's official SDK, so a later move to the real platform API is straightforward, and there's a small CLI for quick tests. The catch is that it depends on undocumented web endpoints, so Google's internal changes can break it at any time.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
langchain
The agent engineering platform.
dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
headroom
Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
litellm
The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]
llama_index
LlamaIndex is the leading document agent and OCR platform