Gemini Cookbook

Active
GitHub Jupyter Notebook Apache-2.0

Description

Google Gemini official Cookbook with examples and tutorials for building agents, function calling, and multimodal applications.

Key Features

  • Official Google Gemini API tutorials and code examples in Jupyter notebooks
  • Agents API with Antigravity agent for building custom managed agents
  • Multimodal capabilities: image generation (Nano-Banana 2), video (Veo 3.1), music (Lyria 3)
  • File Search for hosted RAG and grounding with Google Maps
  • LiveAPI for real-time multimodal streaming interactions
  • Comprehensive quickstarts covering Gemini 3.5 Flash, thinking, and inference tiers

Use Cases

💡 Learning Gemini API features through hands-on Jupyter notebook tutorials
💡 Building multimodal AI applications with image, video, and audio generation
💡 Developing RAG systems using File Search and grounding capabilities
💡 Creating real-time streaming applications with LiveAPI
💡 Prototyping AI agents using the Antigravity managed agents API

Strengths & Limitations

Strengths

  • Actively maintained, recent updates
  • High community interest (17.7k stars)
  • Permissive open-source license (Apache-2.0)
  • Established track record (2 years in production)

Quick Start

pip install google-genai

from google import genai

client = genai.Client()
response = client.models.generate_content(model='gemini-2.0-flash', contents='Explain quantum computing in one sentence.')
print(response.text)

Related Projects

Google Agent Skills

18.4k · Python
Active A+

Google's officially maintained collection of Agent Skills for Google products and technologies, including Gemini API, BigQuery, Cloud Run, GKE, and more.

googlegeminigoogle-cloud +1
  • · Officially maintained - continuously updated by the Google team
  • · One-command install - add on demand with npx skills add google/skills
  • · Gemini API skills - call Gemini and managed agents APIs on the Agent Platform

New API

45.3k · Go
Active A

New API is a unified AI model hub for aggregation and distribution, supporting cross-conversion of various LLMs into OpenAI, Claude, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management.

api-gatewayai-gatewayopenai +4
  • · Multi-model protocol conversion — Cross-convert various LLMs into OpenAI, Claude, Gemini-compatible formats through a unified API
  • · Organization-level billing — Per-request, usage-based, and cache-hit billing for OpenAI, Azure, DeepSeek, Claude, Qwen supported models
  • · Channel management & load balancing — Multi-channel management, auto failover, API key rotation for high-availability model calls

Screenshot to Code

74.0k · Python
Active A+

Turn screenshots, mockups, and Figma designs into clean code using AI models. Supports HTML/Tailwind, React, Vue, and other frontend frameworks.

screenshot-to-codemultimodalcode-generation +2
  • · Multi-format input - converts screenshots, UI mockups, Figma designs and screen recordings into runnable code
  • · Multi-stack output - generates code for HTML+Tailwind, React+Tailwind, Vue+Tailwind, Bootstrap, Ionic and more
  • · Multi-model AI integration - built-in Gemini, GPT-5 series, Claude Opus models with side-by-side comparison