A curated list of code samples and tutorials for building agents on Gemini Enterprise Agent Platform (previously Vertex AI). This is my fork of Google-Cloud-AI/agent-platform, kept as a bookmark I can find quickly when I need the right starting sample.
The concepts
The repo contains almost no code of its own. Its value is the map: one page that organizes a large platform into the order you meet it when building an agent.
- Foundation models — Gemini, Veo for video, Lyria for music, image generation, and Model Garden with 150+ partner and open-weight models.
- Build — the Agent Development Kit (ADK), the Agents CLI for scaffolding and deploying, the low-code Agent Studio, and Agent Garden templates.
- Tools and data — grounding with Google Search, RAG Engine, Agent Search, and Vector Search 2.0.
- Protocols — Agent2Agent (A2A) for multi-agent handoffs and the Model Context Protocol (MCP) for tools.
Each entry links to the official documentation or to a runnable notebook, many of them in the generative-ai samples repo.
How to use it
Start with the onboarding guide and intro video linked at the top of the README, then jump to the section that matches what you’re building. It sits well next to the ADK and Agent Engine projects elsewhere on this site.
Source code: github.com/avnit/agent-platform
Upstream: github.com/Google-Cloud-AI/agent-platform