Build your first AI agent – powered by Google Gemini with memory
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: SerpApi (Google Search). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 7 nodes and runs when a chat message arrives. Along the way it connects SerpApi (Google Search) and Google Gemini Chat Model.
How it runs
Trigger: When a chat message arrives.
- AI Agent: runs an AI agent, with model: Google Gemini Chat Model; 3 tools (Think, SerpAPI, Calculator); memory: Simple Memory
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- SerpApi (Google Search) in SerpAPI: no direct replacement: call the SerpApi REST API with an HTTP Request tool, or use a verified community node.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| SerpApi (Google Search) SerpAPI | No direct replacement: call the SerpApi REST API with an HTTP Request tool, or use a verified community node |
Nodes used (7)
- Chat Trigger
@n8n/n8n-nodes-langchain.chatTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - Think Tool
@n8n/n8n-nodes-langchain.toolThink - SerpApi (Google Search)
@n8n/n8n-nodes-langchain.toolSerpApi - Google Gemini Chat Model
@n8n/n8n-nodes-langchain.lmChatGoogleGemini - Calculator
@n8n/n8n-nodes-langchain.toolCalculator - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow
From the author
A smart personal assistant that can reason, search, calculate, and remember — powered by Google Gemini and ready in one click. Most AI agents only respond — this one thinks before replying, pulls in real-time facts, does the math, and even remembers the last…