← All N8N workflows
AI & researchAgentAggregateChat TriggerCodeHTTP Request

Ahrefs Keyword Research Workflow

Configured with Agent, Aggregate, Chat Trigger, HTTP Request, and additional nodes. Review the connections and setup before adapting this template.

Workflow preview
TriggerWhen chat messagereceivedChat TriggerAI & modelsGoogle Gemini ChatModelLM Chat Google GeminiAI & modelsGoogle Gemini ChatModel1LM Chat Google GeminiAI & modelsKeyword Data ResponseFormatterAgentAI & modelsKeyword QueryExtraction & Cleaning…AgentCodeExtract Main Keyword &10 related Keyword dataCodeTransformAggregate Keyword DataAggregateWeb / APIAhrefs Keyword APIRequestHTTP RequestData storeSimple MemoryMemory Buffer Window

Node categories in this workflow

  • Trigger
  • AI & models
  • Code
  • Transform
  • Web / API
  • Data store

Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.

Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.

How it works

The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.

Workflow node names, types, and operations
NodeCategoryTypeOperation
When chat message receivedTriggerChat TriggerSee node parameters
Google Gemini Chat ModelAI & modelsLM Chat Google GeminiSee node parameters
Google Gemini Chat Model1AI & modelsLM Chat Google GeminiSee node parameters
Keyword Data Response FormatterAI & modelsAgentSee node parameters
Keyword Query Extraction & Cleaning AgentAI & modelsAgentSee node parameters
Extract Main Keyword & 10 related Keyword dataCodeCodeSee node parameters
Aggregate Keyword DataTransformAggregateSee node parameters
Ahrefs Keyword API RequestWeb / APIHTTP RequestSee node parameters
Simple MemoryData storeMemory Buffer WindowSee node parameters

Setup

  1. Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
  2. Connect your own credentials through n8n’s credential store. Replace REPLACE_WITH_* values with your resource identifiers.
  3. Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
  4. Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.

Requirements

An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.

Credential types declared in the source

  • googlePalmApi

Workflow notes

Keyword Query Extraction

Keyword Query Extraction

This ai agent is important so that you always make sure for all queries you send, only the keyword phrase will be passed over to the API request node, and if you misspell any word, it will be corrected.

The API Request

The API Request

You can tweak this to either get "answer the public kwywords" or "keyword overviews", just visit the api docs page

Extract Keyword Data

Extract Keyword Data

The data from the API query will be so so big and I have written this javascript function to extract the most important bits. You can modify it if you want to also get monthly data, or just download the response as pdf and probably pass it for analysis.

Trigger Node

Trigger Node

This is just a sample trigger node to get started. You can use a telegram, whatsapp, webhook node etc, to get the keyword queried.

Respose Formatter

Respose Formatter

The ai agent node to format responses will give you more room to decide how you want your summaries to be sent back to you. You can modify the system message to get your desired outcome. Otherwise, good luck building on top of this. I will give a detailed docs guide on the main n8n workflow page

Ahrefs Keyword Research Workflow

Ahrefs Keyword Research Workflow

Purpose and structure

This folder contains the Ahrefs Keyword Research Workflow workflow. Its executable nodes use agent, aggregate, chatTrigger, code, httpRequest, lmChatGoogleGemini, memoryBufferWindow. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.

Setup

Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.

Entry points

When chat message received

Verification

Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.

Attribution

https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Aggregate/1576_Aggregate_Stickynote_Automate_Webhook.json MIT; preserve source notices.

More in AI & research