by Agent Circle
This workflow demonstrates how to automate live information gathering, fact-checking, and trend analysis in response to any chat message - using a powerful AI agent, memory, and a real-time search tool. Use cases are many: This is perfect for researchers needing instant, up-to-date data; support teams providing live, accurate answers; content creators looking to verify facts or find hot topics; and analysts automating regular reports with the freshest information. How It Works The workflow is triggered whenever a chat message is received (e.g., a user question, research prompt, or data request). The message is sent to the AI Agent, which follows the following steps: First, it queries SerpAPI – Research to gather the latest real-time information and data from the web. Next, it checks the Window Buffer Memory for any related past interactions or contextual information that may be useful. Finally, it sends all collected data and context to the Google Gemini Chat Model, which analyzes the information and generates a comprehensive, intelligent response. Then, the AI Agent delivers the analyzed, up-to-date answer directly in the chat, combining live data, context, and expert analysis. How To Set Up Download and import the workflow into your n8n workspace. Set up API credentials and tool access for the AI Agent: Google Gemini (for chat-based intelligence) → connected to Node Google Gemini Chat Model. SerpAPI (for real-time web and search results) → connected to Node SerpAPI - Research. Window Buffer Memory (for richer, context-aware conversations) → connected to Node Window Buffer Memory. Open the chat in n8n and type the topic or trend you want to research. Send the message and wait for the process to complete. Receive the AI-powered research reply in the chat box. Requirements An n8n instance (self-hosted or cloud). SerpAPI** credentials for live web search and data gathering. Window Buffer Memory** configured to provide relevant conversation context in history. Google Gemini API** access to analyze collected data and generate responses. How To Customize Choose your preferred AI model: Replace **Google Gemini with OpenAI ChatGPT, or any other chat model as preferred. Add or change memory: Replace **Window Buffer Memory with more advanced memory options for deeper recall. Connect your preferred chat platform**: Easily swap out the default chat integration for Telegram, Slack, or any other compatible messaging platform to trigger and interact with the workflow. Need Help? If you’d like this workflow customized, or if you’re looking to build a tailored AI Agent for your own business - please feel free to reach out to Agent Circle. We’re always here to support and help you to bring automation ideas to life. Join our community on different platforms for assistance, inspiration and tips from others. Website: https://www.agentcircle.ai/ Etsy: https://www.etsy.com/shop/AgentCircle Gumroad: http://agentcircle.gumroad.com/ Discord Global: https://discord.gg/d8SkCzKwnP FB Page Global: https://www.facebook.com/agentcircle/ FB Group Global: https://www.facebook.com/groups/aiagentcircle/ X: https://x.com/agent_circle YouTube: https://www.youtube.com/@agentcircle LinkedIn: https://www.linkedin.com/company/agentcircle
by CustomJS
This n8n workflow shows how to convert PDF files into PNG format with the PDF Toolkit from www.customjs.space. @custom-js/n8n-nodes-pdf-toolkit Notice Community nodes can only be installed on self-hosted instances of n8n. What this workflow does Generate** PDF file from the requested HTML. Convert** the PDF to PNG images. Use** a Code node to handle URLs that point to PDF files. Convert** the PDF to PNG format. Requirements Self-hosted** n8n instance. CustomJS API key** for converting PDF to PNG. HTML** Data to convert PDF files. Code node** for handling URL that indicates PDF file. Workflow Steps: Manual Trigger: Runs with user interaction. HTML to PDF: Request HTML Data. Convert HTML to PDF. Request PDF from Code. Convert PDF to PNG: Convert the generated PNG from PDF Usage Get API key from customJS Sign up to customJS platform. Navigate to your profile page Press "Show" button to get API key Set Credentials for CustomJS API on n8n Copy and paste your API key generated from CustomJS here. Design workflow A Manual Trigger for starting workflow. HTTP Request Nodes for downloading PDF files. Code node for handling URL that indicates PDF file. Convert PDF to PNG. You can replace logic for triggering and returning results. For example, you can trigger this workflow by calling a webhook and get a result as a response from webhook. Simply replace Manual Trigger and Write to Disk nodes.
by Yaron Been
Jfirma1 Test_model AI Generator Description test model Overview This n8n workflow integrates with the Replicate API to use the jfirma1/test_model model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: jfirma1/test_model API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Creativeathive Lemaar Door Wm AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the creativeathive/lemaar-door-wm model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: creativeathive/lemaar-door-wm API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Marth
How It Works ⚙️ This workflow is designed to streamline your monthly financial reporting, turning raw transaction data into actionable insights automatically. Here's a step-by-step breakdown of its operation: Trigger (Cron Node): ⏰ The workflow kicks off automatically on a pre-defined schedule, typically the 1st day of every month, ensuring timely report generation without manual intervention. Get Finance Transactions (Google Sheets): 📊 The first functional node connects to your designated Google Sheet. It reads all the transaction data from the specified range (e.g., 'FinanceSummary!A:E'), acting as the primary data input for the report. Filter Previous Month Transactions (Function): 🧹 Once the data is retrieved, this custom JavaScript function meticulously filters out only those transactions that occurred in the complete previous month. This ensures your report is always focused on the most relevant, recently concluded period. Generate AI Financial Insights (OpenAI): 🧠 The filtered transaction data is then passed to OpenAI's GPT-4 model. Here, the AI acts as your personal finance assistant, analyzing the data to: Calculate the total income. Calculate the total expense. Generate 3 concise, key financial insights in bullet points, helping you quickly grasp the financial health and trends. Send Monthly Finance Report Email (Gmail): 📧 Finally, all the processed information comes together. This node constructs a comprehensive email, embedding: A table summarizing all the previous month's transactions. The valuable AI-generated total income, total expense, and key insights. The email is then automatically sent to your designated finance recipients, delivering the report directly to their inbox. Set Up Steps 🚀 Follow these steps carefully to get your "Finance Monthly Report with AI Insight" workflow up and running: Import Workflow JSON: Open your n8n instance. Click on 'Workflows' in the left sidebar. Click the '+' button or 'New' to create a new workflow. Click the '...' (More Options) icon in the top right. Select 'Import from JSON' and paste the provided workflow JSON code. Configure Credentials: Google Sheets Node ("1. Get Finance Transactions"): Click on this node. Under 'Authentication', select your existing Google Sheets OAuth2 credential or click 'Create New' to set one up. Important: Replace <YOUR_GOOGLE_SHEET_ID_HERE> in the 'Sheet ID' field with the actual ID of your Google Sheet. OpenAI Node ("3. Generate AI Financial Insights"): Click on this node. Under 'Authentication', select your existing OpenAI API Key credential or create a new one if you haven't already. Gmail Node ("4. Send Monthly Finance Report Email"): Click on this node. Under 'Authentication', select your existing Gmail OAuth2 credential or create a new one. Customize Email Details: Gmail Node ("4. Send Monthly Finance Report Email"): Replace <YOUR_SENDER_EMAIL_HERE> with the email address you want the report to be sent from. Replace <YOUR_RECIPIENT_EMAIL_HERE> with the email address(es) you want the report to be sent to (multiple emails can be separated by commas). You can also adjust the 'Subject' if needed. Add & Configure Cron Trigger: Click the '+' icon at the very beginning of the workflow (where it says "first step..."). Search for "Cron" and select the 'Cron' node. Connect: Drag a connection from the Cron node to "1. Get Finance Transactions (Google Sheets)". Schedule: Configure the Cron node to your desired monthly schedule. For example: Set 'Mode' to 'Every Month'. Set 'On Day of Month' to '1' (to run on the first day of each month). Set 'At Time' to a specific time (e.g., '09:00' for 9 AM). Review and Activate: Thoroughly review all node configurations to ensure all placeholders are replaced and settings are correct. Click the 'Save' button in the top right corner. Finally, toggle the 'Inactive' switch to 'Active' to enable your workflow. 🟢 Your automated monthly finance report is now live! Troubleshooting Tip: If the workflow fails, check the 'Executions' tab in n8n for detailed error messages. Common issues include incorrect sheet IDs, invalid API keys, or data format mismatches in your Google
by Yaron Been
Jhonp4 Jhonpiedrahita_ai01 AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the jhonp4/jhonpiedrahita_ai01 model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: jhonp4/jhonpiedrahita_ai01 API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Ger Longstacks
Why If you need to use n8n to connect to service providers of yours, some of which happen to rely on firewall white-listing as part of their access control, you'll need to determine or verify the public IP addresses of your n8n instance(s). How does it work The webhook, upon invocation, will use Http Request node to request public IP address information from ++api.ipify.org++ in json format, for 10 times, then aggregate results to an array. The reason to repeat, is to get all the potential public IP addresses of your n8n instance. Often than not, enterprises or network providers deploy at least a pair of gateway devices at the border for redundancy. built-in array functions in a javascript expression are used to pluck all the values under 'ip' key, and to dedup to an array as response body. How to set it up import the workflow set up your own header-auth credential update the workflow to use the new credential test or activate workflow as usual. example invocation $ curl -H "api-key: super-long-api-token" http://localhost:5678/webhook-test/4879bc79-d6f8-48df-bfe4-613366c7f399 ["88.88.88.66", "88.88.88.88"]
by Calistus Christian
Overview Receive a URL via Webhook, submit it to urlscan.io, wait ~30 seconds for artifacts (e.g., screenshot), then email a clean summary with links to the result page, screenshot, and API JSON. What this template does Ingests a URL from a POST request. Submits the URL to urlscan.io and captures the scan UUID. Waits 30s** to give urlscan time to generate the screenshot and result artifacts. Sends a formatted HTML email via Gmail with all relevant links. Nodes used Webhook** (POST /urlscan) urlscan.io → Perform a scan** Wait** (30 seconds; configurable) Gmail → Send a message** Input { "url": "https://example.com" }
by Yaron Been
Creativeathive Lemaar Doorhandle Newset AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the creativeathive/lemaar-doorhandle-newset model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: creativeathive/lemaar-doorhandle-newset API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Creativeathive Lemaar Door Blurrred AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the creativeathive/lemaar-door-blurrred model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: creativeathive/lemaar-door-blurrred API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Digitalhera Herathaisbragatto AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the digitalhera/herathaisbragatto model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Required Parameters prompt** (string): Prompt for generated image. If you include the trigger_word used in the training process you are more likely to activate the trained object, style, or concept in the resulting image. Optional Parameters mask** (string, default: None): Image mask for image inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. seed** (integer, default: None): Random seed. Set for reproducible generation image** (string, default: None): Input image for image to image or inpainting mode. If provided, aspect_ratio, width, and height inputs are ignored. model** (string, default: dev): Which model to run inference with. The dev model performs best with around 28 inference steps but the schnell model only needs 4 steps. width** (integer, default: None): Width of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation height** (integer, default: None): Height of generated image. Only works if aspect_ratio is set to custom. Will be rounded to nearest multiple of 16. Incompatible with fast generation go_fast** (boolean, default: False): Run faster predictions with model optimized for speed (currently fp8 quantized); disable to run in original bf16 extra_lora** (string, default: None): Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars' lora_scale** (number, default: 1): Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora. megapixels** (string, default: 1): Approximate number of megapixels for generated image How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: digitalhera/herathaisbragatto API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters
by Yaron Been
Spuuntries Ilearnmate Icts AI Generator Description None Overview This n8n workflow integrates with the Replicate API to use the spuuntries/ilearnmate-icts model. This powerful AI model can generate high-quality other content based on your inputs. Features Easy integration with Replicate API Automated status checking and result retrieval Support for all model parameters Error handling and retry logic Clean output formatting Parameters Optional Parameters seed** (integer, default: None): Seed for reproducibility of example generation and vector training. Set to 0 for random behavior. num_examples_per_side** (integer, default: 3): Number of descriptive examples to generate for each side of the contrast. More examples might lead to better vectors but will increase generation time. attributes_to_generate** (string, default: girly,modestly,verbose,happy): Comma-separated list of attributes for which to generate control vectors (e.g., 'girly,modestly,verbose,happy') How to Use Set up your Replicate API key in the workflow Configure the required parameters for your use case Run the workflow to generate other content Access the generated output from the final node API Reference Model: spuuntries/ilearnmate-icts API Endpoint: https://api.replicate.com/v1/predictions Requirements Replicate API key n8n instance Basic understanding of other generation parameters