This article provides a complete, practical walkthrough of the Stickynote Automation Triggered n8n agent. It connects HTTP Request, Webhook across approximately 1 node(s). Expect a Simple setup in 5-15 minutes. One‑time purchase: €9.

What This Agent Does

This agent orchestrates a reliable automation between HTTP Request, Webhook, handling triggers, data enrichment, and delivery with guardrails for errors and rate limits.

It streamlines multi‑step processes that would otherwise require manual exports, spreadsheet cleanup, and repeated API requests. By centralizing logic in n8n, it reduces context switching, lowers error rates, and ensures consistent results across teams.

Typical outcomes include faster lead handoffs, automated notifications, accurate data synchronization, and better visibility via execution logs and optional Slack/Email alerts.

How It Works

The workflow uses standard n8n building blocks like Webhook or Schedule triggers, HTTP Request for API calls, and control nodes (IF, Merge, Set) to validate inputs, branch on conditions, and format outputs. Retries and timeouts improve resilience, while credentials keep secrets safe.

Third‑Party Integrations

• HTTP Request
• Webhook

Import and Use in n8n

1. Open n8n and create a new workflow or collection.
2. Choose Import from File or Paste JSON.
3. Paste the JSON below, then click Import.
4. Show n8n JSON

   Title:
   🔐 Intelligent, Private & Local AI: A Dynamic LLM Router Workflow in n8n Using Ollama
   
   Meta Description:
   Discover how to set up a privacy-focused, self-hosted AI chat system using n8n and Ollama. This dynamic LLM router intelligently selects the optimal local large language model (LLM) for each user prompt—no cloud, no data leaks, just private AI orchestration.
   
   Keywords:
   n8n workflow, Ollama, local LLM router, private AI, self-hosted language models, LangChain, LLM orchestration, dynamic LLM selection, AI routing, phi4, qwq, llama3.2, vision models, code generation AI, local AI agents, open-source automation, privacy-first AI
   
   Article:
   —
   
   🔐 Intelligent, Private & Local AI: A Dynamic LLM Router Workflow in n8n Using Ollama
   
   As more businesses and AI enthusiasts prioritize data privacy and sovereignty, the demand for local AI processing has surged. With powerful tools like Ollama and n8n, it's now possible to run sophisticated AI workflows entirely on your machine without relying on third-party cloud services. This article breaks down a powerful n8n workflow designed to act as an AI router that selects specialized local LLMs dynamically—based entirely on the user’s input.
   
   🚀 What Is This Workflow?
   
   At its core, this n8n workflow—titled “🔐🦙🤖 Private & Local Ollama Self-Hosted LLM Router”—automatically processes incoming chat messages, intelligently analyzes the input, and routes it to the most appropriate local AI model running via Ollama.
   
   Imagine having a roster of specialized AI models: one for math and science, another for summarizing articles, a third for programming help, and even models that can understand images or documents. This workflow acts as your smart dispatcher, deciding whom to consult based on what you ask—all while keeping your data completely local.
   
   🎯 Who Is This For?
   
   This solution is tailor-made for:
   
   - AI developers and hobbyists running Ollama locally
   - Privacy-conscious users avoiding third-party cloud services
   - DIY automation enthusiasts using n8n for full-stack no-code/low-code solutions
   - Organizations seeking AI assistants with sensitive or regulated data
   
   🧠 Key Components of the Workflow
   
   1. 📩 Chat Message Trigger
   The workflow begins with the “When Chat Message Received” node, triggered when a user sends input via an integrated chat interface.
   
   2. 🤖 LLM Router Agent (LangChain + Ollama)
   Using a powerful set of classification heuristics and examples, this agent analyzes the user’s prompt. It must decide which model suits the task best. The decision considers factors such as:
   
   - Whether visual input is involved
   - If the task needs advanced reasoning (e.g., quantum physics)
   - Whether it's a programming task
   - The need for fast, simple conversational replies
   - Multilingual translation or summarization
   
   Example:
   Input: “Can you summarize this article in Spanish?”
   → LLM Router selects llama3.2 for its multilingual summarization capabilities.
   
   3. 📌 Classification Logic and Decision Tree
   Unlike simple keyword matching, the router evaluates the actual intent and context of the prompt using a decision-tree protocol, categorizing tasks under predefined model capabilities such as:
   
   - "qwq" for hard reasoning problems
   - "phi4" for fast low-latency answers
   - "qwen2.5-coder:14b" for code tasks
   - "granite3.2-vision" for charts and diagrams
   - "llama3.2-vision" for general image understanding
   
   The output is a tightly structured JSON object containing:
   {
     "llm": "selected_model_name",
     "reason": "why this model was chosen"
   }
   
   4. 🔄 Ollama Dynamic LLM Agent
   Next, the selected model is used to handle the user prompt dynamically. Thanks to a clever expression (={{ $('LLM Router').item.json.output.parseJson().llm }}), the exact model chosen by the router is injected into the agent node.
   
   5. 💬 Conversational Memory
   Both the router and final AI agent support memory handling via LangChain’s MemoryBuffer. This ensures back-and-forth conversations maintain context over multiple messages—similar to how ChatGPT remembers earlier messages in a session.
   
   6. 🔒 Everything Stays Local
   All processing happens on your machine with zero external API calls (outside optionally installed models). This means you retain full ownership, control, and privacy over your input/output data—a critical requirement for industries handling regulated datasets.
   
   ⚙️ How to Set It Up
   
   To replicate or modify this workflow:
   
   1. ✅ Install and run Ollama locally.
   2. ⬇️ Pull required models (e.g., `ollama pull qwq`, `ollama pull phi4`, `ollama pull qwen2.5-coder:14b`).
   3. 🔧 Configure the Ollama API in n8n with default (http://127.0.0.1:11434).
   4. 🧠 Open the workflow in n8n and activate the automation.
   5. 🧪 Interact via a chatbot UI or send a test payload to the webhook.
   
   🛠️ Customize It Your Way
   
   This system can be extended to match your use case:
   
   - Replace default models with your preferred specialized Ollama models
   - Modify the decision rules and branching logic
   - Add preprocessing for file uploads, image parsing, or OCR integrations
   - Chain responses with follow-up tasks like summarization or data extraction
   
   🔌 Third-Party APIs Used
   
   This workflow is proud to be entirely self-contained, with minimal external API reliance. It uses:
   
   - 🌐 Ollama API (http://127.0.0.1:11434): for all LLM model execution, hosted locally on your machine
   
   There are no calls to cloud-based LLM providers like OpenAI or Anthropic, making it a fully private AI solution.
   
   🧩 Why This Matters
   
   AI adoption doesn't have to come at the cost of privacy and transparency. This self-hosted dynamic LLM router shows how tools like LangChain, Ollama, and n8n can work together to create scalable, secure, and intelligent AI systems—with no cloud dependency. Whether you're a developer looking for granular model control or an organization concerned with data sovereignty, this template gives you full reign over your conversational AI stack.
   
   🔁 Try It Out and Stay Local
   
   All you need to get started is a machine powerful enough to run Ollama, basic familiarity with n8n flows, and a desire to keep your AI truly yours. For AI routing that’s smart, flexible, and private—this workflow sets a new standard.
   
   —
   
   Keywords Recap:
   n8n, Ollama, LangChain, LLM router, local AI, self-hosted language models, dynamic model selection, private machine learning, AI with memory, no cloud AI, open-source workflow automation
   
   Third-Party APIs:
   
   - Ollama Local API (http://127.0.0.1:11434)
   
   With this, you’re ready to harness the full potential of private conversational AI—dynamically, intelligently, securely.

5. Set credentials for each API node (keys, OAuth) in Credentials.
6. Run a test via Execute Workflow. Inspect Run Data, then adjust parameters.
7. Enable the workflow to run on schedule, webhook, or triggers as configured.

Tips: keep secrets in credentials, add retries and timeouts on HTTP nodes, implement error notifications, and paginate large API fetches.

Validation: use IF/Code nodes to sanitize inputs and guard against empty payloads.

Why Automate This with AI Agents

AI‑assisted automations offload repetitive, error‑prone tasks to a predictable workflow. Instead of manual copy‑paste and ad‑hoc scripts, your team gets a governed pipeline with versioned state, auditability, and observable runs.

n8n’s node graph makes data flow transparent while AI‑powered enrichment (classification, extraction, summarization) boosts throughput and consistency. Teams reclaim time, reduce operational costs, and standardize best practices without sacrificing flexibility.

Compared to one‑off integrations, an AI agent is easier to extend: swap APIs, add filters, or bolt on notifications without rewriting everything. You get reliability, control, and a faster path from idea to production.

Best Practices

• Credentials: restrict scopes and rotate tokens regularly.
• Resilience: configure retries, timeouts, and backoff for API nodes.
• Data Quality: validate inputs; normalize fields early to reduce downstream branching.
• Performance: batch records and paginate for large datasets.
• Observability: add failure alerts (Email/Slack) and persistent logs for auditing.
• Security: avoid sensitive data in logs; use environment variables and n8n credentials.

FAQs

Can I swap integrations later? Yes. Replace or add nodes and re‑map fields without rebuilding the whole flow.

How do I monitor failures? Use Execution logs and add notifications on the Error Trigger path.

Does it scale? Use queues, batching, and sub‑workflows to split responsibilities and control load.

Is my data safe? Keep secrets in Credentials, restrict token scopes, and review access logs.