Open Deep Research - AI-Powered Autonomous Research Workflow
17 nodes · chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches
- Engine
- n8n
- Nodes
- 17
- Trigger
- scheduled/triggered
- Source file
- 1747_HTTP_Stickynote_Automate_Webhook.json
Workflow flow
Chat Message Trigger
@n8n/n8n-nodes-langchain.chat
LLM Response Provider (OpenRouter)
@n8n/n8n-nodes-langchain.lmChatOpenRouter
LLM Memory Buffer (Input Context)
@n8n/n8n-nodes-langchain.memoryBufferWindow
LLM Memory Buffer (Report Context)
@n8n/n8n-nodes-langchain.memoryBufferWindow
Fetch Wikipedia Information
@n8n/n8n-nodes-langchain.toolWikipedia
Generate Search Queries using LLM
@n8n/n8n-nodes-langchain.chainLlm
Parse and Chunk JSON Data
Code
Perform SerpAPI Search Request
HTTP
Perform Jina AI Analysis Request
HTTP
Format SerpAPI Organic Results
Code
Extract Relevant Context via LLM
@n8n/n8n-nodes-langchain.agent
Generate Comprehensive Research Report
@n8n/n8n-nodes-langchain.agent
Split Data for SerpAPI Batching
SplitInBatches
Split Data for Jina AI Batching
SplitInBatches
14 steps · flows top to bottom, branches left to right
Browse by integration
Browse all integrations →Import into n8n
- Download the n8n JSON file (full or sanitized).
- In n8n: Workflows → Import from file.
- Open each node and reconnect credentials to your accounts.
- Test with manual execution before enabling triggers.
Sanitized JSON removes credential IDs — safer for sharing. Flow graph JSON is OpenRuna's lightweight format for diagrams and other tools, not n8n import.
Overview
Open Deep Research - AI-Powered Autonomous Research Workflow is a free n8n workflow on OpenRuna — 17 nodes connecting chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches, memoryBufferWindow, toolWikipedia. Download the JSON, view the flow diagram, and import it into your n8n instance.
What this workflow does
"Open Deep Research - AI-Powered Autonomous Research Workflow" automates a chat-to-chainLlm flow in n8n across 17 nodes. 17 nodes · chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches A scheduled/triggered entry point kicks it off, and each node passes data to the next until the run completes. On OpenRuna you get the visual graph, the integration list, and a downloadable JSON ready to import into n8n. Use it to learn integration patterns, fork it for your own use case, or deploy it quickly after reconnecting credentials.
Use cases
- Share it with your team as a documented reference for scheduled/triggered automations in the chat stack.
- Study how data moves from chat to chainLlm before building your own variant.
- Use it as a starting template when wiring chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches, memoryBufferWindow, toolWikipedia — adjust node parameters to your accounts and record IDs.
- Import "Open Deep Research - AI-Powered Autonomous Research Workflow" into n8n, reconnect credentials for chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches, memoryBufferWindow, toolWikipedia, and run the same automation in your own workspace.
Example output
Imported into n8n, "Open Deep Research - AI-Powered Autonomous Research Workflow" exposes 17 configured nodes. Trigger type: scheduled/triggered. Integrations: chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches, memoryBufferWindow, toolWikipedia. Open each node after import to map credentials to your own chat and chainLlm accounts. Run it once in test mode to verify any branch logic (Switch/IF nodes) before enabling production triggers.
Tips by platform
Claude
Paste the exported JSON for "Open Deep Research - AI-Powered Autonomous Research Workflow" into Claude and ask it to explain each of the 17 nodes. Claude is good at suggesting credential mappings for chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches, memoryBufferWindow, toolWikipedia, plus error-handling and idempotency improvements before you run it in production.
ChatGPT
Have ChatGPT generate a checklist for adapting "Open Deep Research - AI-Powered Autonomous Research Workflow" to your accounts — which chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches, memoryBufferWindow, toolWikipedia credentials to create and which node parameters to change first.
Cursor
Open the downloaded JSON in Cursor and use Agent mode to refactor hard-coded URLs into env vars, or to generate tests for any Code nodes. Keep the OpenRuna flow diagram open so you do not break connection order across the 17 nodes.
Frequently asked questions
- How do I import "Open Deep Research - AI-Powered Autonomous Research Workflow" into n8n?
- Click Download n8n JSON on this page, then in n8n choose Workflows → Import from file and select the downloaded file. Reconnect credentials on each node — the export carries credential IDs from the original author's instance, not working secrets.
- Which integrations does "Open Deep Research - AI-Powered Autonomous Research Workflow" use?
- It uses: chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches, memoryBufferWindow, toolWikipedia. The flow diagram above shows how each service connects across the 17 nodes. Filter OpenRuna by integration to find related workflows and tools.
- Can I import a sanitized export without credentials?
- Yes. Use "Download sanitized JSON" to strip credential references before sharing internally. You will still add your own chat and chainLlm credentials in n8n after import.
- What trigger type does "Open Deep Research - AI-Powered Autonomous Research Workflow" use?
- Trigger type: scheduled/triggered. After import, confirm the trigger node (webhook, schedule, or app event) matches your environment, then activate the workflow when you are ready to run it.
- Is "Open Deep Research - AI-Powered Autonomous Research Workflow" free to use?
- OpenRuna catalogs community n8n workflows under open licenses. Check the source corpus link for the original license; commercial use may require verifying the third-party API terms for chat, chainLlm, lmChatOpenRouter, httpRequest, agent, splitInBatches, memoryBufferWindow, toolWikipedia.
Related resources
- Agent
PraisonAI
24/7 AI employee team for automating complex challenges. Low-code multi-agent framework with handoffs, guardrails, memory, RAG, and 100+ LLM providers
- Agent
Prompt Optimizer
AI prompt optimization tool with multi-round iterative improvements, dual-mode optimization for system and user prompts, and multi-model support. Available as web app, desktop app, Chrome extension, and Docker deployment. AGPL-3.0 licensed
- Agent
Archon
Workflow engine for deterministic AI coding agents. Define development processes as YAML workflows (planning → implementation → validation → review → PR) with isolated Git worktrees for parallel execution. MIT licensed
- Agent
A2A Protocol
Agent2Agent (A2A) open protocol enabling communication and interoperability between opaque agentic applications. Donated to Linux Foundation by Google with 50+ technology partners. Apache 2.0 licensed
- Agent
CAMEL
First and best multi-agent framework for building scalable agent systems. Apache 2.0 licensed with extensive tooling for agent communication and task automation
- Agent
Neuron AI
PHP Agentic Framework for building production-ready AI driven applications. Connect components (LLMs, vector DBs, memory) to agents that can interact with your data. MIT licensed
- Agent
smolagents
Lightweight agent framework centered on tool use and code-executing workflows
- Agent
Supermemory
Memory API and app for AI agents that provides fast, scalable, context-aware storage and retrieval across projects. MIT licensed
