Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / AI Agents & Assistants

AI Agents & Assistants

Run Open Deep Research with Gemini and OpenRouter

When you run it or send a chat message, an LLM generates search queries, collects and chunks web results, and OpenRouter and Gemini write a research report.

Import it free Sign in to open it

What it does

# Open Deep Research - AI-Powered Autonomous Research Workflow ## Overview Automated workflow: Open Deep Research - AI-Powered Autonomous Research Workflow. This workflow integrates 11 different services: stickyNote, httpRequest, code, agent, chainLlm. It contains 21 nodes and follows best practices for error handling and security. ## Workflow Details - Total Nodes: 21 - Node Types: 11 - Error Handling: ✅ Implemented - Security: ✅ Hardened (no sensitive data) - Documentation: ✅ Complete ## Node Breakdown - Chat Message Trigger: chatTrigger - Generate Search Queries using LLM: chainLlm - LLM Response Provider (OpenRouter): lmChatOpenRouter - Parse and Chunk JSON Data: code - Perform SerpAPI Search Request: httpRequest - Perform Jina AI Analysis Request: httpRequest - Format SerpAPI Organic Results: code - Extract Relevant Context via LLM: agent - Generate Comprehensive Research Report: agent - Split Data for SerpAPI Batching: splitInBatches - ... and 11 more nodes ## Usage Instructions 1. Configure Credentials: Set up all required API keys and credentials 2. Update Variables: Replace any placeholder values with actual data 3. Test Workflow: Run in test mode to verify functionality 4. Deploy: Activate the workflow for production use ## Security Notes - All sensitive data has been removed or replaced with placeholders - Error handling is implemented for reliability - Follow security best practices when configuring credentials ## Troubleshooting - Check error logs if workflow fails - Verify all credentials are properly configured - Ensure all required services are accessible

The steps

  1. Manual Trigger
  2. Chat Message Trigger
  3. Generate Search Queries using LLM
  4. LLM Response Provider (OpenRouter)
  5. Parse and Chunk JSON Data
  6. Perform SerpAPI Search Request
  7. Perform Jina AI Analysis Request
  8. Format SerpAPI Organic Results
  9. Extract Relevant Context via LLM
  10. Generate Comprehensive Research Report
  11. Split Data for SerpAPI Batching
  12. Split Data for Jina AI Batching
  13. LLM Memory Buffer (Input Context)
  14. LLM Memory Buffer (Report Context)

34 steps in total.

Similar automations

AI Agents & AssistantsOpen Deep Research with OpenRouter, SerpAPI and Jina AI14 stepsAI Agents & AssistantsRun Open Deep Research with Gemini and OpenRouter34 stepsAI Agents & AssistantsRun Deep Research with SerpAPI, Jina AI and Gemini14 stepsAI Agents & AssistantsGenerate Deep Research Reports from Telegram with Multiple LLMs105 steps