Automate meeting intelligence with VEXA, OpenAI & Mem0 for conversation insights

by Stephan Koning ✓ · 692 views · created 2025-08-06 · Document Extraction, AI Summarization

What this workflow does

This AI workflow has 22 nodes and runs when an HTTP POST request hits its webhook URL (plus 2 other triggers). Along the way it connects Redis, Baserow and OpenAI Chat Model. It also calls gateway.dev.vexa.ai and api.mem0.ai over HTTP.

How it runs

Trigger: When an HTTP POST request hits its webhook URL (plus 2 other triggers).

1. Route: Bot Action (Start/Stop) (Switch): routes items into 2 branches
2. SET your webhook (HTTP Request): calls gateway.dev.vexa.ai (PUT)
3. VEXA: Get Transcript (HTTP Request): calls an HTTP API
4. Redis: get
5. HTTP: Start VEXA Bot (HTTP Request): calls gateway.dev.vexa.ai (POST)
6. HTTP: Stop VEXA Bot (HTTP Request): calls an HTTP API (DELETE)
7. Process: Split Transcript Segments (Split Out): splits a list into separate items
8. Stop and Error: stops the run with an error
9. Merge: merges the data from its input branches
10. Baserow: update

…plus 7 more steps. See the full node list below.

Services it uses

RedisBaserowOpenAI Chat Model

HTTP calls to: gateway.dev.vexa.ai, api.mem0.ai

Before you upgrade to n8n 3.0

Nodes used (15)

• No Operation, do nothingn8n-nodes-base.noOp
• Redisn8n-nodes-base.redis
• Webhookn8n-nodes-base.webhook
• Baserown8n-nodes-base.baserow
• HTTP Requestn8n-nodes-base.httpRequest
• Switchn8n-nodes-base.switch
• Split Outn8n-nodes-base.splitOut
• Edit Fields (Set)n8n-nodes-base.set
• Mergen8n-nodes-base.merge
• Aggregaten8n-nodes-base.aggregate
• Information Extractor@n8n/n8n-nodes-langchain.informationExtractor
• OpenAI Chat Model@n8n/n8n-nodes-langchain.lmChatOpenAi
• Stop and Errorn8n-nodes-base.stopAndError
• Manual Triggern8n-nodes-base.manualTrigger
• Coden8n-nodes-base.code

From the author

VEXA: AI-Powered Meeting Intelligence I'll be honest, I built this because I was getting lazy in meetings and missing key details. I started with a simple VEXA integration for transcripts, then added AI to pull out summaries and tasks. But that just solved…

View the original on n8n.io → Check your own copy