Store persistent AI agent memory with Claude, Voyage AI, Postgres, and Redis

by Oneclick AI Squad ✓ · 14 views · created 2026-09-29 · Internal Wiki, AI RAG

What this workflow does

This workflow has 41 nodes and runs when an HTTP POST request hits its webhook URL (plus 3 other triggers). Along the way it connects Redis and Postgres.

How it runs

Trigger: When an HTTP POST request hits its webhook URL (plus 3 other triggers).

1. Normalize Chat Input (Code): runs custom JavaScript code
2. Set Maintenance Configuration (Edit Fields (Set)): sets 4 fields: decayFactor, decayAfterDays, minImportanceToKeep…
3. Normalize Forget Input (Code): runs custom JavaScript code
4. If: checks a condition and branches into true / false
5. Decay Unused Memory Importance (Postgres): run a query
6. If: checks a condition and branches into true / false
7. Set Configuration Parameters (Edit Fields (Set)): sets 16 fields: anthropicApiUrl, chatModel, extractionModel…
8. Respond with Validation Error (Respond to Webhook): sends the response back to the webhook caller
9. Prune Stale Memories (Postgres): run a query
10. Delete Memories in Postgres (Postgres): run a query

…plus 27 more steps. See the full node list below.

Services it uses

RedisPostgres

Before you upgrade to n8n 3.0

Nodes used (10)

• Webhookn8n-nodes-base.webhook
• Manual Triggern8n-nodes-base.manualTrigger
• Coden8n-nodes-base.code
• Ifn8n-nodes-base.if
• Respond to Webhookn8n-nodes-base.respondToWebhook
• Edit Fields (Set)n8n-nodes-base.set
• Redisn8n-nodes-base.redis
• HTTP Requestn8n-nodes-base.httpRequest
• Postgresn8n-nodes-base.postgres
• Schedule Triggern8n-nodes-base.scheduleTrigger

From the author

Quick overview This workflow provides persistent AI agent memory by combining Redis session history, PostgreSQL + pgvector long-term storage, Voyage AI embeddings, and Anthropic Claude for chat and memory extraction, with webhooks for chat and forgetting…

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