supermemory — AI Memory Engine

Store and recall customer insights with TTL rules in a vector-backed directory.

152|46|Updated Mar 23, 2026

Search Tags:#semantic search #memory #sales enablement #customer insights #vector store #ttl expiration #multi-channel sdr

Ready to run

npx skills add https://github.com/iPythoning/b2b-sdr-agent-template --skill supermemory-ai-memory-engine

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: supermemory — AI Memory Engine
Source: https://github.com/iPythoning/b2b-sdr-agent-template/tree/main/skills/supermemory
Command: npx skills add https://github.com/iPythoning/b2b-sdr-agent-template --skill supermemory-ai-memory-engine

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

You lose valuable customer context over time, causing your SDR to repeat questions, miss preferences, and weaken follow-ups.

Core Features & Use Cases

Semantic Memory Storage: Store extracted customer facts, conversation insights, market signals, and effective scripts to build long-lived sales context.
Semantic Recall for Better Context: Retrieve relevant memories by searching, then inject them back into the conversation workflow to improve relevance and continuity.
Lifecycle Controls with TTL: Keep some memories permanent while expiring time-sensitive insights (like market signals) automatically.

Use Case: After reviewing multiple calls with a lead, capture their stated pricing sensitivity and preferred product bundle, then recall those details during the next outreach to increase reply rates.

Quick Start

Ask an AI agent to add a new insight to your memory by running the command: memory:add "Interested in bulk pricing for Model X and prefers WhatsApp follow-ups".

Frequently Asked Questions about supermemory — AI Memory Engine

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I store and recall customer insights for B2B sales outreach?▼

Semantic memory storage captures customer facts and market signals, then uses vector-backed search to retrieve relevant items for future turns. This prevents repeated questions and forgotten context during multi-channel SDR workflows by injecting recalled insights back into the conversation.

How do I add a new customer insight to my sales memory store?▼

To add a new customer insight to your sales memory store, use the memory:add command followed by the text string of the insight. This saves the extracted customer fact or conversation detail into a local vector-backed directory for persistent storage and future semantic recall.

Can I set automatic expiration for time-sensitive market signals in a vector store?▼

Yes, you can set automatic expiration for time-sensitive market signals using typed TTL rules. This lifecycle control allows you to keep permanent customer facts while ensuring time-sensitive insights expire automatically, keeping your sales context clean and relevant.

Does this semantic memory engine work for multi-channel SDR workflows?▼

Yes, this semantic memory engine is designed for multi-channel SDR workflows. It captures effective scripts and customer preferences across channels, then retrieves the most relevant items to improve relevance and continuity during future outreach turns.

What are the limitations of using a local vector-backed directory for sales context?▼

Using a local vector-backed directory for sales context limits accessibility to a single local environment rather than a distributed cloud setup. Memory operations rely on command-driven add, search, list, forget, and stats functions without native external API synchronization.