skills.rest
Wike-CHI
Wike-CHICOMMUNITY
Explore all skills by this author →
WebsiteGitHub

supermemory

Store and semantically index non-dialog knowledge with vector embeddings and LanceDB.

2|Updated Mar 31, 2026
Search Tags:#memory#lancedb#semantic-search#vectors#ttl#market-intelligence
One-click install
npx skills add https://github.com/Wike-CHI/acquisition-agent --skill supermemory-wike-chi
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: supermemory
Source: https://github.com/Wike-CHI/acquisition-agent/tree/main/skills/supermemory
Command: npx skills add https://github.com/Wike-CHI/acquisition-agent --skill supermemory-wike-chi

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Supermemory captures, persists, and retrieves non-dialogual knowledge and operational insights to prevent information loss across sales and market research workflows, enabling agents to act on structured facts and unstructured signals with TTL-aware retention.

Core Features & Use Cases

  • Persistent semantic store for customer facts, market signals, competitor intelligence, and effective outreach scripts using vector embeddings.
  • TTL and lifecycle management with configurable retention per memory type and scheduled automatic cleanup to avoid stale context.
  • Query and operational commands including memory:add, memory:search, memory:list, memory:delete, and memory:stats for programmatic ingestion and semantic retrieval.
  • Integrations with LanceDB-backed storage, embedding models, and an L1 MemOS collaboration pattern for combined structured and unstructured memory use in B2B acquisition scenarios.

Quick Start

Add a customer_fact entry describing Al Rashid Industries' procurement scale, tag it with saudi_arabia and tire_manufacturer, set source to linkedin and confidence to 0.9.

Frequently Asked Questions about supermemory

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

FAQPage Schema
How do I store and retrieve market intelligence using semantic search?▼

You can store and retrieve market intelligence using semantic search by applying vector embeddings to index unstructured signals and operational insights, enabling reliable programmatic retrieval through command APIs.

How do I manage stale context and retention policies for vector embeddings?▼

Manage stale context for vector embeddings by applying TTL and lifecycle management with configurable retention periods per memory type, ensuring scheduled automatic cleanup prevents outdated information from polluting retrieval.

How do I capture B2B customer facts and competitor intelligence for acquisition workflows?▼

Capture B2B customer facts and competitor intelligence for acquisition workflows by storing structured operational insights in a persistent semantic store, tagging entries with relevant metadata like source and confidence for reliable retrieval.

Can I use LanceDB for non-dialog memory storage in market research?▼

Yes, you can use LanceDB for non-dialog memory storage in market research as it serves as the backing database for vector embeddings, supporting the ingestion and semantic retrieval of unstructured market signals.

What is the best way to programmatically add and search operational insights?▼

The best way to programmatically add and search operational insights is using command APIs like memory:add for ingestion and memory:search for semantic retrieval, allowing structured facts to be queried reliably.

Does TTL-aware retention work with semantic memory for competitor intelligence?▼

Yes, TTL-aware retention works with semantic memory for competitor intelligence by applying scheduled automatic cleanup and configurable retention policies per memory type to avoid stale context during retrieval.

Related Skills

Explore More Marketing & Sales Skills→
heysuhasheysuhas
2

chroma

Manage vector embeddings and metadata in a local-first database for semantic search and RAG applications.

Community
Intermediate
iPythoningiPythoning
152

graphify

Build queryable knowledge graphs from B2B sources and export results to graphify-out/.

Community
Intermediate
DoubleslashSEDoubleslashSE
4

cqs-patterns

Teach and enforce CQRS patterns in .NET applications.

Community
Basic
hiyenwonghiyenwong
2

chat-history-lancedb

Store and search chat histories locally with LanceDB vector embeddings and RAG retrieval.

Community
Advanced