skills.rest
cablate
cablateCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

vector-memory

Store and retrieve facts, decisions, and lessons across sessions.

15|1|Updated Mar 17, 2026
Search Tags:#knowledge management#semantic search#persistent memory#long-term storage#vector memory#context recall
One-click install
npx skills add https://github.com/cablate/ai-toolkit --skill vector-memory-cablate
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vector-memory
Source: https://github.com/cablate/ai-toolkit/tree/main/skills/vector-memory
Command: npx skills add https://github.com/cablate/ai-toolkit --skill vector-memory-cablate

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables long-term storage and retrieval of knowledge, facts, and decisions across sessions to maintain context continuity.

Core Features & Use Cases

  • Knowledge Retention: Store facts, decisions, lessons, and preferences for quick search later.
  • Semantic Recall: Retrieve relevant information based on natural language queries to support ongoing tasks.
  • Use Case: Remembering user preferences throughout a project or recalling past decisions when making new ones.

Quick Start

Use the vector-memory skill to store a new fact about the project and retrieve it later when needed.

Frequently Asked Questions about vector-memory

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

FAQPage Schema
How does semantic search work for persistent memory across sessions?▼

Semantic search enables persistent memory by storing facts and decisions in a searchable format, allowing natural language queries to retrieve relevant context across sessions. It uses retrieval and decay models to maintain memory relevance over time.

How do I store and recall project decisions for long-term knowledge management?▼

Long-term knowledge management stores project decisions, facts, and lessons using persistent vector memory, enabling semantic recall through natural language queries to support ongoing tasks and maintain context awareness.

Can I use vector memory to maintain context awareness for software engineering tasks?▼

Vector memory maintains context awareness for software engineering by persistently storing facts and decisions, implementing retrieval and decay models to keep relevant information accessible across multiple sessions.

What is the best way to retrieve past lessons and preferences when making new project decisions?▼

The best way to retrieve past lessons is using semantic search on persistent memory, which matches natural language queries to stored facts and preferences to support new decision-making workflows.

Does persistent memory handle decay to ensure memory relevance over time?▼

Persistent memory handles decay by implementing retrieval and decay models that manage stored facts and decisions, ensuring memory relevance is maintained as project contexts evolve over time.

Related Skills

Explore More Software Engineering Skills→
gatovillanogatovillano

retrieval-augmented-generation

Retrieve user-specific information via semantic search and knowledge graph analysis.

Community
Advanced
raydocsraydocs

memory-scout

Search .flow/memory files for relevant pitfalls, conventions, and decisions.

Community
Intermediate
TheTesseractAITheTesseractAI

project_tasks

Create, track, and update persistent project tasks with dependencies and states.

Community
Intermediate
NITISH-gitbitNITISH-gitbit

qmd

Combine BM25 keyword matching, vector semantic search, and LLM reranking for local Markdown file retrieval.

Community
Intermediate