graph-recall

Retrieve long-term memory via vector search and recursive graph traversal on SQLite.

Updated Jul 14, 2026

Search Tags:#knowledge graph #ai agents #memory #sqlite #vector search #context expansion

Ready to run

npx skills add https://github.com/roy2392/scout-graph-memory --skill graph-recall-roy2392

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: graph-recall
Source: https://github.com/roy2392/scout-graph-memory/tree/main/skills/graph-recall
Command: npx skills add https://github.com/roy2392/scout-graph-memory --skill graph-recall-roy2392

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires better-sqlite3, sqlite-vec, @huggingface/transformers, and includes scripts (resource) components.

What problem does it solve?

This skill solves the problem of unbounded, disconnected memory growth in AI agents by providing a structured, graph-based retrieval system that maintains semantic relationships between facts.

Core Features & Use Cases

Semantic Graph Recall: Performs vector-based similarity searches combined with recursive graph traversal to find related entities and facts.
Context Expansion: Automatically enriches user queries with relevant 1-hop and 2-hop graph connections to provide deeper, grounded answers.
Use Case: When an agent is asked about a specific incident, this skill retrieves the incident details and automatically pulls in related system components and prior decisions to provide a comprehensive, context-rich response.

Quick Start

Use the graph-recall skill to retrieve and expand memory context for the user query regarding the recent system incident.

Frequently Asked Questions about graph-recall

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

FAQPage Schema

How do I implement long-term memory retrieval for AI agents using a knowledge graph?▼

Long-term memory retrieval for AI agents is implemented by combining vector-based semantic search with recursive graph traversal on a SQLite database to identify and expand context for entities, incidents, and historical threads.

How does context expansion work when querying an AI agent memory database?▼

Context expansion automatically enriches user queries by retrieving relevant 1-hop and 2-hop graph connections, pulling in related system components and prior decisions to provide a comprehensive, grounded response.

Do I need a pre-populated SQLite database to perform semantic graph recall?▼

Yes, semantic graph recall requires a pre-populated memory database and the sqlite-vec extension to perform high-precision semantic lookups and recursive graph traversal effectively.

What is the best way to structure unbounded memory growth for AI agents?▼

The best way to structure unbounded memory growth is using a graph-based retrieval system that maintains semantic relationships between facts in a SQLite-backed knowledge graph, preventing disconnected memory expansion.

Can I use sqlite-vec for vector search in an AI agent memory system?▼

Yes, you can use sqlite-vec for vector-based similarity searches combined with recursive graph traversal to find related entities and facts within a SQLite-backed knowledge graph.

What are the limitations of using graph-based retrieval for AI agent memory?▼

Graph-based retrieval requires a pre-populated memory database to function, meaning it cannot perform semantic lookups or context expansion on empty datasets or without the sqlite-vec extension installed.