memory

Persist and retrieve knowledge in a local SQLite database with optional vector embeddings.

35|3|Updated Jun 24, 2025

Search Tags:#embeddings #memory #sqlite #knowledge-management #hybrid-search #markdown-export

Ready to run

npx skills add https://github.com/intelligentcode-ai/intelligent-claude-code --skill memory-intelligentcode-ai

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: memory
Source: https://github.com/intelligentcode-ai/intelligent-claude-code/tree/main/src/skills/memory
Command: npx skills add https://github.com/intelligentcode-ai/intelligent-claude-code --skill memory-intelligentcode-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Persistent storage of knowledge and decisions to enable agents to recall context, avoid rework, and reason with prior results.

Core Features & Use Cases

Local persistence: Stores memories in SQLite and exports as Markdown for Git-traceability.
Hybrid search: Optional embeddings for semantic search alongside keyword queries.
Memory lifecycle: Write, search, update, archive, and list memories; export to Markdown; link memories; manage categories such as architecture, implementation, issues, and patterns.
Use Case: An agent captures a design decision, then later searches for related patterns and retrieves the original rationale to inform a change request.

Quick Start

To save a memory, run a write operation like: memory.write with title and summary, then search with memory.find.

Frequently Asked Questions about memory

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

FAQPage Schema

How do I store agent memory and context locally for later retrieval?▼

To store agent memory locally, you can persist knowledge and decisions in a local SQLite database. This enables agents to recall context, avoid rework, and reason with prior results through rich querying by category, tags, or semantic search.

How does hybrid search work for retrieving stored context and memories?▼

Hybrid search for retrieving memories combines traditional keyword queries with optional vector embeddings for semantic search. This approach requires installing the @xenova/transformers package to enable semantic matching alongside standard keyword retrieval.

Can I export SQLite memory logs to Markdown for Git traceability?▼

Yes, you can export stored memories from the SQLite database to Markdown. This allows you to track memory lifecycle changes, including architecture decisions and implementation patterns, within Git for version control and traceability.

Do I need Node.js and better-sqlite3 to manage local knowledge bases?▼

Yes, managing local knowledge bases requires Node.js and the better-sqlite3 package to handle SQLite database operations. You can optionally install @xenova/transformers to enable semantic search and associated tooling.

What is the best way to organize agent knowledge into categories like architecture and patterns?▼

The best way to organize agent knowledge is by managing memory categories such as architecture, implementation, issues, and patterns. You can write, update, archive, and link memories to maintain a structured local knowledge base for future reasoning.

Why use a local SQLite database for persistent agent memory instead of just text logs?▼

Using a local SQLite database for persistent agent memory provides structured storage and rich querying capabilities that text logs lack. It supports writing, updating, archiving, and semantic retrieval of design decisions, enabling agents to recall prior rationale.