nhadaututthekynhadaututthekyCommunityยท4 Agent Skills Included

neural-memory

Persistent graph memory with associative recall across sessions

Stores decisions, errors, and facts as interconnected neurons and recalls them through spreading activation instead of keyword search. Eliminates lost context between sessions, repeated mistakes, and costly embedding API calls. Includes intake, audit, and evolution workflows that keep stored knowledge clean, current, and easy to retrieve.
npx skills add nhadaututtheky/neural-memory --all -g -y
Available:

Instructs the agent on when to save memories, how to recall them at the right depth, and how to run the session lifecycle from recap to final flush.

All Skills in This Repository (4)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install Neural Memory?โ–ผ

Run `npx skills add nhadaututtheky/neural-memory --all -g -y` in your terminal to install all skills in this suite globally.

How to give an AI agent persistent memory?โ–ผ

Neural Memory stores experiences as a connected neuron graph locally, so your agent recalls past decisions and context in every new session without any cloud service.

Does Neural Memory need a vector database or API keys?โ–ผ

No. It runs fully offline on local SQLite using graph traversal and spreading activation, so there are no embedding costs or external dependencies.

Does Neural Memory work with Claude Code and OpenClaw?โ–ผ

Yes. It ships as a plugin and MCP server that works with Claude Code, OpenClaw, Cursor, and other MCP-compatible clients.

How do I keep stored memories clean over time?โ–ผ

Use the built-in memory-audit and memory-evolution skills to find duplicates, resolve contradictions, prune stale entries, and improve recall quality.

Related Repositories in Software Engineering

View All in Software Engineeringโ†’