on-device-memory-layer

Community

Persist local memory for on-device AI agents.

Authorzengbaocheng
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Device-side AI agents often struggle with persistent local memory and offline operation. This Skill provides a fully local, zero-external-dependency memory layer based on ClawMem architecture to store and retrieve memories on-device.

Core Features & Use Cases

  • Local MCP Server for unified memory operations (remember, recall, forget, search)
  • Hooks API to automatically capture memories from code
  • Hybrid Memory Decay with semantic search to keep relevant memories and decay outdated ones
  • File-based storage without a database

Quick Start

Tell your Hermes agent to enable the on-device memory layer and reference memory in its config.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: on-device-memory-layer
Download link: https://github.com/zengbaocheng/hermes-tech-hub/archive/main.zip#on-device-memory-layer

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 510,000+ vetted skills library on demand.