general-agentic-memory

Community

Dual-agent memory for deeper AI agent reasoning.

Authoryuyijiong
Version1.0.0
Installs0

System Documentation

What problem does it solve?

The GAM approach delivers Just-in-Time memory optimization and iterative retrieval for AI agents, enabling structured long-term memory and guided research at query time.

Core Features & Use Cases

  • Just-in-Time memory construction: MemoryAgent builds abstracts from documents and stores associated pages for on-demand retrieval.
  • Iterative deep research: ResearchAgent performs planning, search, integration, and reflection to answer complex, multi-hop questions.
  • Flexible retrieval: supports keyword (BM25), vector (dense), and page-index retrieval to cover diverse information needs.
  • Use cases: building agents that require deep research over stored memories, multi-hop QA, or context-rich assistants that reason over context.

Quick Start

Trigger the GAM skill with a query that requires deep research over stored memories to produce an integrated answer.

Dependency Matrix

Required Modules

None required

Components

references

💻 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: general-agentic-memory
Download link: https://github.com/yuyijiong/paper-to-skill/archive/main.zip#general-agentic-memory

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 223,000+ vetted skills library on demand.