knowledge-graph

Organize a three-layer memory system with entity knowledge, daily notes, and persistent memory.

239|30|Updated Jan 22, 2026

Search Tags:#AI agents #memory #cron #knowledge-graph #facts.jsonl #living-summaries #entity-lookup

Ready to run

npx skills add https://github.com/jdrhyne/agent-skills --skill knowledge-graph-jdrhyne

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: knowledge-graph
Source: https://github.com/jdrhyne/agent-skills/tree/main/clawdbot/knowledge-graph
Command: npx skills add https://github.com/jdrhyne/agent-skills --skill knowledge-graph-jdrhyne

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

AI agents often forget context across sessions; this skill provides a durable three-layer memory system to retain and enrich knowledge over time, reducing repeated context gathering.

Core Features & Use Cases

Three-Layer Memory: Entity Knowledge (life/areas), Daily Notes (memory), and Persistent Memory (MEMORY.md) for long-term context.
Automated Fact Extraction & Synthesis: Cron-driven extraction of durable facts and weekly synthesis to keep living summaries fresh.
Fast Entity Lookup: Efficient retrieval via summary.md and selective loading of facts.jsonl to balance performance and detail.

Quick Start

Create workspace structure as documented, initialize first entities with summary.md and facts.jsonl, and enable the fact-extraction cron and weekly-synthesis cron as described in SKILL.md. Use the entity lookup flow to fetch lightweight context from summary.md, and load facts.jsonl only when deeper detail is required.

Frequently Asked Questions about knowledge-graph

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

FAQPage Schema

How do I give my AI agents persistent memory across sessions?▼

To give AI agents persistent memory, this skill organizes a three-layer system with entity knowledge, daily notes, and persistent MEMORY.md, ensuring durable fact extraction and reducing repeated context gathering across sessions.

How does cron-driven fact extraction work for AI agent memory?▼

Cron-driven fact extraction works by scheduling automated workflows that pull durable facts from daily notes and append them to facts.jsonl with auto-incremented IDs, keeping living summaries fresh.

What is the best way to structure entity lookup for AI agents?▼

The best way to structure entity lookup is fetching lightweight context from summary.md first, then loading facts.jsonl only when deeper detail is required, balancing performance and context retrieval.

Can I use this memory system across multi-agent workspaces?▼

Yes, you can use this memory system across multi-agent workspaces. It applies the three-layer memory architecture to single or multi-agent setups for shared durable fact extraction and context retrieval.

How do I set up weekly synthesis for living summaries?▼

To set up weekly synthesis for living summaries, initialize entities with summary.md and facts.jsonl, then enable the weekly-synthesis cron as described in the skill documentation to refresh summaries.

Why does my AI agent forget context without persistent memory layers?▼

AI agents forget context because they lack durable storage. Without persistent memory layers like entity knowledge and facts.jsonl, agents must repeatedly gather context instead of retrieving atomic facts.