hierarchical-memory

Manages short-term, long-term, and episodic memory layers with Qdrant vector search.

Updated Mar 23, 2026

Search Tags:#semantic search #memory management #ai agent #vector search #qdrant #knowledge retention #episodic memory

Ready to run

npx skills add https://github.com/sakamotomomotaro0809-netizen/tateyomi --skill hierarchical-memory-sakamotomomotaro0809-netizen

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: hierarchical-memory
Source: https://github.com/sakamotomomotaro0809-netizen/tateyomi/tree/main/taisun_agent/.claude/skills/hierarchical-memory
Command: npx skills add https://github.com/sakamotomomotaro0809-netizen/tateyomi --skill hierarchical-memory-sakamotomomotaro0809-netizen

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI agents lose context between sessions and struggle to recall past decisions, patterns, and solutions. This Skill provides a three-layer memory architecture that captures, consolidates, and retrieves knowledge across sessions. ## Core Features & Use Cases - Three Memory Layers: Short-term session memory (in-memory store), long-term semantic memory (Qdrant vector database), and episodic memory (timestamped observation logs). - Automatic Consolidation: Session-end hooks migrate important patterns from short-term to long-term storage and log decisions to episodic records. - Semantic Retrieval: Vector similarity search via Qdrant finds relevant past knowledge even when queries use different wording. - Use Case: A developer asks the agent to remember an authentication pattern; it is stored in Qdrant with metadata tags, and weeks later a semantic search for "auth implementation" retrieves it instantly. ## Quick Start Ask the agent to store an important code pattern in long-term memory and later retrieve it with a semantic search query.

Frequently Asked Questions about hierarchical-memory

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

FAQPage Schema

How do I give an AI agent persistent memory across sessions?▼

Use a layered memory architecture: store session context in a short-term in-memory store, persist important patterns in a Qdrant vector database, and log decisions as episodic records. Consolidation hooks migrate key information at session end.

What is the difference between short-term, long-term, and episodic memory?▼

Short-term memory holds current session context with token-based search and a 100-item limit. Long-term memory stores permanent knowledge in Qdrant with vector similarity search. Episodic memory records timestamped decisions and events in JSONL files retained for 30 days.

How does semantic memory search work with Qdrant?▼

Text is converted to vector embeddings and stored in a Qdrant collection on localhost:6333. Queries are embedded the same way, and Qdrant returns the most similar stored entries, enabling retrieval even when wording differs from the original.

Why is my agent not finding stored memories?▼

First verify Qdrant is running by checking localhost:6333/health, then confirm the target collection exists. If retrieval is still empty, make the search query more specific or check whether consolidation hooks ran at session end.

What are the limitations of vector-based long-term memory?▼

Vector search can return loosely related results for vague queries, so metadata tags like topic and priority should be added when storing. Outdated patterns also accumulate over time and require periodic cleanup to keep retrieval accurate.