skills.rest
phonowell
phonowellCOMMUNITY
Explore all skills by this author →
GitHub

memory-systems

Stores and retrieves cross-session memories with vector search and graph-based entity relationships.

1|Updated Jan 27, 2026
Search Tags:#agent#retrieval#memory#persistence#consolidation#graph#vector-search
One-click install
npx skills add https://github.com/phonowell/mimikit --skill memory-systems-phonowell
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-systems
Source: https://github.com/phonowell/mimikit/tree/main/.agents/skills/context-engineering-collection/skills/memory-systems
Command: npx skills add https://github.com/phonowell/mimikit --skill memory-systems-phonowell

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Agents often lose continuity across sessions because memory isn't persisted, leading to repetitive context and wasted time. This skill provides a unified memory layer that combines vector-based semantic search with graph-based entity relationships and temporal validity, enabling cross-session recall and reasoning.

Core Features & Use Cases

  • Cross-session memory persistence for agents
  • Semantic recall via vector search combined with entity graphs and temporal validity
  • Contextual enrichment by retrieving related relationships and memories for a given entity

Quick Start

Start a memory session, store a fact about an entity, and then retrieve memories related to a query.

Frequently Asked Questions about memory-systems

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

FAQPage Schema
How do I persist agent memory across sessions with high retrieval fidelity?▼

Cross-session memory persistence for agents combines vector-based semantic search with property graphs and temporal validity graphs, enabling recall and reasoning over histories.

What's the best way to maintain entity continuity for an agent using a property graph?▼

Maintain entity continuity by storing facts in a property graph for entities combined with a temporal memory graph, supporting time-bound queries and cross-session reasoning.

Can I perform just-in-time loading and consolidation for agent memories using numpy?▼

Yes, this memory system requires only numpy as a dependency to perform just-in-time loading and consolidation of cross-session agent memories.

How does vector search work with graph-backed relationships for contextual memory retrieval?▼

Vector search retrieves semantically related memories while graph-backed relationships provide contextual enrichment by retrieving related entities and their connections for a given query.

When do I need a temporal memory graph for agent memory persistence?▼

A temporal memory graph is needed when agents must reason over histories and perform time-bound queries requiring temporal validity checks across persisted cross-session knowledge.

Related Skills

Explore More Software Engineering Skills→
Alex1980AlexAlex1980Alex

pdf-knowledge

Index PDFs into vector and graph knowledge stores for search and extraction.

Community
Advanced
FVossebeldFVossebeld

memory-systems

Store and retrieve structured memories with vector and graph search.

Community
Advanced
MichielDeanMichielDean

llmem

Store and retrieve LLM memories in SQLite with semantic search.

Community
Advanced
muratcankoylanmuratcankoylan
17.7k

memory-systems

Persist agent memory across sessions using multi-layer architecture and temporal knowledge graphs.

Community
Advanced