skills.rest
speqqai
speqqaiOFFICIAL
Explore all skills by this author →
GitHub

context-engine

Build temporal knowledge graphs with episode, entity, and community subgraphs.

Updated Apr 27, 2026
Search Tags:#ontology#retrieval#knowledge-graph#neo4j#temporal-knowledge-graph#graphiti
One-click install
npx skills add https://github.com/speqqai/claude --skill context-engine-speqqai
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: context-engine
Source: https://github.com/speqqai/claude/tree/main/skills/read-about-context-engine
Command: npx skills add https://github.com/speqqai/claude --skill context-engine-speqqai

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Master temporal knowledge graphs for AI agents by giving them a persistent, structured memory with traceable provenance across conversations, tasks, and environments.

Core Features & Use Cases

  • Ontology-driven extraction and graph construction for agent memory
  • Bi-temporal modeling with Episode, Semantic Entity, and Community subgraphs
  • Hybrid retrieval with cosine similarity, BM25, and graph traversal, plus community-aware summarization
  • MCP server integration for live access and control of context graphs

Quick Start

Design and query temporal graphs for intelligent agent memory using Graphiti-backed pipelines, Neo4j, and Graph-augmented retrieval.

Frequently Asked Questions about context-engine

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

FAQPage Schema
How do I build a temporal knowledge graph for AI agent memory?▼

Retrieve data from a temporal knowledge graph using hybrid retrieval that combines cosine similarity, BM25 lexical search, and graph traversal. This approach returns contextually relevant subgraphs with community-aware summarization for agent reasoning.

Does context-engine work with Neo4j and MCP servers?▼

Yes, context-engine works with Neo4j and MCP servers by using Cypher-based mutations for graph updates and integrating MCP servers for live access. This enables real-time control and querying of context graphs across MCP-enabled deployments.

What is bi-temporal modeling in knowledge graphs and when do I need it?▼

Bi-temporal modeling in knowledge graphs tracks both event occurrence time and record insertion time within Episode, Entity, and Community subgraphs. You need it to give AI agents persistent memory that maintains traceable provenance across changing environments and conversations.

How do I retrieve data from a temporal knowledge graph using hybrid search?▼

DUPLICATE REMOVE

Can I use Graphiti pipelines for ontology-driven graph construction?▼

Yes, you can use Graphiti-backed pipelines for ontology-driven extraction and graph construction. This builds structured knowledge graphs for intelligent agent memory by processing data through Graphiti pipelines and Neo4j storage.

Related Skills

Explore More Software Engineering Skills→
opensage-agentopensage-agent
113

neo4j-query

Execute arbitrary Cypher queries against Neo4j graph databases to retrieve structured JSON records.

Official
Intermediate
0xUrsanomics0xUrsanomics
2

recall

Retrieve ranked context from local knowledge graphs and memory files.

Community
Advanced
Mercurium-AnalyticsMercurium-Analytics

django-pgsearch-patterns

Integrate Django with pg_search and pgvector for hybrid BM25 and vector search.

Official
Advanced
ChakshuGautamChakshuGautam

memory-systems

Stores and retrieves agent memories via vector store and temporal knowledge graph with entity/time filters.

Community
Advanced