sys-agents

Provides industry-proven design patterns for effective AI agents based on production systems like Claude Code, Manus, and Cursor. Use when designing agent architectures, optimizing context management, or implementing sub-agent patterns.

Implements Orchestrator, Swarm, and Hierarchical patterns for preventing context saturation. Use when designing multi-agent systems for context isolation and parallel execution.

Provides unified interface for all context engineering patterns. Use when optimizing AI agent context: compression, degradation detection, KV-cache optimization, or session management.

Combines vector and keyword search for improved retrieval. Use when implementing hybrid search systems, building RAG systems, or when neither vector nor keyword approach alone provides sufficient recall.

Implements progression from Vector RAG → GraphRAG → Temporal Knowledge Graphs. Use when designing persistent memory architectures for AI agent systems.