Enables AI agents to search, read, and traverse a local knowledge base of Markdown files using full-text search and relationship graph, reducing token usage.
Indexes installed SKILL.md files and provides deterministic search and recommendation tools to help AI agents select relevant skills without executing them.
Enables AI agents to perform hybrid semantic+keyword search over structured markdown lairs and memory files, with tools for protocol checks and anti-pattern detection.
Provides context-aware skill selection for AI agents, reducing token usage by 85-98% and improving accuracy through semantic retrieval, session memory, and feedback learning.