knowledge-base-cache

What problem does it solve?

Create and manage a layered knowledge base with hot/cold/warm caches to reduce API costs and enable scalable knowledge retrieval.

Core Features & Use Cases

• Layered architecture (hot cache, cold storage, warm vector layer) with automatic context assembly and token budgeting
• Working Memory layer to coordinate multi-source inputs and assemble relevant context
• Auto-refresh and cache-management tools to keep knowledge fresh with minimal manual intervention
• Script-driven tooling to build, validate, and reuse knowledge assets across AI agents

Quick Start

Initialize the knowledge base structure and run the cache manager to initialize and build the hot cache.