This is the complete technical documentation for Hindsight, a biomimetic memory system for AI agents. You get everything: the retain/recall/reflect API operations, deployment guides for Docker and Kubernetes, SDKs for Python/Node.js/Rust, and cookbook recipes for common patterns. The docs cover the four parallel retrieval strategies (semantic, BM25, graph, temporal), memory bank configuration with dispositions, and document_id mechanics for conversation threading. Start with best-practices.md for the fastest path to correct integration. The structure is well organized under references/ with API specs, developer guides, SDK docs, and working examples all separated clearly.
npx skills add https://github.com/vectorize-io/hindsight --skill hindsight-docs