LeanKG: Stop Burning Tokens. Start Coding Lean.

Local-first semantic memory engine for AI agents - scores, trusts, and forgets so your agent stops making the same mistake twice.

Memory as advisory for LLM agents — forgets noise, keeps what matters. Lazy exponential decay, four-op API, OpenUSD cold tier. Python ≥3.11. Patent-pending.

A modern web application for generating, exploring, and curating color palettes, integrated with a design-focused AI assistant and automated synchronization with Notion.