Nucleus

This is a file-based memory and governance layer that sits between your AI tools and your codebase. It exposes 114 MCP tools across memory (engrams that persist cross-session), execution verification (5-tier GROUND checks from syntax to runtime), human-in-the-loop corrections (ALIGN), and compliance configs for EU DORA, Singapore MAS TRM, and SOC2. The core workflow is machine verifies, human corrects, system learns. Each correction automatically generates a training pair and audit event. No embeddings, no vendor lock-in, just JSON and markdown in a `.brain` folder. Use it when you're tired of re-explaining the same context every session or when you need audit trails for regulated environments.