#llm-tools

A declarative language that compiles to professional SVG floor plans — like Typst/LaTeX, but for architecture. Built for AI agents: deterministic output, JSON diagnostics that carry their own fix, and a describe/lint channel that verifies a plan against its brief without rendering an image. Zero-dependency TypeScript.

Structured planning, bounded memory, TDD, and Git guardrails for local coding models in Pi Code (I don't know TypeScript at all; this is mostly a local-model experiment, with occasional help from Claude Code)

Decantr AI design intelligence layer for AI-generated web applications

RuvNet Brain — a downloadable, source-grounded brain for Claude Code over Reuven Cohen's (rUv's) RuvNet stack: RuVector/RVF, Ruflo, AgentDB, RuLake, SPARC + 21 building blocks. Grounds Claude in real source via one MCP tool (search_ruvnet), so it builds with the stack instead of drifting off it.

A local-first, file-based memory CLI for AI tools. Own your context in plain Markdown — auditable, versionable, and provider-agnostic.

Control plane for Claude Code agents across many repos — durable personas, per-task workspaces, and a credential vault the model never reads from