Functional, extensible L-System architecture w/ support for probabilistic rules
Node.js bindings for the NLP++ text-analysis engine (peer of the Python package NLPPlus)
isettingkit is a modular UI toolkit designed to streamline the creation and management of business rule-driven interfaces. It offers a suite of reusable components, utilities, and type definitions to facilitate the development of dynamic, rule-based forms
The Ring-0 agentic orchestration core (ADR-0044): the intent→plan→execute→observe loop, the Planner + ToolInvoker ports, and a deterministic rule-based planner. A first-party app expresses a goal; the loop plans which tools compose to satisfy it and runs
Stage 2.7 of the runtime pipeline — propose coherent input units (boundary discovery) with a structural kind hypothesis + confidence. Rule-based v1 (port of v1 section/sub-section logic); learned 1-2M-param span proposer reserved for v0.5.1.
Stage 2 of the runtime pipeline — derive a LocaleHint from QueryShape (script + known-format hits). Rule-based v1; trained classifier deferred to v0.6.0.
Stage 2.5 of the runtime pipeline — categorize inputs by query shape (postcode_only / locality_only / structured_address / intersection / po_box / landmark / vague). Rule-based for v1.
Mailwoman rule-based classifiers.
Rule-based 3D filtering and colorization for IFC models
Automated rule-based trading system for Polymarket with real-time WebSocket price updates.
Pillar-2 model-driven MutationProvider — asks Claude to rewrite the prompt given dev-set failures. Closes the v0 prompt-optimizer's L91 'rule-based-only' gap.