Open-source AI tooling
weathership
We build open-source AI tooling for the systems that run enterprise — data warehouses, knowledge graphs, manufacturing systems, and the federated compute fabric that ties them together. Each project reads a system in motion and turns that reading into structured signal you can act on, with a paper trail an auditor would accept.
Projects
All projects →Methods
All methods →RASE — Rapid Agentic Systems Engineering
A Python-native MBSE metamodel that couples SysML v2 semantics with Reinforcement Learning with Verifiable Rewards for agent training.
Dempster–Shafer evidence fusion for column classification
Multi-source belief-function combination over a restricted frame of discernment, yielding `[Bel, Pl]` intervals at every hierarchy level.
ColBERT MaxSim late interaction
Classification by ColBERT MaxSim retrieval against an iteratively-optimized augmented controlled vocabulary, with per-text-feature analysis driving discriminative power.