Engineering tools for specs-driven development and predictive modelling.

CognitiveSDD: From requirements to verified artefacts

CognitiveSDD is a specs-driven workflow orchestrator that walks AI coding agents and AI modelling agents through phase-gated projects — from user stories or system needs to verified, traceable artefacts — inside network-firewalled containers. A single workflow engine, INCOSE-compliant requirements discipline, ADR-backed architecture, end-to-end @req / @story traceability, and a defense-in-depth security model apply to both project categories.

Software Projects (Python, TypeScript, C/C++, Go, Rust)

For software developers, CognitiveSDD orchestrates a structured workflow through user story discovery, requirements derivation, architecture design with ADRs, test specification with traceability markers, autonomous implementation inside firewalled containers, and full verification — producing source code, automated test suites, and a traceable build where every test links back to its requirement.

Engineering Projects (SysML v2 MBSE)

For systems engineers, CognitiveSDD applies the same phase-gated discipline to Model-Based Systems Engineering. The orchestrator guides the AI through stakeholder needs elicitation, INCOSE-compliant requirements (materialised as requirement def elements), structural architecture (part def, ports, interfaces), verification specs (verification case def stubs), and behavioural modelling — producing a complete SysML v2 model with end-to-end requirement-to-verification traceability.

CognitiveEstimator: Automated predictive modeling

CognitiveEstimator is our specialized tabular regression and probability calibration library designed for applied engineering. It turns tabular in-memory data tables (such as simulation runs, time-series data, or cost parameters) into calibrated, deterministic, dict-in/dict-out predictors under a strict execution budget, providing honest conformal uncertainty intervals and bit-identical reproducibility.

Code provided as open source

CognitiveSand publishes developer tools under the MIT license, allowing developers to audit, extend, and integrate our core utilities directly from our repositories.

Discover agents-sync on GitHub

agents_sync is a cross-platform background daemon that keeps user-level custom agents and skills bidirectionally synchronised across Claude Code, Codex, Antigravity, and OpenCode. It allows engineering teams to construct their AI workflows and custom skills once, then execute them seamlessly from every developer tool installed in their local environments.

Discover scan-supply-chain on GitHub

scan-supply-chain acts as a security validation filter that detects indicators of compromise from PyPI and npm supply chain attacks before dependency compilation. Using extensible TOML threat profiles and blast radius mapping, it scans third-party manifests to alert engineers of rogue lifecycle scripts or unauthorized network sockets.