Flamehaven LogoFlamehaven.space
back to selected work
engineeringPROTOTYPEPRIVATE

Flamehaven-Governance-Core

FGC is an experimental architecture for running LLM tasks through a controlled pipeline. It is best understood as a "governance wrapper" around AI usage, not as a standalone AI model.

Private Repository

This system is listed as a B2B case note. The repository itself is not public; the page is here to show the architecture thesis and engagement relevance.

About This Work

This codebase is a prototype and should not be treated as a production safety system.

Repository Overview

This codebase is a prototype and should not be treated as a production safety system.

README Core

FGC is an experimental architecture for running LLM tasks through a controlled pipeline. It is best understood as a "governance wrapper" around AI usage, not as a standalone AI model.

This repo is a rebrand/split of the former "Flamehaven-NNSL" prototype; you may still see legacy "NNSL" names in internal modules.

This codebase is a prototype and should not be treated as a production safety system.

Use & Documentation

Detailed installation, commands, examples, and deeper usage notes live in the repository README and docs.

README Map

  • What is FGC in this repo?
  • Where can it be used?
  • Architecture (high level)
  • Quick Start
  • CLI examples
  • Config and security notes

Key Signals

  • An invocation entry point with drift and stability tracking.
  • Safety checks (FlameModal) and ethics scoring (EthicsController).
  • An optional boundary layer (NCIP) for external AI providers with alignment scoring.
  • Guarded LLM calls for prototypes: one place to enforce checks and collect telemetry.
  • Research demos: drift scoring, safety/ethics heuristics, alignment scoring loops.

Announcements

synced Mar 13, 2026

No mirrored announcements yet.