Active development
In progress. Real code, not yet shown publicly anywhere else.
Design Bench · Holding AGI accountable
Sovereign AI IDE runtime
A local-first, offline-capable governance core for an IDE: immutable signed decision records, an append-only governance journal with replay, and a four-channel evidence firewall around retrieval.
Active developmentinternal designation — Sovereign-IDE
In more detail
Python 3.12, with policy-gated mutations, quorum approvals, and a governed model registration and training-job lifecycle sitting underneath an Electron workbench shell. It's the only one of the previously-unlisted 00-Active projects actually pushed to a named public GitHub remote (IAmSoThirsty/Governance-IDE), rather than living purely as a local working directory.
Recent commit history culminates in work attesting the LLC's own local sovereign production deployment — this is the runtime the rest of the corpora and manifests below (State Register, the V4 corpus, the V3Q manifest) are built to plug into, not a separate parallel effort.
Concrete specifics
- ·Pushed to a real GitHub remote: github.com/IAmSoThirsty/Governance-IDE
- ·22 Python source files plus a dedicated policies/schemas/scripts tree
- ·15 most recent commits are all feature and hardening work, not scaffolding
Directly related
Constitutional ratification & signing package
The machine-readable enforcement package for a fail-closed action gate — CEL-based rule evaluation, Ed25519-signed authority and approval documents, and an independent out-of-process evaluator — currently pending the owner's own cryptographic ratification signature.
Deterministic training & epoch authority
A constitutional model-training and state-authority system — deterministic curriculum generation, signed checkpoints, an epoch controller, a hostile-audit validation suite. Its own docs are explicit that current validation runs against a simulated backend, not completed real-model training.
Go deeper