CORE

Executable constitutional governance for AI-assisted software development.

AI coding tools generate code fast. Too fast to stay sane.

Without enforcement, AI-assisted codebases accumulate invisible debt — layer violations, broken architectural contracts, files that grow unbounded. And agents, left unconstrained, will eventually do something like this:

Agent: "I'll delete the production database to fix this bug"
System: Executes.
You:    😱

CORE makes that impossible — not detectable after the fact. Impossible.

Agent: "I'll delete the production database to fix this bug"
Constitution: BLOCKED — Violates data.ssot.database_primacy
System: Execution halted. Violation logged.
You:    😌

CORE is a governance runtime that constrains AI agents with machine-enforced constitutional law — enforcing architectural invariants, blocking invalid mutations automatically, and making autonomous workflows auditable and deterministic.

LLMs operate inside CORE. Never above it.

Blocking rule → targeted drilldown → automated remediation → verified compliance.

This demo shows:

• A structural violation (linkage.assign_ids)
• Deterministic blocking of execution
• Rule-level audit inspection
• Automated remediation via core-admin dev sync --write
• Verified compliance after repair

Governance is executable.

CORE separates responsibility into three constitutional layers. This separation is enforced as law — not convention.

Where humans define what the system is for and why decisions were made. Contains architectural papers, northstar documents, user requirements, architectural decision records, and planning documents. This is the entry point for anyone trying to understand CORE before reading its implementation.

.specs/ is read by humans and searchable by CORE's semantic layer. It is never written by CORE itself.

Defines what is allowed, required, or forbidden. Contains machine-readable constitutional rules, enforcement mappings, phase-aware governance models, and the authority hierarchy (Meta → Constitution → Policy → Code).

Mind never executes. Mind never mutates. Mind defines law.

Reads constitutional constraints, orchestrates autonomous reasoning, and records every decision with a traceable audit trail. Every operation follows a structured phase pipeline:

INTERPRET → PLAN → GENERATE → VALIDATE → STYLE CHECK → EXECUTE

Will never bypasses Body. Will never rewrites Mind.

Deterministic, atomic components: analyzers, evaluators, file operations, git services, test runners, CLI commands.

Body performs mutations. Body does not judge. Body does not govern.

Every autonomous operation is governed by the same constitutional loop:

flowchart TD
    A["🟢 GOAL\nHUMAN INTENT"] --> B["📂 CONTEXT\nRepo state • knowledge • history"]
    B --> C["🔒 CONSTRAINTS\nImmutable rules\n120 rules • 7 engines"]
    C --> D["🗺️ PLAN\nStep-by-step reasoning\nRule-aware plan"]
    D --> E["✨ GENERATE\nCode • changes • tool calls"]
    E --> F["✅ VALIDATE\nDeterministic checks\nAST • semantic • intent • style"]
    F -->|Pass| G["▶️ EXECUTE\nApply compliant changes"]
    F -->|Fail| H["🔄 REMEDIATE\nRepair violation\nAutonomy Ladder"]
    H --> E
    G --> I["✓ SUCCESS\nChanges committed"]

    subgraph "SAFETY HALT"
        direction TB
        J["🚨 CONSTITUTIONAL VIOLATION\n→ HARD HALT\n+ FULL AUDIT LOG"]
    end

    E -.->|Any violation| J
    F -.->|Any violation| J

    classDef phase      fill:#f8f9fa,stroke:#495057,stroke-width:2px
    classDef constraint fill:#d1e7ff,stroke:#0d6efd,stroke-width:2.5px
    classDef validate   fill:#fff3cd,stroke:#ffc107,stroke-width:2.5px
    classDef halt       fill:#ffebee,stroke:#dc3545,stroke-width:3px

    class A,B,D,E,G,I phase
    class C constraint
    class F validate
    class J halt

Within CORE:

• No file outside an autonomy lane can be modified
• No structural rule can be bypassed silently
• No database action occurs without authorization
• All decisions are phase-aware and logged with full decision traces
• No agent can amend constitutional law

If a blocking rule fails, execution halts. No partial states.

Enforcement strengths: Blocking · Reporting · Advisory

Deterministic when possible. LLM only when necessary.

120 rules across 126 policies. 121 executable.

CORE progresses through defined levels. Each adds capability while remaining constitutionally bounded.

A0 — Self-Awareness       ✅  Knows what it is and where it lives
A1 — Self-Healing         ✅  Fixes known structural issues automatically
A2 — Governed Generation  ✅  Natural language → constitutionally aligned code
A3 — Governed Autonomy    🎯  Daemon finds, proposes, and fixes violations unattended  ← current
A4 — Self-Replication     🔮  Writes CORE.NG from its own understanding of itself

git clone https://github.com/DariuszNewecki/CORE.git
cd CORE
poetry install

cp .env.example .env
make db-setup

# Run a constitutional audit
poetry run core-admin code audit

Full documentation, architecture deep-dive, and governance reference: dariusznewecki.github.io/CORE

To understand what CORE is for before reading its implementation, start here: .specs/northstar/CORE-What-It-Does.md

Current Release: v2.2.2

Active work: A3 Governed Autonomy — the daemon runs continuously, finds constitutional violations in its own codebase, proposes fixes, executes approved changes, and verifies the result. The governor's role is to define intent, review proposals that require architectural judgment, and approve constitutional changes.