How does CORE actually stop an AI agent from making a dangerous change?

CORE runs the AI agent inside its governance system, never above it. Before execution, generated code is validated against constitutional rules (215 rules across 15 engines). If a violation is detected, execution halts with no partial state change and logs the violation. The agent cannot proceed until the violation is remediated or approved by the proper authority.

What kind of rules can CORE enforce?

Constitutional rules block unconditionally. Policy rules block when strict_mode is enabled, otherwise report. Advisory rules and capability tier currently report violations without blocking (blocking for capability tier is under review in ADR-079). The governance directory itself (.intent/) is immutable—no component can rewrite the rules.

Can I see an audit trail of what CORE approved or blocked?

Yes. CORE records every action with a complete consequence chain showing finding, proposal, approval authority, execution time, and file changes with commit hashes. Two examples are shown live in the documentation: one for autonomous self-approved changes and one for changes requiring human governor approval. Both are queryable end-to-end.

Back to articlesAI Regulation & Policy

AI Regulation & Policy

CORE: Open-source governance layer blocks AI agents from dangerous code changes

Hacker News10h ago5 min read

Key takeaway

CORE is an open-source governance runtime that constrains AI agents with machine-enforced constitutional rules, blocking invalid code mutations automatically before execution. The tool makes autonomous AI workflows auditable and deterministic by logging every action's decision chain and enforcing architectural invariants structurally, rather than detecting violations after the fact. It is available now as a pip-installable package.

Summaries like this, in your inbox every morning.

3 Key Points

What happened
A new tool called CORE enforces constitutional rules on AI coding agents, structurally blocking violations before execution—for example, preventing an agent from deleting a production database. Every action is logged with a complete audit trail showing finding, proposal, approval, execution, and file change.
Why it matters
AI coding tools generate code faster than teams can review it, creating invisible technical debt and architectural violations. CORE makes dangerous mutations impossible by moving enforcement from after-the-fact detection to hard barriers before any code runs, giving developers deterministic control over autonomous workflows.
What to watch
CORE is available now on pip (version 2.x, beta stage) and can be tested immediately with a Docker command that runs a live governance demo. The system separates four repository layers—specs (human intent), mind (law), will (judgment), and body (execution)—enforced as constitutional law, not convention.

FAQ

How does CORE actually stop an AI agent from making a dangerous change?: CORE runs the AI agent inside its governance system, never above it. Before execution, generated code is validated against constitutional rules (215 rules across 15 engines). If a violation is detected, execution halts with no partial state change and logs the violation. The agent cannot proceed until the violation is remediated or approved by the proper authority.
What kind of rules can CORE enforce?: Constitutional rules block unconditionally. Policy rules block when strict_mode is enabled, otherwise report. Advisory rules and capability tier currently report violations without blocking (blocking for capability tier is under review in ADR-079). The governance directory itself (.intent/) is immutable—no component can rewrite the rules.
Can I see an audit trail of what CORE approved or blocked?: Yes. CORE records every action with a complete consequence chain showing finding, proposal, approval authority, execution time, and file changes with commit hashes. Two examples are shown live in the documentation: one for autonomous self-approved changes and one for changes requiring human governor approval. Both are queryable end-to-end.

Discussion

No comments yet. Be the first to share your thoughts!

Stay ahead with AI news

Get curated AI news from 200+ sources delivered daily to your inbox. Free to use.

Get Started Free

Free · takes 30 seconds · unsubscribe anytime

1 minute a day. The AI essentials.

200+ sources · Email / LINE / Slack

Get it free →

CORE: Open-source governance layer blocks AI agents from dangerous code changes

Key takeaway

3 Key Points

FAQ

Discussion

Related Articles

MongoDB adds AI retrieval tools to fight enterprise project failures

Skyways builds global cargo drone fleet in near-total secrecy

Stripe deploys AI agents for compliance, cuts review time 26%

OpenAI's GPT-5.6 gets Trump case-by-case approval

Trump targets quantum computing breakthrough by 2028

KPMG: Boards need AI fluency to govern responsibly

Stay ahead with AI news