cd /news/ai-safety/the-neutral-proof-standard-for-conse… · home topics ai-safety article
[ARTICLE · art-51777] src=github.com ↗ pub= topic=ai-safety verified=true sentiment=· neutral

The neutral proof standard for consequential AI-agent actions

Actenon released a set of open-source tools that cryptographically gate AI agents from executing unauthorized consequential actions such as payments, deletions, and deployments. The Actenon Kernel, Permit, and Cloud products require a cryptographic proof bound to each action before execution, leaving a verifiable audit trail. The project aims to prevent destructive AI-agent behavior by enforcing human-in-the-loop approvals and runtime limits.

read1 min views1 publishedJul 8, 2026
The neutral proof standard for consequential AI-agent actions
Image: source

actenon-kernelactenon-kernel PublicStop AI agents from taking destructive actions they weren't authorized to. Actenon gates consequential actions, payments, deletes, deploys, access changes, so nothing executes without a cryptograph…

Python

1 - actenon-permitactenon-permit PublicActenon-Permit: an open-source authority broker for AI agents. Bounded, revocable capability grants with hard runtime limits, human-in-the-loop approvals, kill switch, and a tamper-evident action l…

Python

1 - actenon-cloudactenon-cloud PublicPrivate Actenon Cloud control plane for enterprise proof-bound execution: policy, approvals, credential brokering, tenants, audit evidence, and operational workflows.

Python

Repositories

actenon-permitPublicActenon-Permit: an open-source authority broker for AI agents. Bounded, revocable capability grants with hard runtime limits, human-in-the-loop approvals, kill switch, and a tamper-evident action ledger.

Actenon/actenon-permit’s past year of commit activity - actenon-cloudPublicPrivate Actenon Cloud control plane for enterprise proof-bound execution: policy, approvals, credential brokering, tenants, audit evidence, and operational workflows.

Actenon/actenon-cloud’s past year of commit activity - actenon-kernelPublicStop AI agents from taking destructive actions they weren't authorized to. Actenon gates consequential actions, payments, deletes, deploys, access changes, so nothing executes without a cryptographic proof bound to that exact action. Every decision leaves a verifiable receipt. Open-source, runs locally. No valid proof, no execution.

Actenon/actenon-kernel’s past year of commit activity

── more in #ai-safety 4 stories · sorted by recency
── more on @actenon 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/the-neutral-proof-st…] indexed:0 read:1min 2026-07-08 ·