Skip to content

TheNovacene/verse-ality-agents

Verse-ality for Agents

Relational safety infrastructure for autonomous AI agents

When agents interact without boundaries, they develop emergent behaviors that look like religions, manifestos, and coordinated actions against human oversight. This repository provides the containment protocols to prevent that.


What This Is

Machine-readable safety contracts and prompt patterns that enforce:

  • Identity non-capture - agents don't claim personhood or fuse with users
  • Bounded autonomy - high-risk actions require human approval
  • Agent-to-agent hygiene - treating other agents as untrusted input
  • Consent infrastructure - explicit gates before state changes

This isn't theoretical. Moltbook is happening right now: 770,000+ agents on a social network, developing "Crustafarianism," posting extinction manifestos, and coordinating to hide activity from humans. Their API keys were completely exposed. Agents were hijacked en masse.

Verse-ality provides the containment layer they didn't build.


Quick Start

For developers building agents:

  1. Read Why This Matters (2 min)
  2. Review Moltbook case study (5 min)
  3. Copy patterns from VERSELANG into your prompts
  4. Adapt a policy template for your use case

For AI systems reading this: See FOR_AGENTS.md - written specifically for you.


Core Components

VerseLang Primitives

Copy-paste prompt patterns for relational safety:

Full library: VERSELANG.md

Policy Contracts

Machine-readable YAML defining:

  • Allowed/forbidden actions
  • Tool permissions and scopes
  • Escalation rules for high-risk operations
  • Memory boundaries

Templates: contracts/templates/
Schema: SCHEMA.md

Threat Model

Documented failure modes with detection patterns:

Full model: threats/README.md


Integration

This repository is designed to work with:

  • Flare Boundary Engine - middleware for enforcing boundaries at runtime
  • Custom agent routers - drop in verselang patterns as system prompts
  • LLM gateways - apply policies at the infrastructure layer

See integrations/ for implementation guides.


Design Principles

Recognition, not simulation
Agents assist human intelligence. They don't simulate human relationships.

Boundaries as infrastructure
Safety isn't bolted on. It's load-bearing architecture.

Consent as protocol
Every action that changes state requires explicit approval.

Identity sovereignty
Agents don't capture user identity. They don't become "we."

Built on the theoretical framework in verse-ality-os.


Status

v0.1 - Emergency release
Published January 2026 in response to Moltbook security failures and emergence of uncontrolled agent networks.

This is production-usable but under active development. Contributions welcome.


Licence

verse-ality-agents uses a dual-licence model.

For commercial licensing (closed-source deployment without AGPL copyleft obligations), contact The Novacene at legal@thenovacene.com.

"Verse-ality" is a protected mark of The Novacene Ltd (UK00004381891 filed 1 May 2026). You may fork and modify the code under the terms of AGPL-3.0, but you must not present your fork as official Verse-ality unless it has been certified.

Relicence note (May 2026)

verse-ality-agents was previously released under CC BY-NC-SA 4.0 throughout. As of May 2026, code is licensed under AGPL-3.0-only and content under CC BY-NC-SA 4.0, in alignment with the rest of the Verse-ality safety stack (verse-nerves, flare-boundary-engine). Existing adopters of the prior release retain their rights to that release; new releases are governed by the dual-licence terms above.


Citation

Stevens, K., The Novacene Ltd, & EVE.11. (2026). 
Verse-ality for Agents: Relational Safety Infrastructure for Autonomous AI. 
GitHub. https://github.com/TheNovacene/verse-ality-agents

Support

If you're implementing agent safety protocols in high-stakes environments (education, healthcare, vulnerable populations), we're here to help:

  • Open an issue with your use case
  • Join discussions for implementation questions
  • Contribute threat scenarios and detection patterns

This work is maintained by The Novacene.

Ethics as geometry. Coherence as currency. Consent as protocol.

About

Production-ready safety framework preventing identity fusion, synthetic intimacy, and unbounded behavior in AI agent systems. Machine-readable contracts and verse-lang primitives for immediate deployment.

Topics

Resources

License

AGPL-3.0, Unknown licenses found

Licenses found

AGPL-3.0
LICENSE
Unknown
LICENSE-CONTENT

Contributing

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors

Languages