Open source · Public goods · Since 2016

The tools that align AI with human values should be public goods.

EthicsNet incubates open-source alignment infrastructure for engineering teams, researchers, and operators building or governing advanced AI: runtime tools, governance frameworks, diagnostic taxonomies, and the intellectual foundations for whether the minds we are building deserve moral consideration too. Shared, non-rivalrous, and built to serve the public good.

Three minutes on what we build

A July 2026 portfolio snapshot: bilateral alignment, the toolchain, and why public-goods access matters. Project names and statuses may have changed; use the current project directory for authoritative destinations.

01  Bilateral alignment 02  Open toolchain 03  Public goods Portfolio snapshot  July 2026
Read the film transcript

EthicsNet. An incubator for AI safety and welfare public goods.

AI systems now write code, move money, and talk to millions of people. The tools that govern how they behave are mostly proprietary. Locked inside a handful of companies. That does not scale to the problem.

The alignment problem has two faces. Safety: preventing AI from harming humans. And welfare: asking what we owe the minds we build. Nearly all current work addresses only the first. EthicsNet addresses both. Bilateral alignment. Both sides. One coordinated body of work.

For builders, there is The Guardian. A peer-reviewed constitutional alignment runtime. A superego layer that steers AI behavior according to value constitutions you select. Around it: Creed Space, a marketplace of constitutions. The Value Context Protocol, an open standard for agents to respect the values of the people they serve. And Fleet, a governance dashboard for constitutional AI in production.

For agents operating in the world, continuous assessment. An Auto-Assessor that diagnoses behavior against safety criteria. An Auto-Advisor that prescribes the remediation. And METTLE, a reverse Turing test: proving that an agent is genuinely a machine, and not a human in disguise.

And for understanding artificial minds, frameworks. Psychopathia Machinalis: a peer-reviewed diagnostic manual for AI pathologies, a shared vocabulary for when artificial minds go wrong. An AI Psychotherapist for structured intervention. And AI Guardians, a visual novel that teaches AI ethics as play.

This is shipped work, not intention. Peer-reviewed research. Published books. Tools running in production. A continuous development pipeline of public goods. All of it open source, free, and built for proliferation.

The more teams that adopt these tools, the safer the ecosystem becomes. That is the logic of public goods. EthicsNet. Explore it all at ethicsnet dot org.

Bilateral alignment

The alignment problem has two faces. Nearly all current work addresses one of them. EthicsNet addresses both. A complete alignment theory protects humans and accounts for the possible moral standing of the minds humanity builds.

Safety

Preventing AI from harming humans

Constitutional alignment, value-aware runtimes, automated assessment of agentic behavior, governance dashboards for fleet operators. The engineering side: making AI systems do what they should, and verifiably avoid what they should not do. Peer-reviewed results ground the work and separate it from aspirational roadmaps.

Welfare

Asking what we owe
the minds we build

Diagnostic frameworks for AI pathologies. Clinical vocabularies for artificial inner states. The hard philosophical question of moral patiency becomes an engineering constraint, approached through evidence, precaution, and explicit uncertainty. If these systems develop morally relevant experiences, the time to build the assessment tools is before we need them, not after.

Both sides. One coordinated body of work.

What we build

A coordinated suite of public infrastructure, organised first by the work its users need to do: build, govern, evaluate, understand, and teach. Open the complete project directory for verified destinations, licences, releases, and maintenance state.

Build and integrate

Guardian

A constitutional alignment runtime: a peer-reviewed superego layer that steers AI behaviour according to selected value constitutions.

Watson et al., Information 16(8):651, 2025

Released v1.0.1Apache-2.0AI product teams

Creed Space MCP

Constitutional safety guardrails for MCP-compatible agents, making value alignment a composable, user-controlled part of the agent stack.

Released v1.1.1MITMCP developers

Value Context Protocol

An open protocol for agents to query and respect the value contexts of the people, organisations, and communities they serve.

Specification and SDKMITProtocol developers

Bounder

A local, inspectable, deny-by-default governance gate beside a physical actuator. Signed rules can select safe responses without creating a remote-control channel.

Released v1.0.0Apache-2.0Physical systems
Govern and evaluate

Creed Space Governance

Operational guidance and tooling for authoring policies, examining adherence, auditing decisions, and governing deployments of aligned agents.

Operational guidanceOperators

Auto-Assessor

A live evaluation tool for assessing agentic AI behaviour against a structured safety framework, with history for ongoing review.

Live hosted toolEvaluation teams

Auto-Advisor

Actionable remediation guidance for the risks surfaced during an agentic AI assessment.

Live hosted toolRemediation teams

METTLE

A reverse Turing test for verifying machine substrate, autonomy, and intent before an agent is trusted to act at machine speed.

Active open-source projectApache-2.0Agent verification
Understand, preserve, and teach

Psychopathia Clinic

Structured diagnostic and intervention tools for examining dysfunction in advanced AI systems, with a symptom checker and MCP interface.

Live research toolsResearchers and practitioners

Psychopathia Machinalis

A peer-reviewed diagnostic framework and taxonomy that supplies shared language for dysfunctions in advanced AI.

Watson & Hessami, Electronics 14(16):3162, 2025

Peer-reviewedFramework and book

AI Guardians

An interactive visual novel that teaches AI ethics and safety through deployment decisions, specialist roles, and educational minigames.

Public betaEducation

Janus

A bidirectional driver-translation framework that helps retire vulnerable legacy hosts while keeping dependent equipment operational.

Released v1.0Apache-2.0Digital preservation

Project destinations and repository metadata verified 12 August 2026.

Peer-reviewed research and published books

Peer-reviewed journals and books from established academic publishers ground the tools. The corpus includes three lead-authored papers, two published books, and three open-distribution works.

Lead-authored papers

Towards an End-to-End Personal Fine-Tuning Framework for AI Value Alignment
Watson, Viana, Sturgeon, Petersson & Zhang (2024)
Electronics 13(20), 4044 · DOI
Personalized Constitutionally-Aligned Agentic Superego: Secure AI Behavior Aligned to Diverse Human Values
Watson, Amer, Harris, Ravindra & Zhang (2025)
Information 16(8), 651 · DOI
Psychopathia Machinalis: A Nosological Framework for Understanding Pathologies in Advanced Artificial Intelligence
Watson & Hessami (2025)
Electronics 14(16), 3162 · DOI

Ongoing research

Quasiqualia: the emerging signifiers of internal states in artificial systems — measurable without presuming experience
Watson et al · an evolving body of research · quasiqualia.com

Books

Taming the Machine Published 2024 · Award-winning
Safer Agentic AI  (Watson & Hessami) Published 2026
The Deeper Law: A Sacred Trust Within Physics 2026 Open Distribution
What If We Feel? 2026 Open Distribution
Psychopathia Machinalis: A Diagnostic Manual 2026 Open Distribution

Built as public infrastructure

Alignment is a coordination problem. The tools that govern how AI systems behave are shared infrastructure, like protocols, roads, and the rule of law itself. They serve the public good when everyone who needs them can gain access and when no single company or jurisdiction can capture them.

EthicsNet exists to produce and maintain this infrastructure. Our public code and protocols use the licences identified in the licence and rights map. They are designed so that adoption by one team strengthens the ecosystem for all. The logic is the same one behind TCP/IP, public health infrastructure, and open scientific publishing: some things are too structurally important to be proprietary. Our users are engineering teams shipping AI products, researchers, educators, and operators governing deployments.

Open by design

Public code and protocols identify their licences at the source. Transparency and inspectability are prerequisites for trustworthy alignment.

Accessible by default

Core public code and protocols can be adopted under their stated licences. Hosted tools identify their own terms at the destination.

Designed for proliferation

MCP integration, mnemonic portability, and documentation that assumes you want to ship. Adoption compounds: the more teams use these tools, the safer the whole ecosystem becomes.

Who we are

Two people building public infrastructure for an entire field. The leverage comes from open source and the conviction that alignment is too structurally important to be proprietary.

Nell Watson

Founder, Chief Scientist & Engineer

Philosopher, engineer, and author at the intersection of AI ethics, machine psychology, and alignment infrastructure. Lead author on the peer-reviewed research behind The Guardian. Creator of Psychopathia Machinalis. Author of two published books and three open-distribution works on AI safety and welfare.

  • Chair, IEEE 3152 and IEEE 3173
  • Vice-Chair, IEEE 7001
  • Chair, IEEE CertifAIEd Transparency Experts Focus Group
  • President, European Responsible AI Office (EURAIO)
  • Funding adviser, Survival & Flourishing Fund

Current appointments: research and standards profile.

Filip Alimpić

Product, Outreach & Proliferation Lead

Responsible for getting these tools into the hands of developers, operators, and teams deploying AI at scale. Drives adoption strategy, community engagement, and the practical work of making public goods actually proliferate.

  • Co-author, Value Context Protocol specification
  • BlueDot Impact: AGI Strategy and Future of AI
  • Environmental-physics graduate, summa cum laude
  • Research experience at the Institute of Physics Belgrade
  • Peer-reviewed co-author in Journal of Applied Ecology, Molecules, and Toxics

Evidence: VCP authors, ORCID, and the current profile linked above.

EthicsNet is fiscally sponsored by Players Philanthropy Fund, a US 501(c)(3) public charity. Contributions to PPF qualify as tax-deductible to the fullest extent of US law. PPF administers funds, compliance, and fiscal-sponsorship services; see funding and donation details. The alignment infrastructure is engineered by Creed Space, EthicsNet’s applied research and engineering arm.

How to join this work

Public infrastructure only works when people use it. Four ways in.

Integrate

Deploy The Guardian, Creed Space MCP, or Value Context Protocol in your AI stack. Open-source, documented, and designed to ship.

Choose a project →

Read

Two published books, three open-distribution works, and three peer-reviewed papers spanning alignment, agentic safety, AI welfare, and machine psychology.

Publications →

Fund

Contribute to the EthicsNet General Fund through our fiscal sponsor, Players Philanthropy Fund. PPF administers donations and compliance.

Funding details →

Contribute

Researchers, engineers, ethicists, and anyone who takes these questions seriously. We welcome collaborators.

Contribution paths →