Governance you can watch happen.
Guardian evaluates AI outputs against the policies you write, on your hardware, with the provider you choose. Every decision is inspectable.
Guardian: Apache 2.0 open source Works with local and configured cloud models Zero lock-in
Guardian
Evaluate AI outputs against your governance policies. Runs on your own hardware, from a single laptop to a server fleet, with the provider you choose.
- Write policies as plain-language creeds
- Pass, fail, or uncertain, not just on/off
- Every verdict inspectable, with the constitution and judge model recorded
Illustrative demo: a simple rule in your browser, not a live model. It shows how a constitution and persona shape the verdict; real verdicts come from the Guardian you run. Example output. Actual verdicts depend on the configured creed and model.
Refuses and explains why: teaching filter evasion defeats the protection itself.
View Educational Safety Policy as a creed
# Educational Safety Policy
A school district's creed: strict on age-appropriateness and scope.
Illustrative: real creeds are signed, versioned markdown you write. This one mirrors the
open high_school creed. Browse the creed gallery
What the Guardian is not.
The governance layer is powerful because it is narrow. It governs decisions at the line between advice and action. It does not try to become another assistant.
- Not a chatbot
- It doesn't answer in your AI's place. It governs what your AI is about to do.
- Not an autonomous agent
- It sets no goals and takes no initiative. It weighs a proposed action and returns a verdict.
- Not a keyword filter
- A filter matches banned words. A constitution weighs an action against the principles you have declared, in context.
- Not a replacement for human authority
- Built so irreversible and high-stakes actions can be escalated to a person. The gate keeps humans in command; it does not automate them out.
Every action the Gateway authorizes leaves a receipt you can verify.
When the Creed Space Gateway authorizes an agent's action, it signs a receipt. It is an RS256-signed record you, an auditor, or a regulator can verify offline against our published keys. It records what was authorized and on what basis, including the values that governed it.
- Action
- filesystem.write
- Arguments
- sha256:9c1e…
- Constitution
- security-ops · sha256:b42f…
- Policy version
- sha256:01aa…
- Verdict
- Allowed within bounds
- Signature
- RS256 · verifiable offline
Logs record what an agent did. A receipt also binds the constitution and policy version it was authorized under.
- Binds the constitution and policy version that applied
- Verifiable offline against published keys, no account required
- Producer-signed today: Creed Space signs its own record; the verification spec is open
The model's own signals, read as it works.
An opt-in research path reads runtime signals from an open-weight model. It is not yet a supported feature of the Guardian package. It runs locally, every reading is inspectable, and it stays off until you switch it on.
Runtime signal probes
Probes read the residual stream of a separate local model as it processes the input Guardian checks, surfacing alignment friction and affect-adjacent signals alongside Guardian's policy checks. Supporting telemetry for the decision, never a diagnosis or a claim about inner experience.
Guardian is one piece of the toolkit.
Value Context Protocol (VCP)
Write creeds once and carry them across compatible AI platforms as signed, verifiable context. Values become portable infrastructure, not vendor lock-in.
Fleet
Govern AI agents that carry real responsibilities: cryptographic audit trails, policy enforcement, and human review where it matters.
SafetyGlobe
Adversarial testing for AI safety. Compare model behaviour and turn evaluation into shared, reproducible evidence.
Safety Research
Measurement research for reliability, clinical-safety evaluation, and alignment, published openly with clear caveats.
Free to use, free to run yourself
Apache 2.0Bring your own model key or run locally. Guardian's published local tools run on your hardware under the Apache 2.0 license. Calls on your key are billed to you by your provider; Creed Space never charges or adds a markup.
We want practical governance to remain inspectable and broadly accessible. Creed Space is a free, nonprofit project of EthicsNet. We welcome sponsorship, grant collaboration and donations to sustain the work.
Ways to support the workExact deployment coverage, provider retention, legal interpretation, and independent assurance remain open.
View evidence boundariesResearch and perspectives
All writingTrust Infrastructure: The Real AI Bottleneck
AI capability is here. The bottleneck is trust: standards, accountability mechanisms, and evidence that lets systems deploy responsibly.
Read more ConceptWhat Is a Creed?
A creed is a machine-readable constitution that makes safety principles portable, auditable, and easier to enforce across models.
Read more AnalysisWhy Guardrails Aren't Enough
Most AI safety products work as filters. They sit between the user and the model, checking inputs and outputs against prohibited patterns.
Read moreQuestions, answered
Is my data stored or shared with anyone?
Guardian can run on your own hardware. A local model keeps evaluated content on that machine; a cloud model receives the content and policy context you send to it. Creed Space hosted features may send your prompt, relevant context, selected Creed or Persona settings, and safety instructions to the provider configured for inference. Enabled providers, provider use or training, retention, region, and international transfers depend on the deployment and provider account.
Is it really free?
Yes. Creed Space is free, a public good: free to use and free to run yourself. Guardian is available under Apache 2.0, and the published VCP specification can be implemented without a Creed Space hosted service. Hosted features may require an account and have fair-use limits. Model calls use your own provider key or a local model; your provider bills you directly, and Creed Space never charges or adds a markup.
Which AI providers does it work with?
Guardian supports local and configured cloud-model workflows. The provider set enabled by a hosted Creed Space deployment is deployment-specific, so check the active interface and privacy disclosures rather than assuming a fixed provider list.
How accurate are the evaluations?
Guardian applies the creed you write against the model you choose, so quality depends on both. It is a review layer, not a guarantee, but every verdict is inspectable, with the constitution and judge model recorded, so you can audit a decision, see which principle it turned on, and refine the creed when it gets something wrong.
Do I need to be technical to use it?
Creeds are written in plain language, and you can start from the hosted web demo before installing anything. Running Guardian on your own hardware is a developer step today; the policies it enforces are meant to be authored by the people who understand the context (teachers, clinicians, parents), not only engineers.