Guardian
Constitutional alignment runtime for teams building AI products.
Verified directory
Choose the work you need to do
Every primary destination below was checked directly on 12 August 2026. A linked repository remains authoritative for its licence, release, and support state.
Creed Space MCP
Constitutional safety guardrails for MCP-compatible agents.
Value Context Protocol
Portable, adaptive, and verifiable value context for agents and services.
Creed Space Governance
Guidance for authoring policies, examining adherence, and governing aligned deployments.
Bounder
Local, deny-by-default governance beside physical actuators.
Janus
Bidirectional driver translation for legacy-system migration and preservation.
Auto-Assessor
Hosted assessment of agentic AI behaviour against structured safety criteria.
Auto-Advisor
Remediation guidance for risks found during an agentic AI assessment.
METTLE
Machine-agency verification through procedurally generated challenges.
Psychopathia Clinic
Diagnostic, intervention, symptom-checking, and MCP tools for machine dysfunction.
Psychopathia Machinalis
Peer-reviewed diagnostic framework and taxonomy for dysfunctions in advanced AI.
AI Guardians
Interactive AI ethics and safety education through consequential play.
Reading the directory
What the labels mean
- Released
- A named public release was verified at the linked source.
- Live hosted tool
- A public interactive service exists. Availability does not imply a downloadable open-source implementation.
- Active
- The destination or repository showed current maintenance activity during this review.
- Licence
- The linked repository metadata identified the stated licence. The linked source remains authoritative.