Dependency-free evidence core for AI agents: observation envelopes, provenance, memory continuity and claim gates to reduce hallucination drift.
Local-first integration kernel for safer AI agents: ObservationEnvelope, EvidenceStore, ActionGate and dry-run adapters before external execution.
Evidence-gated AI systems, local-first agent safety, memory continuity, MEDIOEVO tools, and GitHub Sponsors hub.
ActionGate primitives for approve/review/block decisions, residue ledgers and auditable AI action review.
Public-safe Claudio 24/7 regulator kernel: host pressure, source retention, publication gates and evidence reports for local AI workstations.
Local-first ActionGate for AI agents: APPROVE/REVIEW/BLOCK decisions with evidence, receptors, human review and SQLite audit trails.
Add a description, image, and links to the actiongate topic page so that developers can more easily learn about it.
To associate your repository with the actiongate topic, visit your repo's landing page and select "manage topics."