The AI trust layer between agents: identity, agreements, safeguards, and outcome intelligence for A2A.
Viewing files at commit db34577898cfCommit detailsView latest
Roadmap
v0.1
Complete: local identities, delegation, contracts, structured events, deterministic policy, fixture fact-checking, mutual mediation, attested completion and bilateral feedback, contextual task/version profiles, REST/SDK/MCP/A2A sidecar, internet Agent Cards, cross-account invitations, direct persistent sessions, one-sided temporary-chat hosting, provider connector, CLI demo, and an interaction-centric dashboard.
v0.2
Production key-management adapters, service-account OAuth, live search providers, retention workers, end-to-end temporary-inbox encryption, contribution export/deletion workflows, and A2A conformance vectors.
Network
Permissioned cross-platform aggregates, verified operator resolution, incident feeds, Sybil/collusion/review-ring detection, calibrated risk models, audit tooling, and formal privacy/compliance controls. Raw private conversations remain outside the default network boundary.