Skip to Content
What's Supported

AgentTrust ID Feature Status

This page lists what the repository currently implements and what should not be claimed yet. It is intentionally code-backed and avoids production-readiness, fixed latency, fixed cost, and certification claims.

Implemented Runtime Capabilities

CapabilityStatusCode reference
Agent registryImplemented: org-scoped agent records, framework/capability metadata, public-key metadata, status changesinternal/identity/
Opaque agent tokensImplemented: at_ token issue/introspect/revoke path, hash-only Redis storage, server-side validationinternal/tokens/opaque.go, internal/tokens/handler.go
API keysImplemented: API-key validation, pepper-aware hashing, org context propagationinternal/apikeys/
SessionsImplemented: Redis-backed state, scope ceilings, approval/elevation state, expiry/cleanup pathsinternal/agenttrust/session.go, internal/sessions/
Unified action checksImplemented: effect classification, session checks, anomaly checks, approval gate, Guardian routinginternal/agenttrust/check.go
Approvals/elevationImplemented: pending/approved/denied/expired approval lifecycle, max five-minute elevationinternal/agenttrust/approval.go
MCP mediationImplemented: MCP proxy and sampling guard route mediated requests through AgentTrust ID checksinternal/mcp/
A2A mediationImplemented: JSON-RPC task server plus adapter/delegation pathsinternal/a2a/
API session bridgeImplemented: verified JWT claims can initialize local AgentTrust ID sessionsinternal/agenttrust/api_adapter.go
Federation bridgeImplemented: server-side federation token verification and local session initializationinternal/federation/
Audit loggingImplemented: event ingestion/query, compliance summary support, audit-chain/integrity testsinternal/audit/, internal/integrity/
Notifications/alertsImplemented service surface for alert rules and delivery pathsinternal/notifications/
DashboardImplemented operator UI; split into the dashboard repo during public migrationdashboard/

Guardian pipeline & integration surfaces

The Guardian pipeline (Fast / Spot / Deep, risk-tier based, not a fixed percentage split) and the three integration surfaces (MCP, A2A, Direct API) routed through the UnifiedChecker are documented on the Architecture page.

This page does not claim “90% Fast / 8% Spot / 2% Deep”, fixed p95 latency, fixed per-decision cost, or a scikit-learn-based Spot Guard.

SDK Surface

The Python, TypeScript, Go, Java, and Rust SDKs expose the same core areas: agents, opaque tokens, actions/checks, sessions, approvals, delegations, federation, and integration helpers where language-appropriate.

Package coordinates are:

LanguageInstall coordinate
Pythonpip install agenttrustid
TypeScriptnpm install @agenttrustid/sdk
Gogo get github.com/agenttrustid/sdk/go@v0.3.0
Rustcargo add agenttrustid
Javaid.agenttrust:agenttrustid:0.3.0

Current status

AgentTrust ID is in controlled beta - a runtime authorization platform for AI agents with code-backed support for opaque tokens, per-action evaluation, session-scoped authorization, approval gates, instant revocation, audit trails, MCP / A2A / API / federation mediation, and five SDKs.

Last updated on