TRACE: Trust Runtime Attestation and Compliance Evidence

Specification  |  Schema  |  Examples  |  Registry  |  Test Suite  |  Reference Impl

Developer Preview. Launching at Confidential Computing Summit, June 23 2026.

An open specification for hardware-attested AI agent governance records. TRACE defines the format, anchoring protocol, and verification rules for cryptographically provable evidence that an AI agent ran under a specific policy, in a verified hardware environment, on classified data, invoking identified tools — bound into a single signed artifact rooted in silicon attestation.

A TRACE Trust Record answers: what ran, where, under which policy, touching which data, calling which tools — in a form any third party can verify without trusting the operator.

Quick start

pip install agentrust-trace

from agentrust_trace import TrustRecord, sign_record

record = TrustRecord(
    subject="spiffe://trust.example.org/agent/payments-processor",
    model_id="claude-sonnet-4-6",
    platform="amd-sev-snp",
    policy_hash="sha256:b2c3d4...",
)
signed = sign_record(record, key=signing_key)

Resources

📖 Full documentation	trace.agentrust-io.com
📄 Specification	spec/trace-v0.1.md
🔍 Schema	schema/trace-claim.json
📦 PyPI	agentrust-trace
🧪 Test suite	trace-tests
🗂 Registry	trace-registry
🔗 Reference implementation	cmcp
💬 Discussions	GitHub Discussions
📋 Changelog	CHANGELOG.md

Standards alignment

Targeting the Agentic AI Foundation (AAIF) at the Linux Foundation. Active standardization track in CoSAI WS4. Builds on RFC 9711 (EAT), RFC 9334 (RATS), and SCITT draft-22.

Contributing

See CONTRIBUTING.md and GOVERNANCE.md. All contributors must agree to the ANTITRUST.md policy.