Publish research library with three versioned technical reports

.github/workflows/reader-journey.yml

@@ -16,6 +16,7 @@ jobs:
         with:
           python-version: '3.12'
       - run: python tools/check-site.py
+      - run: python tools/build-research.py --check
       - run: python tools/build-controls.py --check
       - run: python tools/build-header.py --check
       - run: python tools/build-discovery.py --check

404.html

@@ -29,6 +29,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>

community/index.html

@@ -96,6 +96,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/" aria-current="page">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>

data/research.json

@@ -0,0 +1,90 @@
+{
+  "papers": [
+    {
+      "slug": "trace",
+      "short_title": "TRACE",
+      "title": "TRACE: Trust, Runtime Attestation, and Compliance Evidence (A Portable Attestation Format for AI Agent Runtime Governance)",
+      "authors": [
+        "Rishabh Poddar",
+        "Aaron Fulkerson",
+        "Imran Siddique"
+      ],
+      "topic": "Runtime evidence",
+      "description": "TRACE technical report: portable runtime claims, recorded software benchmarks, conformance outcomes, source and explicit attestation limits.",
+      "contribution": "A portable format for runtime claims, with recorded measurements of signing, verification, record size, and conformance fixtures.",
+      "limits": [
+        "The recorded run used agentrust-trace 0.2.0 and trace-tests 0.2.0 on July 1, 2026. It did not measure silicon certificate-chain appraisal.",
+        "The missing-runtime fixture passes at Level 0 in the saved results. The cMCP fixture fails at all three levels. Those outcomes limit what the historical conformance checks establish.",
+        "A signature proves integrity and signing-key possession. Hardware origin requires verified attestation and key binding; inclusion in a log does not prove that every event was recorded."
+      ],
+      "changes": "Clarifies the signature and hardware-evidence boundary, corrects the description of saved conformance outcomes, and preserves the historical measurements.",
+      "spec": "https://trace.agentrust-io.com/",
+      "code": "https://github.com/agentrust-io/trace-spec",
+      "patent_pending": false,
+      "date": "2026-09-27",
+      "abstract": "TRACE (Trust, Runtime Attestation, and Compliance Evidence) proposes a portable record for claims about AI agent runtimes: workload identity, model, policy, data class, tool transcript, build provenance, and appraisal. It composes RATS/EAT, signatures, and transparency evidence into a format that a relying party can evaluate against its own trust policy. A valid signature establishes integrity and possession of the signing key; hardware origin additionally requires verified attestation and a binding from that evidence to the key. This technical report describes the original design and preserves the recorded software evaluation of agentrust-trace 0.2.0 and trace-tests 0.2.0. The evaluation measures canonicalization, Ed25519 signing and verification, record size, and fixture outcomes. It does not measure silicon certificate-chain appraisal or establish that the recorded runtime claims are true. The current normative specification and its implementation limits are maintained separately.",
+      "pages": 15,
+      "sha256": {
+        "paper.pdf": "40034a6d7dd62f0e066798bcc746b5fc7b6fa723078f52e4a3c4c919bd821ded",
+        "source.zip": "b31c13247c98c3f83a44a25dfdf6862f89b6d2f38fc95133ef45340138f383f9"
+      }
+    },
+    {
+      "slug": "cmcp",
+      "short_title": "cMCP",
+      "title": "cMCP: Verifiable Policy Enforcement for AI Agent Tool Calls",
+      "authors": [
+        "Rishabh Poddar",
+        "Aaron Fulkerson",
+        "Imran Siddique"
+      ],
+      "topic": "Tool-call enforcement",
+      "description": "cMCP technical report: policy evaluation at the MCP boundary, software experiments, source, citations and limits of the recorded evidence.",
+      "contribution": "A gateway design combining policy evaluation, session sensitivity, tool-catalog pinning, and signed tool-call records.",
+      "limits": [
+        "The reported experiments use software-only TEE mode and synthetic traces. No hardware TEE or independent cross-organization deployment is evaluated in this report.",
+        "The reported 11 of 16 blocked calls measures the false-discovery proportion among blocked calls. It is not the conventional false-positive rate over all negative cases.",
+        "Replay and omission detection depend on trusted keys, freshness checks, and an expected session or log boundary. Gateway records alone do not establish complete information flow."
+      ],
+      "changes": "Narrows the abstract to the measured software behavior, corrects the false-discovery terminology, and adds the publication scope and patent notice.",
+      "spec": "https://cmcp.agentrust-io.com/",
+      "code": "https://github.com/agentrust-io/cmcp",
+      "patent_pending": true,
+      "date": "2026-09-27",
+      "abstract": "cMCP (Confidential MCP) proposes a gateway for policy evaluation at the Model Context Protocol tool-call boundary. The gateway evaluates Cedar policies before dispatch and emits signed records binding policy measurements, session identifiers, and tool-call evidence. Its design combines policy hashing, monotonic session sensitivity, tool-catalog pinning, and audit-chain checks. This technical report preserves software-only experiments for those mechanisms, including synthetic healthcare call traces and simulated attestation paths. The measurements illustrate behavior under the stated inputs and assumptions; they do not validate a hardware TEE, establish complete information-flow tracking, or show that every tool invocation was captured. Hardware provenance requires independent attestation appraisal and signing-key binding. Replay and omission detection additionally depend on freshness checks and an expected session or log boundary. The report distinguishes these deployment requirements from the software behavior measured here.",
+      "pages": 18,
+      "sha256": {
+        "paper.pdf": "f5e90fbe9a466dab97ac3d3da8c436285b78bd77f1de4a9dc0a6f9794707492f",
+        "source.zip": "d50104e97da7744859eb6e7d3e638af3a0e20adaf0dd5137ae4bfc38b474ef1b"
+      }
+    },
+    {
+      "slug": "agent-manifest",
+      "short_title": "Agent Manifest",
+      "title": "Agent Manifest: Portable, Hardware-Attestable Identity and Provenance for AI Agents",
+      "authors": [
+        "Imran Siddique"
+      ],
+      "topic": "Agent identity",
+      "description": "Agent Manifest technical report: signed artifact baselines, recorded Ed25519 benchmarks, delegation checks, source and runtime-evidence limits.",
+      "contribution": "A signed baseline for agent artifacts, with recorded Ed25519 benchmarks, delegation checks, and tamper probes.",
+      "limits": [
+        "The saved benchmark run is dated July 1, 2026, on Windows 11, CPython 3.12.10, and an ARMv8 Qualcomm host.",
+        "Only the Ed25519 profile was measured. The recorded environment did not have the optional post-quantum dependency; no ML-DSA-65 performance result is claimed.",
+        "Signed artifacts do not establish that those artifacts were used during execution. Continuous validation of mutable memory and retrieval state is outside this evaluation.",
+        "The saved environment does not identify the exact SDK commit. It supports inspection of the recorded results, but not a claim of fully pinned independent reproduction."
+      ],
+      "changes": "Separates signed-baseline checks from proof of runtime use, states evaluation limits, and adds the publication scope and patent notice.",
+      "spec": "https://manifest.agentrust-io.com/",
+      "code": "https://github.com/agentrust-io/agent-manifest",
+      "patent_pending": true,
+      "date": "2026-09-27",
+      "abstract": "Agent Manifest proposes a signed record of the artifacts that define an AI agent, including its system prompt, model, policy, tools, retrieval corpus, memory, decision trace, delegation, supply chain, and human approvals. Artifact digests and canonical serialization make changes to the recorded baseline detectable when a verifier has the relevant artifacts and trusted keys. The design composes SPIFFE identities, RFC 8785 canonicalization, Ed25519 signatures, an optional ML-DSA-65 profile, and hardware-attestation bindings. This technical report describes the original model and preserves the recorded Ed25519 software benchmarks, delegation checks, and tamper probes. Signed metadata alone does not prove that the recorded configuration was used during execution. The evaluation does not measure post-quantum performance or establish live hardware provenance; continuous verification of mutable memory and retrieval state is outside its scope. Current SDK behavior and normative requirements are maintained separately.",
+      "pages": 12,
+      "sha256": {
+        "paper.pdf": "325969395ca5a6da6917676ef1285b6a2812ee1c35884fb4c5b39c9da9785675",
+        "source.zip": "f79f033d5e6de385dc0b6308c387194e2515f6fbf718a942dc5b0058b9d23455"
+      }
+    }
+  ]
+}

demos/index.html

@@ -98,6 +98,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>

extensions/ca2a/v0.1/index.html

@@ -99,6 +99,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>

go/index.html

@@ -76,6 +76,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>

index.html

@@ -161,6 +161,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>
@@ -384,6 +385,7 @@ <h3>Build with it</h3>
       <div class="hero-actions">
         <a class="btn btn-primary" href="/quickstart/">Get started, software mode</a>
         <a class="btn btn-ghost" href="/demos/">Demos</a>
+        <a class="btn btn-ghost" href="/research/">Research papers</a>
         <a class="btn btn-ghost" href="/telemetry/">Telemetry</a>
         <a class="btn btn-ghost" href="/marketplace/">Marketplace</a>
       </div>

llms.txt

@@ -34,6 +34,10 @@ AgenTrust is the ecosystem at https://agentrust-io.com and the GitHub organizati
 - [GitHub organization](https://github.com/agentrust-io): Source, releases, issues, governance, and contribution instructions.
 - [Governance resource directory](https://governance.agentrust-io.com/): Curated tools, standards, and research.
 
+## Research
+
+- [Research reports](https://agentrust-io.com/research/): Versioned TRACE, cMCP and Agent Manifest technical reports, with PDFs, source packages, recorded software evidence, citations and explicit limits. Not peer reviewed; use current specifications for implementation.
+
 ## Community and stewardship
 
 - [Community, partners and sponsor](https://agentrust-io.com/community/#adoption): Published roles and partner relationships, each linked to public evidence. OPAQUE sponsors the work. The NSF submission is in review, not an award.

marketplace/catalog/index.html

@@ -32,6 +32,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>

marketplace/index.html

@@ -73,6 +73,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/" aria-current="page">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>

quickstart/index.html

@@ -103,6 +103,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>

registry/index.html

@@ -95,6 +95,7 @@
           <li><a href="/telemetry/">Telemetry</a></li>
           <li><a href="/marketplace/">Marketplace</a></li>
         </ul></details></li>
+        <li><a href="/research/">Research</a></li>
         <li><a href="/community/">Community</a></li>
         <li><a href="https://github.com/agentrust-io">GitHub</a></li>
         <li><a href="https://www.linkedin.com/company/agentrust-io/">LinkedIn</a></li>