From 03ef512f6c37325fb564a3a52864284832315ecd Mon Sep 17 00:00:00 2001 From: Imran Siddique Date: Mon, 29 Jun 2026 11:38:48 -0700 Subject: [PATCH] docs: correct brand name to AgenTrust Fix display brand casing from "AgentTrust" to "AgenTrust" in integration display names and READMEs. Co-Authored-By: Claude Opus 4.8 (1M context) --- integrations/sage-agenttrust/README.md | 4 ++-- integrations/sage-agenttrust/integration.yaml | 4 ++-- sentinel/README.md | 6 +++--- 3 files changed, 7 insertions(+), 7 deletions(-) diff --git a/integrations/sage-agenttrust/README.md b/integrations/sage-agenttrust/README.md index f375dc9..4b057c8 100644 --- a/integrations/sage-agenttrust/README.md +++ b/integrations/sage-agenttrust/README.md @@ -3,7 +3,7 @@ [SAGE](https://github.com/l33tdawg/sage) is consensus-validated agent memory: writes go through BFT consensus, carry a confidence score, and decay over time. This integration is an attestation-verifying reverse proxy that sits in front of a **stock, unmodified** SAGE node -and admits a `POST /v1/memory/submit` only when it carries a verifiable AgentTrust attestation, +and admits a `POST /v1/memory/submit` only when it carries a verifiable AgenTrust attestation, bound to the key that authors the memory on-chain. **Only the submit endpoint is gated** — other SAGE writes (`/forget`, `/vote`, `/corroborate`, `/challenge`, governance, access) pass through to SAGE's own Ed25519 auth + RBAC (out of scope for this submission-provenance bridge). @@ -30,7 +30,7 @@ Two paths: agent ran behind an attested gateway — **not** per-write authorization. **What it does not claim:** the bridge does **not** verify any hardware root of trust with the -published AgentTrust stack — `cmcp_verify`'s per-platform verifiers check the measurement +published AgenTrust stack — `cmcp_verify`'s per-platform verifiers check the measurement format/parse but **defer the silicon root** (TPM EK chains / AMD VCEK / Intel DCAP quote signatures go to *unverified_fields*, "out of scope for Phase 1"), and a C-2 record's `runtime.platform` is self-asserted. So it **never** reports diff --git a/integrations/sage-agenttrust/integration.yaml b/integrations/sage-agenttrust/integration.yaml index 8f37ae5..3584080 100644 --- a/integrations/sage-agenttrust/integration.yaml +++ b/integrations/sage-agenttrust/integration.yaml @@ -1,5 +1,5 @@ -name: SAGE AgentTrust Bridge -vendor: SAGE AgentTrust Bridge +name: SAGE AgenTrust Bridge +vendor: SAGE AgenTrust Bridge integrates_with: - cmcp - trace diff --git a/sentinel/README.md b/sentinel/README.md index 3f59e2c..c7cbd09 100644 --- a/sentinel/README.md +++ b/sentinel/README.md @@ -17,9 +17,9 @@ Runtime behavioral anomaly detection, collusion detection, and quarantine for ag pip install -r requirements.txt python -m src.cli claim.jwt --output report.json -Integration with AgentTrust +Integration with AgenTrust -Sentinel consumes TRACE claims and produces risk scores that can be used by AGT, cMCP, and other AgentTrust components. +Sentinel consumes TRACE claims and produces risk scores that can be used by AGT, cMCP, and other AgenTrust components. Dashboard @@ -27,7 +27,7 @@ bash uvicorn src.server:app --host 0.0.0.0 --port 8001 --reload Open http://localhost:8001 -Integration with AgentTrust +Integration with AgenTrust Sentinel fills the documented gap: "no dedicated behavioral anomaly detection or agent quarantine tooling."