Skip to content

docs: correct brand name to AgenTrust #12

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
imran-siddique merged 1 commit into from
Jun 29, 2026
Merged

docs: correct brand name to AgenTrust #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions integrations/sage-agenttrust/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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).
Expand All @@ -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
Expand Down
4 changes: 2 additions & 2 deletions integrations/sage-agenttrust/integration.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
name: SAGE AgentTrust Bridge
vendor: SAGE AgentTrust Bridge
name: SAGE AgenTrust Bridge
vendor: SAGE AgenTrust Bridge
integrates_with:
- cmcp
- trace
Expand Down
6 changes: 3 additions & 3 deletions sentinel/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,17 +17,17 @@ 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

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."

Expand Down
Loading