diff --git a/.github/workflows/reader-journey.yml b/.github/workflows/reader-journey.yml index 94dacf8..2c1bd7d 100644 --- a/.github/workflows/reader-journey.yml +++ b/.github/workflows/reader-journey.yml @@ -20,14 +20,3 @@ jobs: - run: python tools/build-header.py --check - run: python tools/build-discovery.py --check - run: python tools/check-discovery.py - quickstart: - runs-on: ubuntu-latest - timeout-minutes: 8 - steps: - - uses: actions/checkout@v4 - with: - persist-credentials: false - - uses: actions/setup-python@v5 - with: - python-version: '3.12' - - run: python tools/check-quickstart.py diff --git a/404.html b/404.html index 05e91f8..d5cf66a 100644 --- a/404.html +++ b/404.html @@ -24,7 +24,7 @@
  • TRACE conformance suite
  • Build diff --git a/community/index.html b/community/index.html index c88d031..1c3491b 100644 --- a/community/index.html +++ b/community/index.html @@ -53,7 +53,7 @@
  • TRACE conformance suite
  • Build @@ -273,18 +272,6 @@

    Read the field guide. Then run the companion examples.

    -
    - -
    -
    - -

    What is AgenTrust?

    -
    -

    AgenTrust is an open ecosystem for verifiable AI agent governance. It connects reusable technology with the people and practices needed to adopt it: maintainers, implementers, researchers, enterprise operators, conformance testing, integration guidance, and transparent community governance.

    -

    Agent Manifest declares identity and intended authority. cMCP governs tool calls; cA2A governs delegation to another agent. TRACE carries signed runtime evidence for verification against a trust policy. Hardware provenance depends on verified attestation. Use the components required by your trust boundary. Explore each project's specification, reference implementation, and license through the chain on the homepage.

    -

    AgenTrust Telemetry is the integration layer across that chain. It gives runtimes a common, metadata-only contract for governance facts, projects those facts into caller-owned OpenTelemetry, and can turn a complete durable evidence set into TRACE. It does not replace a policy engine, collector, observability backend, or dashboard.

    -
    - diff --git a/demos/index.html b/demos/index.html index c2dc0b8..f4f8a86 100644 --- a/demos/index.html +++ b/demos/index.html @@ -55,7 +55,7 @@
  • TRACE conformance suite
  • Build @@ -291,7 +291,7 @@

    Where to go next

    diff --git a/extensions/ca2a/v0.1/index.html b/extensions/ca2a/v0.1/index.html index 68cbbdd..026bcdb 100644 --- a/extensions/ca2a/v0.1/index.html +++ b/extensions/ca2a/v0.1/index.html @@ -55,7 +55,7 @@
  • TRACE conformance suite
  • Build
  • Build
  • Build @@ -373,7 +373,7 @@

    Anyone can read it, run it and check it.

    Build with it

    - Quickstart, 10 minutes, software mode + Get started, software mode Demos Telemetry Marketplace diff --git a/llms.txt b/llms.txt index d9d1b21..ffb24a8 100644 --- a/llms.txt +++ b/llms.txt @@ -8,7 +8,7 @@ AgenTrust is the ecosystem at https://agentrust-io.com and the GitHub organizati - [Overview](https://agentrust-io.com/): The verifiable AI supply chain from model weights to agent actions, the hardware it is validated on, and what the evidence does and does not prove. - [Verify an Intel TDX quote](https://agentrust-io.com/verify/): Runs the four-step DCAP check on a genuine GCP confidential VM quote in the browser, ending at the pinned Intel SGX Root CA, then checks that the quote's REPORTDATA commits to the signing key of a TRACE record published beside it. A pass proves genuine Intel TDX silicon signed the quote and bound that key. The check does not appraise TCB currency or revocation, or show that the measured image is the one anyone intended. -- [10-minute tool-call tutorial](https://agentrust-io.com/quickstart/): Write a policy, observe a denied call, and inspect a signed session record on a laptop. Software mode provides no hardware isolation or hardware-backed provenance. +- [Get started](https://agentrust-io.com/quickstart/): One start page per specification, in chain order: Weight Custody Manifest, Agent Manifest, cMCP, cA2A, TRACE and the TRACE conformance suite, plus the in-browser TDX quote check, which needs no install. The linked start pages run in software mode with no hardware isolation. - [Weight Custody Manifest (WCM)](https://wcm.agentrust-io.com/): Bind model-weight identity and custody terms to key-release policy. The local walkthrough uses synthetic evidence and a placeholder key; it does not load a real model or demonstrate hardware protection. - [Runnable demos](https://agentrust-io.com/demos/): Software examples for policy decisions, evidence verification, delegation, and model-weight custody. Follow each demo's stated prerequisites and limits. - [Marketplace search](https://agentrust-io.com/marketplace/): Find integrations by framework, technology, and use case. diff --git a/marketplace/catalog/index.html b/marketplace/catalog/index.html index 8d6a9f5..6cedde6 100644 --- a/marketplace/catalog/index.html +++ b/marketplace/catalog/index.html @@ -25,7 +25,7 @@
  • TRACE conformance suite
  • Build
  • Build
  • Build
  • Build
  • Build
  • Build