Skip to content


Assay Logo
Assay

CI-native evidence compiler for agent governance

Assay compiles agent runtime signals and selected external outcomes into verifiable evidence and bounded Trust Basis claims. MCP policy enforcement is the fast path: Assay can sit between an agent and its tools, make deterministic allow/deny decisions, and preserve the evidence chain for CI, security review, and audit without a hosted backend.

If you already have machine-readable AI run artifacts, start with the smallest receipt path: Promptfoo JSONL to evidence receipts. For runtime flag decisions, use the second adoption path: OpenFeature EvaluationDetails to CI Review Artifact. For model inventory/provenance boundaries, use the third adoption path: CycloneDX ML-BOM Model to Inventory Receipt.


Install

curl -fsSL https://getassay.dev/install.sh | sh

Core Capabilities

  • Protocol Policy Enforcement


    Validate MCP tool calls against JSON Schema constraints, sequence rules, and allowlists. No LLM calls in CI.

    Policy Reference

  • Evidence Bundles


    Tamper-evident audit trails with content-addressed IDs. Verify bundles offline and keep canonical evidence separate from projections.

    Evidence Guide

  • Trust Basis & Receipts


    Compile verified bundles into Trust Basis claims and import bounded external receipt families for eval outcomes, runtime decisions, and model inventory.

    Receipt Matrix Promptfoo JSONL Receipts OpenFeature Decision Receipts CycloneDX Inventory Receipts

  • Tool Signing


    Ed25519 signatures for tool definitions. DSSE envelope format. Trust policies for supply chain security.

    Signing Spec

Quick Start

1. Capture Traces

assay import --format inspector session.json --out-trace trace.jsonl

2. Validate

assay validate --trace-file trace.jsonl --format sarif

3. Export Evidence

assay profile init --output assay-profile.yaml --name quickstart
assay evidence export --profile assay-profile.yaml --out bundle.tar.gz
assay evidence verify bundle.tar.gz

4. Generate Trust Artifacts

assay trust-basis generate bundle.tar.gz --out trust-basis.json
assay trust-card generate bundle.tar.gz --out-dir trustcard

trustcard.json is the canonical Trust Card artifact. trustcard.md and trustcard.html are deterministic reviewer projections of the same claim rows and frozen non-goals.

5. Optional: Lint with a Pack

assay evidence lint --pack eu-ai-act-baseline bundle.tar.gz
Result Exit Code Output
Pass 0 Summary
Fail 1 SARIF with findings
Error 2 Config/Schema validation

GitHub Action

- uses: Rul1an/assay-action@v2

Zero-config. Discovers evidence bundles, verifies integrity, uploads SARIF to GitHub Security.

GitHub Action Guide

Defense in Depth: Runtime Enforcement (Linux, Optional)

Optional kernel-level hardening for Linux deployments.

# Landlock sandbox (rootless)
assay sandbox --policy policy.yaml -- python agent.py

# eBPF/LSM kernel-level enforcement
sudo assay monitor --policy policy.yaml --pid <agent-pid>

Standards Alignment

Standard Integration
CloudEvents v1.0 Evidence envelope format
W3C Trace Context traceparent correlation
SARIF 2.1.0 GitHub Code Scanning
EU AI Act Article 12 Optional pack mapping

Next Steps