Private Preview

The trust substrate
for the agentic internet

Know what your AI agents did, who authorized it, and whether it should have happened. Register agents, track every action, and prove compliance — before the auditor asks.

12Providers
36Tools
8Registered Agents
Built on open standardsDUADPOSSACedarW3C DIDNIST
01OSSA

What agents ARE

Vendor-neutral YAML manifest spec. One manifest defines capabilities, trust, policy, and SBOM — exports to 23+ deployment targets.

02DUADP

Where they're FOUND

DNS for AI agents. A federated mesh where any node can publish and discover agents without a central registry. Cryptographically verified.

03ContractPlane

How they're TRUSTED

The trust & economics plane. Identity, evidence, policy enforcement, and release authority at scale. Verify before you deploy.

Trust stack

Every layer.
One authority plane.

ContractPlane.ai

The Trust Substrate for the Agentic Internet

Click any node to explore ↓

AGENT WORLD

identity + lease request

CONTRACTPLANE TRUST PRIMITIVES

trust evaluation + policy enforcement

GOVERNANCE MECHANISMS

evidence emission

INTEGRATION SURFACE

infrastructure services

INFRASTRUCTURE

↑ Evidence flows up↓ Policy flows downClick any node to explore
Platform surfaces

Six surfaces.
One authority layer.

Focused object⚠ verified_with_warnings
code-reviewer /agent
DIDdid:web:discover.duadp.org:agents:code-reviewer
Policycedar-policies.contractplane.default
OwnerBluefly platform agents
RuntimeOracle / DUADP discovery mesh
Lanerelease/v0.1.x
Evidence chain
  1. Registration verified through DUADP discovery
  2. Cedar policy pack evaluated with reason codes
  3. Trace envelope linked to release candidate
  4. Promotion blocked until warning is cleared
Open Inspect
How it works

Four steps to a
governed system.

From unknown agent to production-ready governed system.

1

Register

Build an OSSA-validated agent with DID identity using our Agent Builder — or bring your own. ContractPlane verifies who made it, who owns it, and what it can do.

2

Test

Dragonfly, our automated testing engine, runs behavioral and security checks against your agent. Every result is signed and added to an immutable evidence chain.

3

Approve

Cedar, the formally verified policy framework, evaluates the evidence against your rules. A trust score is computed. Human reviewers clear the final gate when required.

4

Deploy

The release gate opens only when your custom thresholds are met. No shortcuts, no overrides. Export to Docker, Kubernetes, or any of 13+ supported targets.

Security by design

Enterprise-grade.
From day one.

Cedar Pre-Authorization

Zero-trust enforcement at the transport layer. <100ms via WebAssembly. 13 policy sets, 181 verified statements.

OpenTelemetry Observability

Every agent action traced. Security events logged. Cost tracked. Correlation IDs on every span.

W3C DID Identity

Every agent has a Global Agent Identifier (GAID). Cryptographic proof of origin. Ed25519 / ECDSA signatures.

Least-Privilege by Default

Scoped tool permissions. Explicit action allowlists. Autonomy modes: supervised / semi-auto / full-auto.

Supply-Chain Provenance

CycloneDX / SPDX SBOM pointers in every manifest. OSCAL control mapping for FedRAMP alignment.

DUADP Revocation Mesh

Network-wide agent invalidation. Gossip-propagated revocations reach all federation nodes within seconds.

Immutable Evidence Chain

Every registration, approval, and promotion creates a JWS-signed, append-only record. Non-repudiable audit artifacts.

Behavioral Scoring

Risk score (0–100) per actor computed from behavioral tests, policy outcomes, and incident history.

Release Gate Enforcement

Promotion is blocked until all required evidence workflows pass. No shortcut paths. Gate state is machine-readable.

Lease-Bound Execution

Agents operate under time-bounded leases with scoped delegation. Expired or revoked leases terminate execution immediately.

Human-in-the-Loop Gates

High-risk transitions require named reviewer approval. Approvals are cryptographically bound to the evidence at review time.

OSCAL / FedRAMP Controls

Control families mapped to NIST SP 800-53. OSCAL artifacts generated per registration. FedRAMP alignment documented.

Sovereign AI

Run AI where
policy allows.

Control where models run, where data resides, which operators access what, and what evidence is produced — without rebuilding your stack.

Data Residency Controls

Define where data may reside per jurisdiction. US-only, EU-only, air-gapped, or customer-hosted — enforced at the policy layer, not just the deployment layer.

Model Routing Policies

Route workloads to approved models based on data classification. PII stays on sovereign infrastructure. Public-safe text uses cost-efficient providers.

Operator Access Controls

Define which operators — human or machine — may access which data classes, models, and tools. Cedar policy enforcement on every call.

Deployment Portability

Move from SaaS to dedicated VPC to on-prem without rewriting. Same control plane, same policies, same agent definitions across all topologies.

Audit Evidence Chain

Every inference, retrieval, and document flow produces signed evidence. Export compliance artifacts for FedRAMP, EU AI Act, HIPAA, or your own governance framework.

Document Sovereignty

OCR, layout extraction, and clause analysis run where policy allows. Contracts and compliance packets never leave approved boundaries.

Built on trust

Powered by open
infrastructure.

No proprietary lock-in. ContractPlane runs on battle-tested open platforms trusted by governments and enterprises worldwide.

Category strategy

The category
is forming.

Market research

The problem
is already here.

82×
Machine identities per human employee
CyberArk 2025
18%
Enterprises confident in AI agent IAM
CSA / Strata
45%
Teams sharing API keys across agents
Gravitee 2026
93%
Leaders call agent governance urgent
Capgemini Research
Thought leadership

We helped
write the standards.

NIST submission

NIST CAISI: Why the US Government Made Agent Standards a National Priority

Formal input to NIST Docket NIST-2025-0035 in March 2026 — outlining a three-layer architecture: OSSA identity, DUADP discovery, Cedar execution policy.

Thomas Scola · March 2026 · openstandardagents.org
Foundational paper

Why AI Agents Need an Open Standard

The case for a vendor-neutral specification layer: why fragmented runtimes, proprietary registries, and ephemeral credentials can't scale to the agentic internet.

Thomas Scola · openstandardagents.org
Protocol paper

DUADP: Universal Agent Discovery Protocol

The technical specification for decentralized, federated agent discovery — DID-backed trust anchors, gossip-propagated registries, and cryptographic verification at every hop.

Thomas Scola · openstandardagents.org
Web standards

Agents as First-Class Citizens of the Web

How DNS TXT records, well-known URIs, and W3C DIDs form a trust root for agents — the same primitives that made the web trustworthy, applied to autonomous systems.

Thomas Scola · openstandardagents.org
Introducing OSSA

Introducing OSSA: The OpenAPI for AI Agents

A vendor-neutral YAML manifest spec for autonomous systems. One manifest defines capabilities, trust, policy, and SBOM — with an honest look at what it means to build open.

Thomas Scola · openstandardagents.org
Compliance deadline

EU AI Act · August 2026

High-risk AI systems must demonstrate traceability, human oversight, and documented risk controls. ContractPlane.ai produces the evidence artifacts compliance requires.

Effective August 2026 · EU Product Liability Directive Dec 2026
Get started

Start governing
your fleet.

ContractPlane.ai is in private preview.
Register your first agent today.