DEVELOPERS

Integration Guides

Where Runtime Authority connects to the rest of your stack -- and an honest split between what works today and what's a dedicated connector we haven't built yet.

None of the entries below are a fabricated "it just works" integration. Agent frameworks that are Python-native can call the SDK directly today, using the exact same agent.authorize(...) call shown throughout these docs. Cloud platforms and enterprise systems that would need a dedicated connector are marked accordingly.

Agent frameworks and protocols

Any Python process can call the SDK's authorize() before taking an action -- these frameworks are all Python-native, so the integration pattern works today even without a dedicated connector.

OpenAI Agents SDKEARLY ACCESS

Anthropic Claude (tool use / Agent SDK)EARLY ACCESS

LangGraphEARLY ACCESS

CrewAIEARLY ACCESS

AutoGenEARLY ACCESS

MCP (Model Context Protocol)EARLY ACCESS

Cloud AI platforms

These require a dedicated connector to bridge the platform's own agent runtime to the Intent API -- not yet built.

Microsoft CopilotCOMING SOON

Azure AI FoundryCOMING SOON

AWS BedrockCOMING SOON

Google Vertex AICOMING SOON

Enterprise systems

The system of record an agent's action ultimately reaches, after a decision allows it -- connector work not yet started.

SAPCOMING SOON

OracleCOMING SOON

Microsoft DynamicsCOMING SOON

ServiceNowCOMING SOON

DevOps

GitHub ActionsCOMING SOON

What "Early Access" means here

There's no PayReality-published package for any of the frameworks above -- "Early Access" means the existing Python SDK already gives you what you need to wire it in yourself (call authorize() at the point your agent would otherwise act), not that a named integration package exists. See SDKs and Integration Examples for the calls involved.

Other documentation

Getting StartedCreate an organization, register an agent, and get your first Authorization Receipt back.ArchitectureThe full path from an agent's signed intent to a decision and its evidence, component by component.Runtime APIThe Intent API: POST /v1/intents, its three possible outcomes, and the request/response lifecycle.AuthenticationThe Operator Key, per-user roles and permissions, per-developer API keys, and agent certificates.Authority GraphDelegated authority, roles, resources, and approval limits, and how governance becomes machine-readable.Runtime PoliciesHow a policy is compiled, versioned, and deployed, and why that differs from the governance document it came from.Authorization ReceiptsWhy logs aren't enough, the receipt lifecycle, and the planned architecture for independent verification.Evidence VerificationSignature verification, evidence export, and audit workflows against the Evidence Portal today.SDKsThe Python SDK, and the language roadmap for Node.js, Go, Java, .NET, and Rust.WebhooksEnterprise events -- IntentReceived, DecisionCompleted, ReceiptIssued, and more -- with real payloads.Integration ExamplesRotating keys, sending a heartbeat, and retiring an agent, with real SDK code for each.Agent RegistrationThe full agent lifecycle: registered, active, suspended, retired, or revoked.API ReferenceEndpoints, schemas, headers, status codes, errors, and versioning.