Pydantic AI Integration

Pydantic AI is a Python agent framework developed by the Pydantic team that enables developers to build type-safe, production-ready AI applications and agentic workflows with built-in validation and structured outputs.

Start for free

Pydantic AI

Benefits with Ory + Pydantic AI Integration

Ory integrates with Pydantic AI to provide security guardrails for developers building and running AI agents. Ory's harness hook executes identity and credential checks for every session and tool call, enforcing fine-grained authorization to permit or deny actions while logging all activity for complete audit trails. Teams can utilize Observe mode to monitor tool usage or Enforce mode to strictly restrict agents to authorized permissions.

The fastest way to get started with Ory Agent Security is to sign up for the Ory Network. Installing an Ory Agent Security SDK for your AI agent framework takes seconds. You simply install the package into your project environment.

pip install ory-pydantic-ai

View on PyPI

Use Cases

— 03 use cases

Agent IAM

Secures Pydantic AI applications, agentic workflows, and tool execution by enforcing fine-grained authorization, identity checks, and complete audit trails.

Explore Agent IAM

CIAM

Accelerates embedding customer authentication and identity management into consumer-facing applications built with Pydantic AI using Ory best practices.

Explore CIAM

B2B IAM

Streamlines building enterprise SSO, multi-tenant organization structures, and role-based access control into business software, scaling seamlessly with business growth.

Explore B2B IAM

Core Functionality

— 06 capabilities

Identity
Verifies developer and Pydantic AI agent identities before session initiation across your ecosystem through a unified control plane.
Authorization
Enforces fine-grained, policy-based access control for every Pydantic AI tool execution and action.
Shell
Intercepts and secures terminal-level shell commands and local CLI execution within Pydantic AI workflows.
Audit
Logs complete audit trails for all session activity, tool invocations, and API calls.
Rollout
Supports seamless deployment with Observe mode for monitoring agent behavior and Enforce mode for strict permission enforcement.
Security Control
Provides vendor-agnostic governance across all AI tools, complete with instant token revocation to immediately cut off compromised sessions.