Pydantic AI
BetaType-safe Python agents with Pydantic validation.
Python framework that brings the Pydantic-style developer experience to agent building. Strong typing, structured outputs by default, model-agnostic. Popular in API-product teams that already standardise on Pydantic.
- Category
- Developer frameworks
- Runtime
- Python
- Pattern
- SDK / Library
- Adapter package
- intramedial-actor-pydantic-ai
Status
Pydantic AI is Beta.
The integration path is built and tested. Customers can attach now; expect minor breaking changes until the 1.0 contract freeze.
Ships from the repo as `intramedial-actor-pydantic-ai` — not yet on a package registry.
How to attach
SDK / Library.
Install the adapter
Add intramedial-actor-pydantic-ai to your project.
Issue a workspace API key
Generate a key in the dashboard under Settings → API Keys, scoped to the workspace and environment this agent's data should land in.
Record each run
Construct the adapter once with your token and workspace id where you initialise your Pydantic AI agent, then call recordRun(run) when a run finishes. The adapter maps the run to signed receipts and, by default, captures a failed attestation instead of crashing your agent.
Verify
Trigger one agent run. The Witness page shows the record once the agent has emitted it.
What gets recorded
4 event types, captured today.
- agent.invocation
- Every top-level agent run — the input, the resolved output, timing and token usage.
- tool.call
- Each tool or function the agent invokes, with its arguments and returned result.
- memory.write
- Writes to the agent's persistent memory store, so state changes stay auditable.
- sub_agent.spawn
- Sub-agents the orchestrator spawns, captured with their parent lineage.
Same category
Others in Developer frameworks.
The reference library for building agent applications.
- CrewAIBeta
Multi-agent crew orchestration.
- AutoGen / AG2Beta
Microsoft's multi-agent conversation framework.
OpenAI's native agent framework.
- Claude Agent SDKBeta
Anthropic's native agent SDK.
- Vercel AI SDKBeta
TypeScript-first toolkit for agentic applications.
Start recording Pydantic AI agents.
Every Pydantic AI run lands in the same canonical Witness record as every other framework in the catalogue: signed, replayable, and exportable as evidence.
A Trustvice ProductAgents act when the plane says yes, and the record says why.
Put admission in front of your MCP servers, repositories, SaaS tools and cloud accounts. Every agent gets a lease or a reason – and you keep the lever to stop any of them.
