pydantic

The agent engineering platform.

FastAPI framework, high performance, easy to learn, fast to code, ready for production

Build resilient agents.

Data validation using Python type hints

How Python does AI: agents, realtime voice, image generation, embeddings. Every model, every interface, typed end to end.

SQL databases in Python, designed for simplicity, compatibility, and robustness.

Repair malformed JSON from LLMs, APIs, logs, and user input in Python.

AI observability platform for production LLM and agent systems.

Open-source security automation platform for teams and AI agents

🪄 Turns your machine learning code into microservices with web API, interactive GUI, and more.

Represent, send, store and search multimodal data

The Context Layer for unstructured data: typed, versioned datasets over S3, GCS, Azure

Seamlessly integrate LLMs as Python functions

🤖Self-Modifying Framework from the Future 🔮 World's First AMS

Open-source, self-hosted Claude Code - a terminal AI assistant and the Python framework behind it. Tool-calling, sandboxed execution, multi-agent teams, skills, checkpoints, unlimited context - on Pydantic AI, any model.

Learn Cloud Applied Generative AI Engineering (GenEng) using OpenAI, Gemini, Streamlit, Containers, Serverless, Postgres, LangChain, Pinecone, and Next.js

A hub for various industry-specific schemas to be used with VLMs.

A transparent, minimal, and hackable agent framework. ~300 lines of readable code. Full control, no magic.

The missing bridge between your ML models and your AI agents.

Directly Connecting Python to LLMs via Strongly-Typed Functions, Dataclasses, Interfaces & Generic Types