pydantic-ai

AI observability platform for production LLM and agent systems.

Full-stack AI app generator — FastAPI + Next.js with AI Agents, RAG, streaming, auth, and 20+ integrations out of the box.

OpenTelemetry Instrumentation for AI Observability

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.

AI-powered multi-agent system that automatically analyzes codebases and generates comprehensive documentation. Features GitLab integration, concurrent processing, and multiple LLM support for better code understanding and developer onboarding.

Agentic RAG for local and self-hosted document search: hybrid retrieval, reranking and multimodal RAG on embedded LanceDB, with Docling parsing and an MCP server

Unlock 650+ MCP servers tools in your favorite agentic framework.

This package implements Agent Skills (https://agentskills.io) support with progressive disclosure for Pydantic AI. Supports filesystem and programmatic skills.

Agent traces you can run, not just read.

Running local Language Language Models (LLM) to perform Retrieval-Augmented Generation (RAG)

A unified agent orchestration hub that lets you configure and manage multiple AI agents (native, ACP, AGUI, Claude Code) via YAML, and exposes them through standardized protocols (ACP/OpenCode Server).

Arrest is a small utility to easily structure and validate your REST api calls using pydantic and httpx

AI-powered synthetic data generation — structured tables, unstructured documents, multi-provider LLM support, referential integrity, and code-gen mode for millions of rows

🐮 Build distributed, event-driven agents

A production-ready FastAPI platform with modular components and a built-in control plane.

🐙 Drop-in tools that give AI agents reliable, permission-aware access to external systems.

File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access control. Enables secure multi-user handling and testing in agents via in-memory, local, or containerized storage.

An opinionated list of awesome Pydantic-AI frameworks, libraries, software and resources.

Code examples for Building Effective Agents ported and adapted to use Pydantic AI

Guardrail capabilities for Pydantic AI — cost tracking, prompt injection detection, PII filtering, secret redaction, tool permissions, and async guardrails. Built on pydantic-ai's native capabilities API.