Pydantic Ai Python Packages

logfire

AI observability platform for production LLM and agent systems.

openinference-semantic-conventions

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-langchain

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-openai

OpenTelemetry Instrumentation for AI Observability

pydantic-ai-skills

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

openinference-instrumentation-openai-agents

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-claude-agent-sdk

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-anthropic

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-litellm

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-google-genai

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-agno

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-google-adk

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-haystack

OpenTelemetry Instrumentation for AI Observability

pydantic-ai-backend

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.

openinference-instrumentation-pydantic-ai

OpenTelemetry Instrumentation for AI Observability

openinference-instrumentation-llama-index

OpenTelemetry Instrumentation for AI Observability

pydantic-ai-shields

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.

pydantic-ai-todo

Task Planning and Tracking toolset for Pydantic AI agents, enabling hierarchical task management with subtasks, PostgreSQL storage for multi-tenancy, and an event system for webhooks and callbacks.

subagents-pydantic-ai

Subagent Delegation framework for Pydantic AI, enabling nested subagents that can spawn their own specialists on-the-fly, with smart sync/async/auto mode selection, runtime agent creation, and clean multi-agent architecture. Adds specialization, parallel execution, and task cancellation.

summarization-pydantic-ai

Context Management processor for Pydantic AI agents, providing LLM-powered summarization or zero-cost sliding window trimming to handle infinite/long-running conversations without context overflow. Supports flexible triggers, safe cutoffs, and custom prompts for efficient AI apps.

openinference-instrumentation-bedrock

OpenTelemetry Instrumentation for AI Observability

pydantic-deep

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.

openinference-instrumentation-dspy

OpenTelemetry Instrumentation for AI Observability