# Pydantic AI — card for AI agents

A Python agent framework from the Pydantic team, built around type-safe structured outputs, dependency injection and model-agnostic tool calling.

Maker: Pydantic · category: Agent frameworks and SDKs · open source (MIT)

## Price
- Pydantic AI is open source and free to use; you pay only for the models and infrastructure it runs on.
- Free tier: yes
- Checked: 2026-11-04

## Install
- PyPI: `pip install pydantic-ai`

## Facts
- Interfaces: Python library
- Repository: https://github.com/pydantic/pydantic-ai

## Numbers (AgentGid data)
- Gid Score: 53 (rank #53) (public popularity and activity, not quality)
- Downloads last 7 days: 1,569,286
- GitHub stars: 21,279

## Details (plan limits, live status, safety; from AgentGid's data)
Pydantic AI by Pydantic. Category: Agent frameworks and SDKs. Type: typed agent framework. A Python agent framework from the Pydantic team, built around type-safe structured outputs, dependency injection and model-agnostic tool calling. Open source (MIT) Pricing (checked 2026-11-04): Pydantic AI is open source and free to use; you pay only for the models and infrastructure it runs on. Free tier: yes. Interfaces: Python library Supports: mcp, local, multi_agent Data: Gid Score 53/100, #53 overall; #15 in its category; 21,279.0 GitHub stars; usage +21% over 30 days; latest release 2.71.0 (2026-11-19).

## Alternatives in the same category
- LangChain: https://agentgid.com/agents/langchain/agent.md
- LangGraph: https://agentgid.com/agents/langgraph/agent.md
- AI SDK: https://agentgid.com/agents/vercel-ai-sdk/agent.md
- Claude Agent SDK: https://agentgid.com/agents/claude-agent-sdk/agent.md
- Mastra: https://agentgid.com/agents/mastra/agent.md
- OpenAI Agents SDK: https://agentgid.com/agents/openai-agents-sdk/agent.md

## Links
- AgentGid page: https://agentgid.com/agents/pydantic-ai/

---
AgentGid's catalog is curated: every entry was checked against the maker's official pages (registry, repository, license and pricing pages) on the date shown; a license value shows the quote it stands on wherever AgentGid has one. Usage numbers come from AgentGid's own scan of public repositories set up for AI coding agents. Claims by makers are reported, not tested by AgentGid.
