# Pydantic AI

> Type-safe Python agent framework from the Pydantic team with model-agnostic agents, tools and evals

Source: https://dontaskagain.com/pydantic-ai
Website: https://ai.pydantic.dev/?utm_source=dontaskagain
Pricing: Free
Categories: [Agent frameworks](https://dontaskagain.com/categories/agent-frameworks.md), [Open source](https://dontaskagain.com/categories/open-source.md)
Listed: 2026-10-19
Updated: 2026-10-19

Pydantic AI is an open-source Python agent framework from the team behind the Pydantic validation library. It provides a typed, extensible agent loop where switching models is a one-string change, and the same agent can run behind a web frontend, in a terminal, on a voice call, on a durable queue or in GitHub Actions.

**Key features:**

- Build typed agents that work with any major model provider.
- Add memory, guardrails, sub-agents, planning and persistence with Pydantic AI Harness.
- Run a full terminal coding agent with workspace file access and an allowlisted shell.
- Grade outputs and tool-call trajectories with Pydantic Evals.
- Use Pydantic Graph for typed control flow and Monty to sandbox model-written Python.
- Generate images, embeddings and realtime voice from the same SDK.

Pydantic AI is free under the MIT license and installs with pip or uv. Instrumentation is plain OpenTelemetry, so any backend works; the optional Pydantic Logfire platform and AI Gateway are separate products with a free personal tier.

## More agent frameworks

- [Browser Use](https://dontaskagain.com/browser-use.md): Open-source browser agent and cloud browsers that complete web tasks like form filling, checkout and data extraction
- [Stagehand](https://dontaskagain.com/stagehand.md): Open-source SDK for building browser agents with Playwright-style APIs plus natural-language act, observe and extract
- [LangGraph](https://dontaskagain.com/langgraph.md): Open-source, low-level orchestration framework and runtime for building stateful, controllable agents
- [CrewAI](https://dontaskagain.com/crewai.md): Multi-agent framework and enterprise platform for building, running and governing teams of role-based agents
- [OpenAI Agents SDK](https://dontaskagain.com/openai-agents-sdk.md): OpenAI's lightweight Python framework for building agents with tools, handoffs, guardrails, sessions and tracing
- [Mastra](https://dontaskagain.com/mastra.md): Open-source TypeScript framework for building agents and workflows with memory, evals and observability
- [Agno](https://dontaskagain.com/agno.md): Open-source agent framework and self-hosted runtime for building agents, teams and workflows in your own cloud
- [LlamaIndex](https://dontaskagain.com/llamaindex.md): Document parsing and extraction platform (LlamaParse) plus the open-source LlamaIndex framework for document agents
- [AI SDK](https://dontaskagain.com/ai-sdk.md): Open-source TypeScript toolkit from Vercel for building AI apps and agents with streaming and multi-model support
- [Letta](https://dontaskagain.com/letta.md): Research lab behind MemGPT building stateful agents with persistent, self-improving memory