I love Pydanticai, I dont wanna say that it is an underrated agentic framework (it has 12k stars on github) but this is truly the most developer friendly framework

Refactored my Invoice Generator Agent from using Autogen + Gpt 5 nano to -> PydanticAI + Groq + llama. From 2 minutes cut down into < 1 second. So fast man, unbelievable

Build production-grade Agentic AI apps in pure Python! PydanticAI is a Python agent framework designed to simplify building production-grade Agentic applications. 100% Open Source

Nice tutorials to learn to build AI Agents using PydanticAI (Link in comment)

MongoDB just released a repo with AI Agent and RAG code examples. Includes self-reflecting agents, multi-agent systems, chunking strategies, and vector embedding examples. Uses LangChain, PydanticAI, OpenAI, and all major frameworks and LLMs. 100% free and opensource.

A lot of people asked for a side by side comparison of DSPy and PydanticAI. Here it is! The example is taken directly from the PydanticAI's get started. I included FunctAI (a dspy wrapper for function style api), cause you know... ;) An interesting note is that Maverick could

MongoDB has a huge set of resources in a GenAI cookbook > build agents that reason and plan > optimise RAG pipelines > work with several frameworks (langchain, haystack, pydanticai) > store and scale embeddings with MongoDB Atlas link in replies

Creating a github repo about creating effective agents in PydanticAI, this is the using tools scenario for raw OpenAI SDK vs PydanticAI. Shortens the LOC more than 2x while also having minimal abstractions. Well done

This video covers essential tools & libraries for building Python LLM apps: - Structured Outputs (PydanticAI) - Unified LLM Access (OpenRouter) - Load Balancing (LiteLLM) - Monitoring & Logging (Lockfire) - Doc Parsing/Chunking (Dockling) - Vector DBs (Qdrant) - Web Search

there's some great british humor deep in the pydanticAI docs 😂

𝗜 𝗱𝗶𝘀𝘁𝗶𝗹𝗹𝗲𝗱 𝟰𝟬 battle-tested lessons from the Pioneer of AI Agents ▼ Learn How to Build AI Agents that boost Value, increase Success rates, and cut Risk — using frameworks like LangGraph, CrewAI, PydanticAI, MCP, and Swarm. 》 CORE MENTAL MODEL 𝟭. Expected value

PydanticAI: Build AI apps with Pydantic and LLMs

Finally had some time to publish a simple vibecoded tool I (and Claude Code) built to explore PydanticAI, Arbitron. Replicates a contest where jurors evaluate candidates in pairwise comparisons that get turned into a leaderboard.

Personal AI Agent Mind-Map This is a Multi-agent. Tech Stack: - Python's (Langchain and PydanticAI) - Supabase as DB for RAG and Memory I am building this for my Sem-end-Project.

PydanticAI is such a good tool. And they are shipping so fast, too.

これか！！！？まってたやつ MCP Run Python - PydanticAI -

An auto-commit generator using MCP and PydanticAI

✨【PydanticAI：PythonでAgentic AIアプリを構築！】✨ ✎. FYIG: https://t.co/XXn2U7I4q2 Pydanticチームが開発した、100%オープンソースのAgentic AIアプリケーション構築用フレームワーク「PydanticAI」をご紹介します！🎉 🚀

یه ریپوی خوب از Microsoft برای استفاده از مدلهای رایگان گیتهاب در فریمورک های مختلف... توی codespace هم میتونید اجراش کنید (وب) * AutoGen * LangGraph * Llamaindex * OpenAI * PydanticAI * Semantic Kernel * SmolAgents https://t.co/MO0cgtjYdr