{"slug": "pydanticai", "name": "PydanticAI", "category": "ai", "category_name": "AI models and assistants", "description": "", "recommenders": 3, "commenters": 6, "warners": 1, "score": 2.108, "rising": 0.35, "first": "2025-11-19", "latest": "2026-08-05", "why": "I really like https://ai.pydantic.dev/ as it builds on existing developer knowledge and there is not much to learn in the framework itself.", "why_is_quote": true, "has_verdict": false, "sentiment": {"recommend": 3, "neutral": 2, "compare": 0, "warn": 1}, "spark": [2, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0], "listed": true, "loved": [], "caveat": "", "short_quote": "I really like https://ai.pydantic.dev/ as it builds on existing developer knowledge and there is not much to learn in the framework itself.", "icon": true, "domain": "pydantic.dev", "github_repo": null, "official_url": "https://ai.pydantic.dev", "pricing": "", "aliases": ["PydanticAI", "Pydantic AI", "pydantic-ai"], "verdict": null, "praise": [{"label": "", "summary": "", "quotes": [{"id": 786973992, "item_id": 49185874, "url": "https://news.ycombinator.com/item?id=49185874", "by": "Gayithri2026", "date": "2026-08-05", "stance": "recommend", "quote": "multi-provider (OpenAI/Claude/Gemini/Bedrock), swappable in one line via PydanticAI.", "excerpt": "Location: San Jose, CA (SF Bay Area) Remote: Yes Willing to relocate: No Technologies: Python, FastAPI, PostgreSQL/pgvector, RAG, LangChain, PydanticAI, Celery, Redis, Docker, AWS, Langfuse, Java, Spring Boot R\u00e9sum\u00e9/CV: https://github.com/Gayithri606/resume/blob/main/GayithriPonnapalli-Resume.pdf Email: gayithri@pojoai.com AI engineer building RAG chatbots and AI-driven workflow automation. Five years of production J", "context": "AI engineer building RAG chatbots", "use_case": "multi-provider LLM agents", "switched_from": "", "story": "Ask HN: Who wants to be hired? (August 2026)"}, {"id": 736034560, "item_id": 46002160, "url": "https://news.ycombinator.com/item?id=46002160", "by": "raooll", "date": "2025-11-20", "stance": "recommend", "quote": "I really like https://ai.pydantic.dev/ as it builds on existing developer knowledge and there is not much to learn in the framework itself.", "excerpt": "I really like https://ai.pydantic.dev/ as it builds on existing developer knowledge and there is not much to learn in the framework itself.", "context": "", "use_case": "building AI agents", "switched_from": "", "story": "Ask HN: Best solution to build AI agents?"}, {"id": 735741473, "item_id": 45983842, "url": "https://news.ycombinator.com/item?id=45983842", "by": "ouk", "date": "2025-11-19", "stance": "recommend", "quote": "I use it with the PydanticAI framework and it's quite nice.", "excerpt": "There is also PydanticAI Gateway (https://ai.pydantic.dev/gateway/). I use it with the PydanticAI framework and it's quite nice.", "context": "", "use_case": "LLM agent framework", "switched_from": "", "story": "Control LLM Spend and Access with any-LLM-gateway"}]}], "caveats": [{"label": "", "summary": "", "quotes": [{"id": 781973809, "item_id": 48873363, "url": "https://news.ycombinator.com/item?id=48873363", "by": "reveriedev", "date": "2026-07-11", "stance": "warn", "quote": "Getting those agent systems to behave reliably was often annoying and tricky.", "excerpt": "Back in the medieval age of 2025, I used frameworks like PydanticAI and LangGraph to build agents. Getting those agent systems to behave reliably was often annoying and tricky. Claude Code and Codex have since become capable general-purpose agents. They each have an SDK, but those SDKs expose different interfaces and inherit their respective platform\u2019s quirks. While building CodeAlmanac, I wanted one way to work with", "context": "", "use_case": "building agents", "switched_from": "", "story": null}]}], "who": [{"by": "Gayithri2026", "context": "AI engineer building RAG chatbots", "url": "https://news.ycombinator.com/item?id=49185874", "date": "2026-08-05"}], "tags": [], "use_cases": ["multi-provider llm agents", "building agents", "agent foundation", "agent framework", "building ai agents", "llm agent framework"], "compared": [{"slug": "claude-code", "name": "Claude Code", "co": 2, "switched_from": 0, "switched_to": 2}], "makers": [], "threads": [{"url": "https://news.ycombinator.com/item?id=49156682", "title": "Ask HN: Who wants to be hired? (August 2026)", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=48873362", "title": "item 48873362", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46250874", "title": "PydanticAI-DeepAgents \u2013 Build powerful AI agents", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=46013935", "title": "Agent design is still hard", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=45999648", "title": "Ask HN: Best solution to build AI agents?", "mentions": 1}, {"url": "https://news.ycombinator.com/item?id=45903485", "title": "Control LLM Spend and Access with any-LLM-gateway", "mentions": 1}], "sentiment_by_month": {"2025-11": {"recommend": 2, "neutral": 1}, "2025-12": {"neutral": 1}, "2026-01": {}, "2026-02": {}, "2026-03": {}, "2026-04": {}, "2026-05": {}, "2026-06": {}, "2026-07": {"warn": 1}, "2026-08": {"recommend": 1}, "2026-09": {}, "2026-10": {}}, "quotes": [{"id": 786973992, "item_id": 49185874, "url": "https://news.ycombinator.com/item?id=49185874", "by": "Gayithri2026", "date": "2026-08-05", "stance": "recommend", "quote": "multi-provider (OpenAI/Claude/Gemini/Bedrock), swappable in one line via PydanticAI.", "excerpt": "Location: San Jose, CA (SF Bay Area) Remote: Yes Willing to relocate: No Technologies: Python, FastAPI, PostgreSQL/pgvector, RAG, LangChain, PydanticAI, Celery, Redis, Docker, AWS, Langfuse, Java, Spring Boot R\u00e9sum\u00e9/CV: https://github.com/Gayithri606/resume/blob/main/GayithriPonnapalli-Resume.pdf Email: gayithri@pojoai.com AI engineer building RAG chatbots and AI-driven workflow automation. Five years of production J", "context": "AI engineer building RAG chatbots", "use_case": "multi-provider LLM agents", "switched_from": "", "story": "Ask HN: Who wants to be hired? (August 2026)"}, {"id": 781973809, "item_id": 48873363, "url": "https://news.ycombinator.com/item?id=48873363", "by": "reveriedev", "date": "2026-07-11", "stance": "warn", "quote": "Getting those agent systems to behave reliably was often annoying and tricky.", "excerpt": "Back in the medieval age of 2025, I used frameworks like PydanticAI and LangGraph to build agents. Getting those agent systems to behave reliably was often annoying and tricky. Claude Code and Codex have since become capable general-purpose agents. They each have an SDK, but those SDKs expose different interfaces and inherit their respective platform\u2019s quirks. While building CodeAlmanac, I wanted one way to work with", "context": "", "use_case": "building agents", "switched_from": "", "story": null}, {"id": 740014001, "item_id": 46250875, "url": "https://news.ycombinator.com/item?id=46250875", "by": "kacper-vstorm", "date": "2025-12-12", "stance": "neutral", "quote": "It's built on top of pydantic-ai", "excerpt": "Hey HN, I've been working on pydantic-deepagents, a framework for creating deep AI agents that go beyond simple chatbots. It's built on top of pydantic-ai (which leverages Pydantic for structured data), but adds serious muscle: planning capabilities, filesystem access, subagent spawning, and more. Think of it as a toolkit for agents that can handle real-world tasks like file processing, task organization, and even hu", "context": "", "use_case": "agent foundation", "switched_from": "", "story": "PydanticAI-DeepAgents \u2013 Build powerful AI agents"}, {"id": 736237297, "item_id": 46014831, "url": "https://news.ycombinator.com/item?id=46014831", "by": "mritchie712", "date": "2025-11-22", "stance": "neutral", "quote": "We've tried many approaches and frameworks over the past 2 years (e.g. PydanticAI), but using cc is the first that has felt magic.", "excerpt": "Some things we've[0] learned on agent design: 1. If your agent needs to write a lot of code, it's really hard to beat Claude Code (cc) / Agent SDK. We've tried many approaches and frameworks over the past 2 years (e.g. PydanticAI), but using cc is the first that has felt magic. 2. Vendor lock-in is a risk, but the bigger risk is having an agent that is less capable then what a user gets out of chatgpt because you're ", "context": "", "use_case": "agent framework", "switched_from": "", "story": "Agent design is still hard"}, {"id": 736034560, "item_id": 46002160, "url": "https://news.ycombinator.com/item?id=46002160", "by": "raooll", "date": "2025-11-20", "stance": "recommend", "quote": "I really like https://ai.pydantic.dev/ as it builds on existing developer knowledge and there is not much to learn in the framework itself.", "excerpt": "I really like https://ai.pydantic.dev/ as it builds on existing developer knowledge and there is not much to learn in the framework itself.", "context": "", "use_case": "building AI agents", "switched_from": "", "story": "Ask HN: Best solution to build AI agents?"}, {"id": 735741473, "item_id": 45983842, "url": "https://news.ycombinator.com/item?id=45983842", "by": "ouk", "date": "2025-11-19", "stance": "recommend", "quote": "I use it with the PydanticAI framework and it's quite nice.", "excerpt": "There is also PydanticAI Gateway (https://ai.pydantic.dev/gateway/). I use it with the PydanticAI framework and it's quite nice.", "context": "", "use_case": "LLM agent framework", "switched_from": "", "story": "Control LLM Spend and Access with any-LLM-gateway"}]}