Thanks to @sa.muelcolvin.com (@pydantic.dev) and @badmonster0.bsky.social (@cocoindex.bsky.social)
for their sessions, and to @awscloud.bsky.social Builder Loft for hosting us.

Pydantic Monty: A Minimal Python Sandbox for AI Agents | Pydantic Meet Monty — a secure, minimal Python interpreter written in Rust for running AI-generated code. Learn where it sits between tool calling and full computer use, and why CodeMode matters for AI agents.

A few weeks ago our founder announced Monty, a minimal, secure Python interpreter written in Rust, for running code written by AI agents. People got excited. @sa.muelcolvin.com just wrote up the full story on why he's excited about it and you should be too.
pydantic.dev/articles/pyd...

GitHub - pydantic/monty: A minimal, secure Python interpreter written in Rust for use by AI A minimal, secure Python interpreter written in Rust for use by AI - pydantic/monty

Pydantic's Monty

A minimal, secure Python interpreter written in Rust for use by AI.

github.com/pydantic/monty

Rust continues its march to power all of the Python ecosystem...

Samuel Colvin of @pydantic.dev just announced Monty, "a minimal, secure Python interpreter written in Rust for use by AI"

Learn more about the 🐍 + 🦀 magic happening at Pydantic with our podcast linked below:

filtra.io | Pydantic: The Python Darling That Loves Rust A filtra.io interview featuring Pydantic.

Podcast with Pydantic: filtra.io/rust/intervi...

Stream #35: Production-grade AI agents with SurrealDB & Pydantic AI YouTube video by SurrealDB

We’re gearing up for our first SurrealDB Stream of 2026. On Jan 8, join @sa.muelcolvin.com (CEO and Founder at @pydantic.dev) and our own Tobie Morgan Hitchcock to explore the practical challenges of taking Graph-RAG agents from experiment to production with SurrealDB and
Pydantic AI.👇

Thanks to @pydantic.dev for inviting us to be part of the Py AI Festive Meetup in London. A great evening of lightning sessions from Pydantic, WALT Labs, and our own @martinschaer.bsky.social, with plenty of good conversation in between. Thanks as well to Google Cloud for hosting.

Pydantic AI with Samuel Colvin - Software Engineering Daily Python’s popularity in data science and backend engineering has made it the default language for building AI infrastructure. However, with the rapid growth of AI applications, developers are increasin...

Samuel Colvin is the creator of @pydantic.dev and Pydantic AI. He joins Gregor Vand to talk about Pydantic origin, type safe AI applications, Pydantic AI’s evolution, LogFire observability, and the future of sustainable open-source AI tooling.

@sa.muelcolvin.com

bit.ly/3Mj4SkE

Some personal (very belated*) news, I've moved to the bay area!

Let me know if you're in SF or Palo Alto and want to get coffee.

Also, last reminder that we have the inaugural Py AI meetup with @pydantic.dev in SF on Tuesday. Register now: luma.com/gjtfecc7

* I actually got here in the summer.

A screenshot of using Logfire + DBOS + Pydantic AI agent.

I wrote a tutorial on integrating DBOS with Logfire. It's super easy to set up (kudos to the @pydantic.dev team!) -> just a few lines to configure the exporter and your Logfire write token. Once it's running, you'll get a unified view of your app with logs + traces in one place.

Py AI Meetup · Luma Join us for an evening of cutting-edge AI discussions featuring lightning talks from leading practitioners: Samuel Colvin (CEO of Pydantic) Reducto + Modal…

I'm teaming up with @sa.muelcolvin.com to launch a new meetup series, Py AI.

Our first one is November 11 in San Francisco with talks from @pydantic.dev, @modal-labs.bsky.social, ReductoAI and @fastmcp.bsky.social.

Hosted by our friends at pebblebed.com

RSVP here: luma.com/gjtfecc7

Just putting this here. Not much more to say.

@pydantic.dev

New social icon for @opensourcepledge.com spotted on
@pydantic.dev's website. Lookin' sharp! 👀

uv tree for dbos v2.0.0

Several people (thanks to @mitsuhiko.at and @sa.muelcolvin.com) noted early on that DBOS had too many dependencies. In the latest Python release, we trimmed it down to just 6 direct deps while still implementing durable workflows and queues in one library.

It's lightweight (for real).

You made my day @pydantic.dev 😁
pydantic.dev/articles/pyd...

ICYMI, #Heroku support for @pydantic.dev is here.

To get started, all you have to do is provision Managed Inference and Agents from Heroku Elements or via the command line.

🔗 https://sforce.co/3Ii73mR

AG-UI - Pydantic AI Agent Framework / shim to use Pydantic with LLMs

Pydantic AI now supports AG-UI - an open protocol for building chat agents, meaning you can use existing frontend apps to interact with @pydantic.dev AI agents.

ai.pydantic.dev/ag-ui/#agent...

Well true, but that's kind of different.

Is this (the content of the screenshot) really true? No one has offered me any money 😢

I don't care. But if you do the underscore thing, that doesn't apply.

Podcast with @sa.muelcolvin.com on Software Engineering Radio is out!

Covers the @pydantic.dev ecosystem including Pydantic Validation, Pydantic AI and @logfire.pydantic.dev. Well worth a listen.

se-radio.net/2025/07/se-r...

Human-seeded Evals: Scaling Judgement with LLMs (with Samuel Colvin) · Luma Everyone agrees evals are essential—but almost no one implements them rigorously. Why? They're hard to write, time-consuming, and brittle. Samuel Colvin,…

I'm chatting to Hugo Bowne-Anderson tomorrow about Human Seeded Evals and @logfire.pydantic.dev on Youtube at 4pm UK.

I'm pretty confident something like the think I'm describing here is where we'll end up with evals. Please join, I'd love to hear what you think.

lu.ma/voeyx7n1

Feature Request: `mode` parquet, or access to the preview query as a view via `_` · duckdb duckdb · Discussion #17122 I'd really like a way to output a query to a parquet file (in order to plot the results). I think the simplest way to do this would be to support .mode parquet This wouldn't affect the mode of prin...

@hannes.muehleisen.org I want this about 3 times a day and I can't be the only one.

We discussed it at data council and you seemed keen to implement something. Please can it happen 🙏.

github.com/duckdb/duckd...

Building AI Applications the Pydantic Way (Sponsor: Pydantic) - PyCon US 2025 PyCon US 2025

At @pycon.us today @sa.muelcolvin.com is talking about Pydantic AI and Pydantic Logfire.

Room 316, 11.30 today.

There will be code.

us.pycon.org/2025/schedul...

Pydantic, Jason Liu & MCP Meetup - April 8, 2025 YouTube video by Pydantic

The recording of last week's meetup with Jason Liu, David Soria Parra (Anthropic), OpenAI and @sa.muelcolvin.com is now live on youtube.

Notably this includes David's plan for the future of MCP.

youtu.be/GqufkaLJV44

GitHub - gi0baro/emmett-mcp: MCP extension for Emmett framework MCP extension for Emmett framework. Contribute to gi0baro/emmett-mcp development by creating an account on GitHub.

Yo! Spent the weekend over MCP and built something.
You can now build MCP servers in your Emmett application 👀
github.com/gi0baro/emme...

Python devs building AI (agents): Can we chat about your experience? My name is Greg Kogan and I'm conducting user research with experienced Python developers who build AI applications, particularly agent-based systems. If selected, we'll do a 45-minute Zoom interview ...

Are you building agents, or building with AI more generally?

Double win:

* Help make @logfire.pydantic.dev better
* Get $100 Amazon voucher

Sign up for a short interview with the amazing Greg Kogan:

docs.google.com/forms/d/e/1F...

THE EVAL HAS LANDED. 🦅

pydantic-evals has been a major piece of work from David Montague over the last month.

I'm pretty excited to see it move the dial on how easily Python developers can benchmark and improve AI code.

Yup fair.

It's all a bit nuts.

?