Simon Willison explored how to programmatically map SQLite query result columns back to their source table and column names — a capability that would let Datasette enrich query results with contextual metadata. He tasked Claude Code (Opus 4.8) with finding solutions, which surfaced three approaches: using the apsw library, calling SQLite's sqlite3_column_table_name() C function via Python ctypes, and parsing EXPLAIN bytecode output. The research is published as a GitHub README and covers the tradeoffs of each technique.
Simon Willison announced asyncinject 0.7, a release of his Python utility library for an asyncio dependency injection pattern. He originally built the library a few years ago and has used it with Datasette. The notable angle is that Claude Fable 5 spotted bugs in the dependency and fixed them, which Willison describes as unusually proactive behavior.
Simon Willison released micropython-wasm 0.1a2, with the main change being a new CLI. The CLI was added from issue #7 and was inspired while drafting a related post about MicroPython in a sandbox. Its purpose is to make the post's “Try it yourself” section easier to demonstrate and follow, especially for readers experimenting with Python, WebAssembly, and sandboxing.
Simon Willison describes his latest attempt to safely run Python plugin-style code inside his own applications. The alpha package micropython-wasm uses MicroPython compiled to WebAssembly, executed through the maintained wasmtime Python library. His goals include clean PyPI installation, CPU and memory limits, controlled file and network access, host functions, and reliable documentation.
Simon Willison released datasette-agent-micropython 0.1a0, an alpha aimed at letting Datasette Agent generate and execute Python safely. The project focuses on sandboxing, with MicroPython and WebAssembly-related techniques suggested by the tags. Willison says the early results look promising and that GPT-5.5 has not yet escaped the sandbox, though this remains an early alpha.
Simon Willison released micropython-wasm 0.1a1, a small update connected to Python, sandboxing, and WebAssembly. The release fixes limitations that appeared while he was trying to use it to build datasette-agent-micropython. The post does not list detailed changes, so this should be read as an early usability and compatibility improvement rather than a major feature launch.
Simon Willison released micropython-wasm 0.1a0, an alpha package described as his latest sandboxing experiment. It bundles a lightly customized WASM build of MicroPython with a wrapper for executing code through wasmtime. The post is brief, but relevant to developers tracking Python sandboxing, WebAssembly runtimes, and controlled execution environments.
Simon Willison demonstrates an experiment for running Python ASGI apps entirely in the browser using Pyodide and a Service Worker. The approach addresses a Datasette Lite limitation: HTML returned through intercepted navigation did not execute script tags, breaking features and plugins. Claude Opus 4.8, used through Claude Code for web, helped explore the implementation. Basic ASGI and Datasette 1.0a31 demos are available.
Simon Willison revisited pydantic-monty, a sandboxed subset of Python implemented in Rust. He asked Claude Code to inspect the most recent release, following his earlier exploration a few months ago. The key finding is that limits for execution duration, memory, allocations, and recursion depth all appear to behave as advertised.
The Hugging Face official blog has announced the launch of "Modular Diffusers" — a major architectural overhaul of its widely popular `diffusers` library. In…
The official Vercel Changelog announces that the bundle size limit for Python Vercel Functions (serverless functions) has been significantly raised to 500MB…
With the explosion of generative AI applications, modern web development has increasingly converged on a golden combination: Next.js (React) on the frontend…
In this Hugging Face blog post, the team takes a deep dive into the evolution of AI agent architectures — specifically how to combine "structured constraints"…
Hugging Face recently published a highly practical technical tutorial demonstrating how to build a fully functional miniature AI agent in just around 70 lines…
Since Anthropic introduced the Model Context Protocol (MCP) open standard, connecting large language models (LLMs) to external tools has never been easier. The…
In this Hugging Face blog post, the team demonstrates how to implement a fully functional, lightweight AI agent (referred to as a "Tiny Agent") that supports…
Hugging Face's official blog published an article taking a deep dive into why Gradio is not just another simple UI library, but the most advantageous…
Hugging Face has officially launched FastRTC, an open-source real-time communication (RTC) library designed specifically for Python developers, aimed at…
On January 24, 2025, Hugging Face announced that smolagents — its open-source library designed for building lightweight, high-performance AI agents — now…
Hugging Face officially launched a lightweight AI agent development framework called `smolagents` at the end of 2024. The core philosophy of this tool is "Code…
Hugging Face and PyCharm — the renowned Python development tool from JetBrains — have announced a deep integration. This collaboration aims to streamline the…
In LLM application development, ensuring that a model outputs content that 100% conforms to a specific format — such as a JSON Schema, a regular expression, or…
As large language models (LLMs) have made tremendous strides in code generation, the long-standing industry gold standard — the HumanEval benchmark — has…
Hugging Face has officially launched Transformers Agents 2.0, a major refactoring and upgrade of its existing Agent framework, designed to provide developers…
Gradio, one of the most popular frameworks for rapid AI prototyping, has officially introduced its powerful "Reload Mode" (hot-reload functionality). In the…
Hugging Face has announced the launch of Gradio-Lite (@gradio/lite), a new library that enables Gradio applications to run entirely within the user's browser…
Hugging Face has announced official support for the Panel framework on its Spaces hosting platform. Previously, Spaces already supported popular tools such as…
This blog post from Replicate provides a clear and accessible introduction to running text-to-image models using Replicate's cloud API service. It serves as an…
This blog post is the second part (hands-on edition) of the Q-Learning section in Hugging Face's Deep Reinforcement Learning Class. The article aims to…
This is a practical tutorial guide written by Hugging Face, designed to help developers and data scientists quickly get started with sentiment analysis using…