Xmloxide – an agent-made Rust replacement for libxml2
Recently several AI labs have published experiments where they tried to get AI coding agents to complete large software projects. - Cursor attempted to make a browser from scratch: https://cursor.com/blog/scaling-agents - Anthropic attempted to make a C Compiler: https://www.anthropic.com/engineering/building-c-compiler I have been wondering if there are software packages that can be easily reproduced by taking the available test suites and tasking agents to work on projects until the existing test suites pass. After playing with this concept by having…
In plain words
Xmloxide is a Rust replacement for libxml2, the widely-used C library for parsing, creating, and manipulating XML and HTML documents. The project was generated by having an AI coding agent work through the existing test suites until they passed, demonstrating an approach to reproducing established software packages using AI assistance. It is intended for developers seeking a Rust alternative to the traditional libxml2 implementation.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Recently several AI labs have published experiments where they tried to get AI coding agents to complete large software projects. - Cursor attempted to make a browser from scratch: https://cursor.com/blog/scaling-agents - Anthropic attempted to make a C Compiler: https://www.anthropic.com/engineering/building-c-compiler I have been wondering if there are software packages that can be easily reproduced by taking the available test suites and tasking agents to work on projects until the existing test suites pass. After playing with this concept by having Claude Code reproduce redis and sqlite, I began looking for software packages where an agent-made reproduction might actually be useful. I found libxml2, a widely used, open-source C language library designed for parsing, creating, and manipulating XML and HTML documents. Three months ago it became unmaintained with the update, "This project is unmaintained and has [known security issues](https://gitlab.gnome.org/GNOME/libxml2/-/issues/346). It is foolish to use this software to process untrusted data.". With a few days of work, I was able to create xmloxide, a memory safe rust replacement for libxml2 which passes the compatibility suite as well as the W3C XML Conformance Test Suite. Performance is similar on most parsing operations and better on serialization. It comes with a C API so that it can be a replacement for existing uses of libxml2. - crates.io: https://crates.io/crates/xmloxide - GitHub release: https://github.com/jonwiggins/xmloxide/releases/tag/v0.1.0 While I don't expect people to cut over to this new and unproven package, I do think there is something interesting to think about here in how coding agents like Claude Code can quickly iterate given a test suite. It's possible the legacy code problem that COBOL and other systems present will go away as rewrites become easier. The problem of ongoing maintenance to fix CVEs and update to later package versions becomes a larger percentage of software package management work.
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 26d ago · cactuscompute.com
