Developer Builds Scheme Compiler to WASM Using AI in 4 Days

Matthew Phillips built Puppy Scheme, a Scheme compiler that compiles to WebAssembly, in approximately four days with AI assistance. The project was inspired by seeing others quickly build near-production-level tools that would normally take months or years.
Key Features and Capabilities
The compiler includes:
- Support for 73% of R5RS and R7RS Scheme standards
- Support for WASI 2 and the Component Model
- Uses WASM GC (garbage collection)
- Pretty good dead-code elimination, creating small binaries
- Self-hosting capability - Puppy compiles its own source code to puppyc.wasm
- A wasmtime wrapper to create native binaries
- A website that runs on Puppy wasm in Cloudflare Workers
Performance Improvements
One night, Phillips told Claude to "grind on performance" and when he woke up, compilation time had improved from 3½ minutes down to 11 seconds.
Example Code
The project includes a component model example:
(define count 0)
(define (counter-view)
(html
(div (@ (class "counter"))
(button (@ (on "click" "on_decrement")) "-")
(span (@ (class "count")) ,(number->string count))
(button (@ (on "click" "on_increment")) "+"))))
(define (handle-event handler)
(cond
((equal? handler "on_decrement")
(if (> count 0)
(set! count (- count 1))))
((equal? handler "on_increment")
(set! count (+ count 1)))))
Current Status
The compiler is still alpha quality, and Phillips runs into bugs frequently, so it's probably not ready for anyone other than him to use. However, he notes that "the number of features is impressive for how little time I spent on it." The project demonstrates how AI can accelerate development of complex compiler projects.
Phillips worked on this as a side project, spending most of a weekend plus an hour or two on a couple of weekday nights. He's not sure where he'll take it from here, but the project is available at puppy-scheme.org.
📖 Read the full source: HN AI Agents
👀 See Also

docvault: Generate Local API Docs to Reduce AI Hallucinations
docvault is a tool that generates markdown API references from source code to help Claude and other LLMs stop hallucinating function signatures. It works for Rust crates and Python packages, outputs a two-tier markdown file, and includes a Claude Code plugin for hands-free operation.

LiteParse: Fast Open-Source Document Parser for AI Agents
LiteParse is an open-source document parser that provides spatial text parsing with bounding boxes, runs locally without GPUs, and supports PDFs, Office documents, and images. It can be installed as a skill for 40+ AI agents including Claude Code, Cursor, and OpenClaw.

OpenClaw SEO Audit Skill Released for Technical Website Analysis
A new OpenClaw skill performs comprehensive SEO audits with the command 'seo audit [url]', checking technical SEO, content quality, on-page elements, structured data, performance metrics, images, and AI search readiness, outputting a health score and prioritized action plan.

Graphify: A Claude Code Skill That Built a Knowledge Graph of Your Repo — 450k Downloads, 40k Stars in 26 Days
Graphify is a Claude Code skill that reads every file in your repo, builds a knowledge graph with Leiden community detection, and queries it at 71x fewer tokens than raw files. 450k+ PyPI downloads, ~40k GitHub stars, #2 global rank in first week.