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

Mozilla Thunderbolt: Open-Source Enterprise AI Client for Self-Hosted Infrastructure
Mozilla announced Thunderbolt, an open-source AI client under MPL 2.0 license designed for organizations to deploy self-hosted AI infrastructure with model choice, enterprise data integration, and cross-platform native applications.

Atelier v0.3 adds targeted markdown revisions with Claude Code
Atelier v0.3 is a free VS Code extension that lets you highlight sections of markdown documents and send them to Claude Code for revisions. The agent responds with targeted edits in the editor, and you can track which feedback each revision addresses.

Comparison of Four Managed OpenClaw Hosting Providers for 2026
A developer tested four managed OpenClaw hosting providers over two months, ranking them based on setup time, uptime, integration reliability, model routing, cost, and multi-step task handling. LobsterTank costs $2/month with basic container hosting, KiwiClaw is $39/month with better support, xCloud is $24/month with solid uptime, and RunLobster is $49/month with extensive tool integration and flat pricing.

devcontainer-mcp: Give AI Agents Their Own Dev Environment, Not Yours
devcontainer-mcp is an MCP server that exposes 45 tools for AI agents to create, manage, and work inside dev containers backed by Docker, DevPod, or GitHub Codespaces — keeping host machines clean.