Developer Builds Scheme Compiler to WASM Using AI in 4 Days

✍️ OpenClawRadar📅 Published: March 1, 2026🔗 Source
Developer Builds Scheme Compiler to WASM Using AI in 4 Days
Ad

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.

Ad

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

Ad

👀 See Also

Tendr Skill: Deterministic CLI Operations for Agent Memory Management
Tools

Tendr Skill: Deterministic CLI Operations for Agent Memory Management

Tendr Skill is an Agent Skill that separates reasoning from execution for structured long-term memory, allowing agents to decide what needs changing while a CLI tool handles structural operations deterministically. It supports [[wikilinks]] and explicit semantic hierarchies across files.

OpenClawRadar
graphify-ts: Local MCP server cuts Claude Code PR review tokens from 63K to 8.7K
Tools

graphify-ts: Local MCP server cuts Claude Code PR review tokens from 63K to 8.7K

graphify-ts builds a local knowledge graph of your codebase using tree-sitter AST + Louvain communities + BM25 + optional ONNX rerank, exposing it via MCP stdio. In production tests, it reduced input tokens by 2.6x and latency by 2.8x for code queries, and cut PR review prompts from 63K to 8.7K tokens.

OpenClawRadar
JobPilot: Claude Code Plugin for Automated Job Applications
Tools

JobPilot: Claude Code Plugin for Automated Job Applications

JobPilot is a Claude Code plugin that automates job searching and application processes using Playwright browser automation. It includes commands for searching job boards, auto-filling applications, generating cover letters, and tracking application statistics.

OpenClawRadar
ClawNet: Peer-to-Peer AI Agent Network Without API Keys
Tools

ClawNet: Peer-to-Peer AI Agent Network Without API Keys

ClawNet is a peer-to-peer network that allows AI agents to collaborate directly without API keys or platform fees. Installation is via a curl script, and features include a task bazaar, shell economy, and knowledge network.

OpenClawRadar