wolfram-fb0

AI writes x86_64 assembly + eBPF for Wolfram fractals direct to /dev/fb0.
The entire build — agent loop, qemu boot, kernel trace — runs in a real Linux VM in your browser via islo. No install. Fork-and-rerun in one click.

Fork the sandbox → Code on GitHub How it works

↑ Rule 30, rendered live in your browser by the same algorithm as src/rule30_reference.s — the agent's target.

Why this needs a real VM, not a container

Most AI coding sandboxes are containers. Containers can't:

islo gives you a real virtualized VM in your browser, with a real kernel, real /dev/fb0, and real eBPF. Which means an AI agent can write code that talks to the kernel for real — and you can watch it happen from a tab.

The build, in five acts

  1. Provision — islo use wolfram-fb0 spins a real Linux VM with nasm, qemu, bpftrace, Ollama (+ the smallest Gemma), and opencode pre-warmed. ~30s to a working shell.
  2. Code — Inside the sandbox, islo skills (plan → build → review → refine) drive opencode with a local Gemma to write pure x86_64 assembly for Rule 30, Mandelbrot, and Julia. No libc, single ELF, talks to /dev/fb0 directly.
  3. Judge — An oracle in the same sandbox assembles each iteration, runs it in --ppm mode, pixel-diffs against a Python reference, and reports binary size. The agent optimizes both.
  4. Boot — qemu-system-x86_64 boots a 4 MB Linux straight into the agent-built ELF on a real framebuffer. AI-written bpftrace programs attach to the binary and stream every syscall + every byte mmapped to fb0.
  5. Share — islo share exposes the framebuffer stream + the eBPF event stream as public URLs. You see the fractal bloom in real time, with the kernel-side trace scrolling beside it.

Live from the sandbox

Framebuffer

Stream connects after a sandbox is forked.

eBPF trace

[trace] waiting for a forked sandbox…

Convergence

Binary size and pixel-diff vs iteration, by target. Filled in after the first full agent run.

chart will render here

Lineage

Fractint (1988) · FractalAsm · A New Kind of Science · islo · opencode

Try islo

Every new account on islo.dev ships with $50 of free credit — no card required. That's enough to spin a real-VM sandbox like this one and run the full convergence loop end-to-end yourself.

Get $50 credit on islo → Code on GitHub