llm-as-computer

npx skills add majiayu000/claude-skill-registry --skill llm-as-computer --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

# LLM-as-Computer: Compiled Transformer Stack Machine A working computer built from transformer primitives. Every instruction fetch and stack read is a parabolic attention head (dot-product → argmax → value extraction). The transformer's weights ARE the interpreter — compiled analytically, not trained. ## What This Proves Attention is lookup; feed-forward is routing. A vanilla transformer with compiled weights can execute arbitrary programs: loops, recursion, arithmetic, memory access. 55 opcodes covering WASM i32 semantics. 21M+ steps/second via the Mojo executor. ## Setup (once per session) ```bash cd /mnt/skills/user/llm-as-computer/src && bash setup.sh ``` This installs Mojo (~20s) and compiles the executor binary (~6s). If Mojo is unavailable, the skill falls back to a pure-Python executor (slower but functional). ## Usage ```python import sys sys.path.insert(0, '/mnt/skills/user/llm-as-computer/src') from programs import make_fibonacci, make_factorial, make_gcd, make_multiply from runner import run, setup # Ensure Mojo is compiled (idempotent) setup() # Run a program — shows instructions, trace, result prog, expected = make_fibonacci(10) print(run(prog)) # Benchmark mode — me

cd /mnt/skills/user/llm-as-computer/src && bash setup.sh
cd /mnt/skills/user/llm-as-computer/src
for f in executor.mojo; do
curl -sL -H "Authorization: token $GH_TOKEN" -H "Accept: application/vnd.github.v3.raw" \
done
for f in isa_lite.py programs.py runner.py; do
rm -f percepta_exec  # force recompile
bash setup.sh