Vilson Vieira automata

I create algorithms that create.

automata / agent.py

Created March 10, 2026 17:22

Minimal Coding Agent in Python

	import json
	import os
	import subprocess
	from pathlib import Path
	from openai import OpenAI

	MODEL = "anthropic/claude-opus-4-6"
	SYSTEM_PROMPT = (
	"You are a precise coding assistant. "
	"Use tools when needed. Keep changes minimal and explain clearly."

automata / config.json

Created July 16, 2025 10:14

Kimi K2 + Claude Code + Groq

	{
	"LOG": false,
	"OPENAI_API_KEY": "",
	"OPENAI_BASE_URL": "",
	"OPENAI_MODEL": "",
	"Providers": [
	{
	"name": "groq",
	"api_base_url": "https://api.groq.com/openai/v1/chat/completions",
	"api_key": "YOUR_GROQ_API_KEY",

automata / bashrc

Created July 14, 2025 18:00

Kimi K2 + Claude Code

	kimi() {
	export ANTHROPIC_BASE_URL="https://api.moonshot.ai/anthropic"
	export ANTHROPIC_AUTH_TOKEN="YOUR_KIMI_API_KEY"
	claude $@
	}

automata / config.json

Created July 14, 2025 13:13

Kimi K2 + Claude Code Router + Claude Code

	{
	"Providers": [
	{
	"name": "kimi-k2",
	"api_base_url": "https://openrouter.ai/api/v1/chat/completions",
	"api_key": "OPENROUTER_API_KEY",
	"models": [
	"moonshotai/kimi-k2"
	],
	"transformer": {

automata / run.sh

Last active November 23, 2024 02:26

Freeing space from Docker on Windows WSL

	# Freeing space from Docker on Windows WSL
	# (No need for HyperV and optimize-vhd: works on Windows Home Edition)

	# Make sure to keep the images you really need running on Docker, this way the following command will
	# only delete the cached layers:

	# On WSL:
	docker system prune -a

	# On PowerShell:

automata / install_mlir_tutorial.sh

Created January 18, 2024 20:57

Install MLIR tutorial on Mac

	brew install cmake cache ninja
	git clone https://github.com/llvm/llvm-project.git
	mkdir llvm-project/build
	cd llvm-project/build
	cmake -G Ninja ../llvm \
	-DLLVM_ENABLE_PROJECTS=mlir \
	-DLLVM_BUILD_EXAMPLES=ON \
	-DLLVM_TARGETS_TO_BUILD="Native;ARM;X86" \
	-DCMAKE_BUILD_TYPE=Release \
	-DLLVM_ENABLE_ASSERTIONS=ON \

automata / run.py

Last active November 29, 2023 19:50

Running finetuned Mistral 7B on MacBook Air M2 (~7 tok/sec)

	# Instead of using llama.cpp directly, interface it through llama-cpp-python.
	#
	# Run:
	# python3 -m venv venv
	# source venv/bin/activate
	# CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install llama-cpp-python
	#
	from llama_cpp import Llama

	if __name__ == "__main__":

automata / Dockerfile

Created September 7, 2023 17:58

Mojo Docker

	FROM ubuntu:22.04

	# Install initial dependencies
	RUN apt-get update && apt-get install -y curl gpg

	# Install modular
	RUN apt-get install -y apt-transport-https && \
	keyring_location=/usr/share/keyrings/modular-installer-archive-keyring.gpg && \
	curl -1sLf 'https://dl.modular.com/bBNWiLZX5igwHXeu/installer/gpg.0E4925737A3895AD.key' \| gpg --dearmor >> ${keyring_location} && \
	curl -1sLf 'https://dl.modular.com/bBNWiLZX5igwHXeu/installer/config.deb.txt?distro=debian&codename=wheezy' > /etc/apt/sources.list.d/modular-installer.list && \

automata / mojograd.mojo

Last active September 6, 2023 02:01

	from random import random_float64
	from math import tanh

	@value
	@register_passable("trivial")
	struct Value:
	var r: Pointer[Int]
	var l: Pointer[Int]
	var data: Float64
	var grad: Float64

automata / launch.json

Created October 23, 2022 15:20

Launch config for Unity Debugger