convez.ai
SkillAutomaçãoIniciante
ilang-ai

AutoCode

ilang-ai/autocode

Do conceito ao deploy em uma conversa, zero configuração

Ver no GitHub
BomPluginScore · de 0 a 100

Skill que transforma descrições em código deployado automaticamente. Com 47 skills integradas, permite ir de ideia a website ao vivo em uma sessão, sem necessidade de conhecimento técnico profundo. Compatível com Claude Code, Cursor, Gemini e outras plataformas de IA.

Instalação

$npx convez-ai ilang-ai/autocode

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
107
Forks
22
Acompanhando
0
Saúde
50%
Último commit
há 4 semanas
Versão
v6.2.2
Issues abertas
0
Contribuidores
5

Casos de uso

  • Prototipagem rápida de aplicações web
  • Deploy automático de projetos sem DevOps
  • Geração e publicação de código com uma descrição natural

Veredito

AutoCode é prático para quem quer ir da ideia ao deploy rápido, mas depende da qualidade da descrição inicial e das limitações das skills predefinidas. Vale como ferramenta de prototipage ágil, não como solução completa de produção.

README

A tradução para o português deste README ainda está na fila.


language:

  • en tags:
  • skill
  • agent-skill
  • autocode
  • deployment
  • shipping
  • beginner-friendly
  • claude-code
  • codex
  • cursor
  • copilot
  • gemini
  • hermes
  • i-lang
  • zero-dependency license: mit

⚡ AutoCode

You say it. AutoCode ships it.

MIT v5.0.0 Skills Zero Deps Platforms I-Lang L2 I-Lang

🇨🇳 中文 · 🇯🇵 日本語 · 🇰🇷 한국어 · 🇪🇸 Español · 🇧🇷 Português · 🇩🇪 Deutsch · 🇫🇷 Français · 🇷🇺 Русский · 🇸🇦 العربية · 🇮🇳 हिन्दी


Every AI coding tool helps you write code. AutoCode helps you ship it.

You say what you want. AutoCode builds it, deploys it, and gives you a live URL. You don't need to know programming. You just say yes or no. When it's done, anyone in the world can visit your website.


🚀 Install

Claude Code (recommended):

/install autocode

That's it. One command. View on Claude Code Marketplace

Or from GitHub:

/plugin marketplace add ilang-ai/autocode
/plugin install autocode@autocode

Restart. Start talking. Done.

Codex

Tell Codex:

Fetch and follow instructions from https://raw.githubusercontent.com/ilang-ai/autocode/refs/heads/main/.codex/INSTALL.md

OpenCode

Tell OpenCode:

Fetch and follow instructions from https://raw.githubusercontent.com/ilang-ai/autocode/refs/heads/main/.opencode/INSTALL.md

Works on Claude Code, Codex, and OpenCode. Same 47 skills, zero changes.

Hermes Agent

hermes skills install ilang-ai/autocode

Cursor

Copy skills/ into ~/.cursor/skills/, or browse Cursor Directory once listed.

Gemini CLI

gemini extensions install https://github.com/ilang-ai/autocode

Any SKILL.md-compatible agent

Copy the skills/ directory into your agent's skills path.


🔰 New to Everything? No Problem.

Never used a server before? Don't know what a terminal is? That's fine — this guide starts from zero.

Step 1: Get a Cloud Computer

You need a cloud computer (VPS) — think of it as a computer in the cloud that's always on.

👉 Go to dev.ilang.ai — new users get $300 free credit (enough for over a year).

How to sign up:

  1. Click the link → registration page
  2. Enter email, create password (10+ characters, mix of uppercase, lowercase, numbers)
  3. Check email, click verification link
  4. Payment: supports credit card, PayPal, Alipay (支付宝)
  5. $300 free credit applied automatically

Create your cloud computer:

  1. Click "Deploy +" (top right)
  2. "Deploy New Server"
  3. Type: "Cloud Compute — Shared CPU" (cheapest)
  4. Location: Closest to you (Tokyo for Asia, New York for Americas, London for Europe)
  5. Image: "Debian 12"
  6. Plan: $6/month (1 CPU, 1GB RAM — enough)
  7. Click "Deploy Now"

Wait 1-2 minutes. Green "Running" = ready.

Find your connection info:

Click server name → you'll see:

  • IP Address — like 149.28.xxx.xxx
  • Username — root
  • Password — click eye icon to show, copy button to copy

Step 2: Connect

Windows: Download PuTTY. Enter IP, click Open. Type username and password.

Mac: Open Terminal. Type: ssh root@your-ip-address. Enter password.

Phone: Download "Termius". Add host with IP, username, password.

Black screen with # = you're in.

Step 3: Install Everything

Paste this, press Enter, wait 2 minutes:

curl -fsSL https://raw.githubusercontent.com/ilang-ai/autocode/main/setup.sh | bash

Step 4: Start Claude Code

claude

Log in when prompted (Anthropic account needed).

Step 5: Install AutoCode

Say:

Install the AutoCode plugin from github.com/ilang-ai/autocode

Permission questions? Always choose the highest number ("Yes, don't ask again"). Safe — AutoCode is pure text, no executable code.

Type /exit, then claude to restart.

Step 6: Build

Build me a restaurant website with online reservations

You're a developer now.


📖 What You'll Experience

First Time

You:      "I want to sell cakes online"
AutoCode:  "What computer do you use? Mac or other?"
You:      "Other"
AutoCode:  "I'll help you get a server. $6/month. OK?"
You:      "OK"
AutoCode:  → Sets up server → Builds website → Deploys
           → "Done. Open nainai-cake.com on your phone."

Your effort: 3 yes/no answers
Result: a live website anyone can visit

Fifth Time

You:      "Build a booking site for my hair salon"
AutoCode:  → Knows your preferences → Builds → Deploys
           → "Live at salon-booking.com. SSL active."

Twentieth Time

You:      "New project"
AutoCode:  → Barely asks → Ships it → You realize you have 20 live websites

User feedback: "I don't even know who did the work — I thought I was supposed to code, but it was already done."


🧠 47 Skills

All automatic. You never activate them.

SkillWhat it does
Intent DetectionKnows what you want instantly
Smart QuestionsMax 2, never technical
Scope DetectionSmall task or big project
Communication AdaptMatches your language and level
Requirement LockStays on track
SkillWhat it does
Task BreakdownBig → small steps, 2-5 min each
PriorityCore first, polish last
Time Estimate"About 20 minutes"
Risk WarningWarns before problems happen
Best ChoiceAuto-picks fastest/cheapest/most stable tech
Decision TranslationExplains in money/speed/stability
SkillWhat it does
ScaffoldProject foundation
Feature BuildOne by one
UI BuildAll devices
SkillWhat it does
Auto CheckReviews code logic silently
SecurityBlocks attacks, encrypts data
PerformanceFast + cheap to run
Multi-DevicePhone/tablet/desktop
SkillWhat it does
ObserveInvestigates on its own
ReasonFinds root cause
Fix & VerifyFixes + confirms
ExplainTells you in your words
Fix GuideStuck? Guides you to screenshot and upload to claude.ai
SkillWhat it does
⭐ Full ReviewEvery save: reviews entire project from beginning. You watch and learn.
MilestoneCelebrates achievements
RollbackOne-click undo
SkillWhat it does
Local RunYour server, your URL
Global DeployCDN, fast everywhere
Edge DeployFree tier
File TransferServer-to-server
SkillWhat it does
Live Progress"✅ 60% (3/5)"
Efficiency Compare"Outsourcing = $5K. You = 25 min."
Celebration"🎉 Done!"
Daily SummaryToday + tomorrow
RoadmapMulti-day plan
SkillWhat it does
PreferencesRemembers your style
PatternsLearns what you build
MistakesNever repeats errors
SkillWhat it does
CompressionI-Lang v4.0 protocol, structured internal planning
MemoryRemembers across sessions

🎯 Precision

Powered by I-Lang v4.0. Structured instructions mean AI gets it right the first time. No rework.

🧠 Memory

Close today → open tomorrow → remembers everything. Gets better every session.


🌍 Different from Everything Else

Other AI coding toolsAutoCode
ForDevelopersAnyone
Ends atCode writtenWebsite live
RequiresTerminal/IDE knowledgeJust say yes or no
Tech decisionsAsks youDecides for you
DeploymentYou figure it outAutomatic
Domain + SSLYou figure it outGuided step by step
MemoryResets each sessionPersistent
ProtocolNoneI-Lang v4.0
LanguageUsually EnglishYour language

❓ Troubleshooting


ilang.ai · ilang.cn · Hugging Face · @adsorgcn

I-Lang Research · iLang Inc. · Canada · MIT · Free Forever

You say it. AutoCode ships it. Powered by I-Lang v4.0.

Ver o original no GitHub

Bom para

Relacionados