convez.ai
SkillDevOps & InfraestruturaAvançado
floomhq

moto — IDE Terminal para Agentes IA

floomhq/moto

IDE terminal com hooks, skills, memória e runtime Docker para agentes IA

Ver no GitHub
BomPluginScore · de 0 a 100

Ambiente operacional completo para agentes Claude e Codex com hooks de segurança, 60+ skills, gerenciamento de memória, automação de navegador e integração com Gmail/WhatsApp. Extrai padrões de 500+ sessões reais para padronizar workflows de agentes em equipes.

Instalação

$npx convez-ai floomhq/moto

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
32
Forks
7
Acompanhando
0
Saúde
75%
Último commit
há 5 meses
Versão
—
Issues abertas
1
Contribuidores
4

Casos de uso

  • Executar múltiplos agentes IA com ambiente operacional padronizado
  • Bloquear comandos destrutivos e vazamentos de secrets via hooks de segurança
  • Automatizar workflows repetitivos com 60+ skills (cost tracking, QA, deploy, etc.)
  • Coordenar agentes remotos em servidores Linux com SSHFS e tmux
  • Rastrear custos por modelo e sessão em operações de IA

Veredito

moto é uma solução robusta para equipes e operadores que rodam agentes IA em produção, com foco em segurança (hooks), operacionalidade (runtime Docker, remote servers) e observabilidade (memória, cost tracking). Recomendado para quem precisa de controle e padronização além de simples prompts.

README

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

moto 🛵

A terminal IDE for AI agents, extracted from 500+ real sessions

License: MIT Claude Code

moto is Floom's terminal IDE for AI agents: Claude as the control plane, Codex for backend/infra/debugging, opencode as an optional worker, subagent workflows, Docker-first runtime, CLAUDE.md / AGENTS.md-style context, safety hooks, 60+ skills, Gmail/WhatsApp integrations, memory, browser automation, and cost tracking.

Formerly buildingopen/moto. Old GitHub URLs redirect.


Who is this for?

  • Founders/operators turning repeated work into software with agents
  • Claude Code / Codex users who want a real operating environment instead of one-off prompts
  • Terminal-first builders running multiple agents on a Mac + remote Linux box
  • Teams standardizing agent rules, hooks, skills, memory, and remote runtime
  • Anyone burned by agents running destructive commands, leaking secrets, or claiming success without fresh evidence

What makes this different?

Most AI coding setups are a prompt file plus a pile of tools. moto is the full operating environment: context, hooks, skills, memory, terminal sessions, remote server runtime, browser automation, Docker sandboxes, and launcher commands for Claude, Codex, and opencode.

The philosophy is simple:

  • context before prompting
  • wireframes before UI code
  • Docker before SaaS integrations
  • subagents before monolithic chats
  • cheap models for mechanical checks
  • expensive models for judgment
  • complexity only after real usage earns it

Quick Start

git clone https://github.com/floomhq/moto.git
cd moto
./install.sh          # Symlinks configs into ~/.claude/

That's it. The installer detects existing configs, backs them up, resolves $HOME paths in hook commands, and installs 17 hooks + 7 scripts + 60+ skills + memory template. Run ./install.sh --copy for standalone files instead of symlinks.

For the full remote workstation from the same repo:

cp .env.example .env
$EDITOR .env
./install.sh mac
./install.sh server-remote

After install:

  1. Edit ~/.claude/CLAUDE.md to match your workflow (search for <!-- Customize --> comments)
  2. Copy claude/CLAUDE-project.md into your project roots
  3. Optionally copy .env.example to .env for API keys used by some hooks/scripts

Comparison

bare Claude CodeClaude Code + dotfilesmoto
Contextmanual per sessionstatic filesCLAUDE.md + AGENTS.md + MEMORY.md
Safetynonenone17 hooks blocking destructive commands, secret leaks, config tampering
Remote workflowDIY SSHDIY SSHmoto up + SSHFS + systemd + tmux
Skillsnonenone60+ slash commands (/cost, /qa, /ship, /debug, etc.)
SidecarsnonenoneGroq / Gemini / NVIDIA routing for cheap stateless work
MemorynonenoneMEMORY.md auto-updated across sessions
Cost trackingnonenonePer-model, per-session token costs
BrowsernonenoneChrome CDP automation via skills
MessagingnonenoneWhatsApp + Gmail integrations

Architecture

moto splits agent work between a Mac control plane and a remote Linux runtime. The Mac stays where the human works, while the server owns long-running sessions, containers, cheap sidecar calls, browser automation, and messaging integrations.

flowchart LR
  subgraph Mac["Mac control plane"]
    IDE["IDE + terminal"]
    Claude["Claude Code"]
    Codex["Codex backend/debug"]
    Browser["Local browser"]
  end

  subgraph Link["Connection layer"]
    SSHFS["SSHFS"]
    Systemd["systemd"]
    Tunnels["SSH tunnels"]
  end

  subgraph Linux["Remote Linux runtime"]
    Tmux["tmux sessions"]
    Docker["Docker containers"]
    CDP["Chrome CDP"]
    Messaging["WhatsApp + Gmail"]
  end

  subgraph Surfaces["Agent surfaces"]
    Skills["60+ skills"]
    Hooks["17 safety hooks"]
    Memory["MEMORY.md"]
    Slash["slash commands"]
  end

  subgraph Sidecars["Stateless sidecars"]
    Groq["Groq"]
    Nvidia["NVIDIA"]
    Gemini["Gemini"]
  end

  IDE --> Claude
  Claude --> Codex
  Browser --> Claude
  Claude --> SSHFS
  Claude --> Systemd
  Claude --> Tunnels
  SSHFS --> Tmux
  Systemd --> Tmux
  Tunnels --> Tmux
  Tmux --> Docker
  Tmux --> CDP
  Tmux --> Messaging
  Claude --> Skills
  Hooks --> Claude
  Memory --> Claude
  Slash --> Claude
  Skills --> Tmux
  Tmux --> Groq
  Tmux --> Nvidia
  Tmux --> Gemini

Read the deep dive: docs/architecture.md


What's included

DirectoryContentsLearn more
claude/CLAUDE.md, hooks, scripts, skills, memoryclaude/skills/README.md · claude/hooks/README.md · claude/memory/README.md
mac/moto CLI, iTerm automation, shell aliases, launchd + SSH templatesmac/README.md
server/Systemd services, Docker stack, safety utils, browser automation, tmuxdocs/bootstrap.md
whatsapp/OpenClaw gateway, verified send, SQLite contact lookupwhatsapp/README.md
gmail/IMAP checker, multi-account supportgmail/
cron/Job templates, health checks, safe-pipeline patternscron/

FAQ

Do I need a remote server? No. ./install.sh works locally. Add ./install.sh mac + ./install.sh server-remote only when you want the integrated remote workflow.

Does this replace Claude Code? No. It's the operating environment around Claude Code (and Codex, and opencode). You still use Anthropic's CLI; moto just makes it reliable, safe, and reproducible.

Is this safe? 17 hooks run on every tool call blocking rm -rf /, secret leaks, wrong package managers, unverified WhatsApp sends, and more. See claude/hooks/README.md.

How much does it cost? The repo is free. Hooks track your Claude/Codex token spend to costs.jsonl. Sidecars route bounded work to free/cheap models so you burn premium tokens on judgment, not mechanical tasks.

Can I use only the hooks? Or only the skills? Yes. The installer is modular. Pick what you need.


Requirements

RequirementRequired?Used by
Claude Code CLIYesEverything
jqYesAll hooks (JSON parsing)
python3OptionalGemini audit hook, email checker
gitleaksOptionalSecret scanning hook

Configuration

After running install.sh:

  1. Edit CLAUDE.md — Search for <!-- Customize --> comments and replace placeholders with your setup
  2. Add project configs — Copy claude/CLAUDE-project.md to each project root
  3. API keys (optional) — Copy .env.example to .env for hooks/scripts that need external APIs

The settings.json file has $HOME paths pre-resolved by the installer. Re-run ./install.sh to pick up changes.


Related Projects

Other open-source tools from BuildingOpen:

ProjectDescription
bouncerIndependent Gemini quality gate that audits Claude Code's output before it can stop
claude-code-statsSpotify Wrapped for Claude Code. Visualize your AI coding stats, token usage, and costs
claude-wrappedVisualize your Claude Code stats with npx claude-entropy
hook-statsAnalyze your Claude Code bash command log
session-recallSearch and recover context after Claude's automatic compaction
browseBrowser automation CLI with autonomous agent mode via CDP
openbrowserGive AI your browser. Check email, track orders, download receipts. MCP server + CLI
openqueenAutonomous coding agent controlled by WhatsApp/Telegram. Gemini orchestrates Claude/Codex
blast-radiusFind all files affected by your changes. One bash script, zero dependencies
dep-checkFind dead imports in your project. One bash script

Changelog

See CHANGELOG.md.


License

MIT

Ver o original no GitHub

Bom para

Relacionados