convez.ai
AgenteDesenvolvimento WebAvançado
AruNi-01

ATMOS - Plataforma de Desenvolvimento para Agentes de IA

AruNi-01/atmos

IDE completa para desenvolvimento e orquestração de agentes de IA com Git e terminal

Ver no GitHub
BomPluginScore · de 0 a 100

ATMOS é um ambiente integrado para construtores de agentes de IA, oferecendo gestão de workspaces com isolamento Git, sessões tmux persistentes, editor integrado e fluxo Git completo. Combina terminal, editor de código, painel de chat global e dashboards de uso em uma única interface desktop e web, permitindo desenvolvimento colaborativo de agentes com suporte a máquinas remotas.

Instalação

$npx convez-ai AruNi-01/atmos

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
7
Forks
1
Acompanhando
0
Saúde
100%
Último commit
há 1 dia
Versão
desktop-electron-2026.11.1
Issues abertas
3
Contribuidores
9

Casos de uso

  • Desenvolvimento paralelo de múltiplos agentes com isolamento de workspaces
  • Gestão integrada de fluxo Git, PRs e code review durante desenvolvimento de agents
  • Monitoramento de uso de tokens e custos de APIs em dashboard centralizado
  • Execução remota de agentes e terminais em VPS ou máquinas via Atmos Computer

Veredito

ATMOS é uma solução madura e completa para quem desenvolve agentes de IA em escala, com features sólidas de DevOps (tmux, Git, workspaces) e observabilidade. Recomendado para equipes que precisam orquestrar múltiplos agentes em ambientes produtivos, mas exige familiaridade técnica considerável.

README

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

ATMOS

Atmosphere for Agentic Builders

简体中文 | English

Atmos screenshot

Features

  • Multi-Workspace Development — Git worktree isolation for parallel agent execution across multiple environments.
  • Persistent Tmux Sessions — Fault-tolerant terminal management with tmux; sessions survive interruptions and restarts.
  • Built-in Lightweight Editor — File preview, inline editing, and switch back to manual coding mode anytime.
  • Integrated Git Workflow — Diff view, commit assistance, code review, and GitHub PR management in one place.
  • Skill Management System — Discover, enable/disable, and delete agent skills with one-click control.
  • Global Agent Chat Panel — Start non-terminal conversations from anywhere, powered by ACP to reuse your Code Agent CLI.
  • Global Search & Command Palette — Keyboard-driven workflow for searching and executing Atmos features.
  • Usage Analytics Dashboard — Track AI coding subscription quotas, agent token consumption, and cost estimation.
  • Agent Status Notifications — Hook-based status monitoring with native notifications and self-hosted push server support.
  • Cross-Platform & Tunnel Connector — Web and desktop apps, mobile app (planned), integrated tunneling (Ngrok/Tailscale/Cloudflare Tunnel).
  • Kanban View - Quickly manage Workspace status, priority, labels and other information in Kanban view.
  • Canvas — A cross-project infinite canvas: pin terminal cards from any workspace or project onto one persistent board, and let Code Agents drive the canvas diagrams, notes, and layout without leaving your agent workflow.
  • Atmos Computer — Register your VPS or any machine to the Atmos Register Center, then connect from Desktop, Web, and run terminals, workspaces, and Canvas on that computer—your Atmos environment, wherever the machine lives.
  • Review Workflow — Review changes in Atmos's built-in diff UI, leave inline comments on specific lines, then hand off to your Code Agent to apply fixes.
  • Agent Status Tracking — Real-time agent lifecycle sync via hooks (running, idle, waiting for permission, done) across the UI, with notifications on state changes—native alerts plus self-hosted push (ntfy, Gotify, or a custom webhook).
  • Lightweight Local Models — One-click run llama-server for small Hugging Face models on your machine—ideal for light tasks such as workspace TODO extraction and Git commit message generation without configuring a cloud API.

Get Started

Download

Latest desktop release: View the latest release.

Homebrew (Desktop App)

brew install --cask AruNi-01/tap/atmos

Desktop App (macOS Install Script)

curl -fsSL https://install.atmos.land/install-desktop.sh | bash

This installer is for macOS only (Intel & Apple Silicon). It downloads and extracts the app to /Applications.

For Linux/Windows, download the installer directly from GitHub Releases: https://github.com/AruNi-01/atmos/releases

Local Web Runtime

Option 1: Install Script

curl -fsSL https://install.atmos.land/install-local-web-runtime.sh | bash

Option 2: npm/bun Package

# Using npm
npx @atmos/local-web-runtime

# Using bun
bunx @atmos/local-web-runtime

Quick Use

Desktop App

  1. Install Atmos via Homebrew or install script.
  2. Launch the desktop app and create or open a workspace.
  3. Connect your project, open a terminal, and work with agents in the same place.

Local Web Runtime

  1. Install via install script or npm/bun package.
  2. The runtime will start automatically (or run ~/.atmos/bin/atmos runtime ensure).
  3. Open your browser to the displayed URL (default: http://127.0.0.1:30303).
  4. Create a workspace and start working with agents.

Run From Source

Prerequisite: just — brew install just (macOS) / cargo install just

## Install
bun install
cargo fetch

## Run in web
just dev-api
just dev-web

# Run in desktop
just dev-web
just dev-desktop

Or without just:

# API
cargo run --bin api -- --cleanup-stale-clients true

# Web
cd apps/web && bun x next dev --turbopack --port 3030

# Desktop
bash ./scripts/desktop/prepare-sidecar.sh && cd apps/desktop && bun run tauri dev --no-watch --no-dev-server-wait --config src-tauri/tauri.debug.conf.json

License

See LICENSE.

Ver o original no GitHub

Bom para

Relacionados