Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions .env.example
Original file line number Diff line number Diff line change
@@ -0,0 +1,2 @@
# Get your free key: https://www.atlascloud.ai/console/api-keys?utm_source=github&utm_campaign=cli
ATLASCLOUD_API_KEY=your-api-key-here
74 changes: 66 additions & 8 deletions README.md
Original file line number Diff line number Diff line change
@@ -1,11 +1,44 @@
# AtlasCloud CLI
# Atlas Cloud CLI

Call AtlasCloud LLM, image, and video models from your shell.
> One command to call 300+ LLM, image, and video models from your shell. Cross-platform · MCP-ready.

![AtlasCloud CLI demo](demo.gif)
<p>
<a href="https://github.com/AtlasCloudAI/cli/releases"><img src="https://img.shields.io/github/v/release/AtlasCloudAI/cli?style=flat&colorA=18181B&colorB=28CF8D" alt="release" /></a>
<a href="https://www.npmjs.com/package/atlascloud-cli"><img src="https://img.shields.io/npm/dm/atlascloud-cli.svg?style=flat&colorA=18181B&colorB=28CF8D" alt="npm downloads" /></a>
<a href="https://github.com/AtlasCloudAI/cli/blob/main/LICENSE"><img src="https://img.shields.io/github/license/AtlasCloudAI/cli?style=flat&colorA=18181B&colorB=28CF8D" alt="license" /></a>
<a href="https://github.com/AtlasCloudAI/cli/stargazers"><img src="https://img.shields.io/github/stars/AtlasCloudAI/cli?style=flat&colorA=18181B&colorB=28CF8D" alt="stars" /></a>
<a href="https://github.com/AtlasCloudAI/cli/pulls"><img src="https://img.shields.io/badge/PRs-welcome-28CF8D.svg?style=flat&colorA=18181B" alt="PRs welcome" /></a>
</p>

![Atlas Cloud CLI demo](demo.gif)

> **[→ Get your free Atlas Cloud API key](https://www.atlascloud.ai/console/api-keys?utm_source=github&utm_campaign=cli)** — 300+ models, one key, OpenAI-compatible.

This repository hosts public installers, release artifacts, and lightweight package-manager wrappers for the `atlas` CLI. The Go source repository is maintained separately.

## Supported Models

- 🎬 **Video** — Seedance 2.0 · Kling 3 · Sora 2 · Veo 3.1 · HappyHorse 1 · Grok Imagine 1.5 · Wan 2.7
- 🎨 **Image** — Nano Banana 2/Pro · GPT Image 2 · Flux 2 · Seedream 5
- 💬 **LLM** — Claude · GPT · DeepSeek · MiniMax · Kimi · GLM · Qwen
- 🔊 **Audio** — Grok TTS

- 📚 **Explore more** — [300+ models »](https://www.atlascloud.ai/models?utm_source=github&utm_campaign=cli)

## Contents

- [Supported Models](#supported-models)
- [Install](#install)
- [Quickstart](#quickstart)
- [Commands](#commands)
- [Global Flags](#global-flags)
- [Updating](#updating)
- [Uninstall](#uninstall)
- [Troubleshooting](#troubleshooting)
- [Support](#support)
- [More Atlas Cloud Tools](#more-atlas-cloud-tools)
- [License](#license)

## Install

### macOS / Linux
Expand Down Expand Up @@ -65,20 +98,33 @@ Download the archive for your OS and architecture from [Releases](https://github

## Quickstart

Generate your first image, video, and chat completion — one line each:

```bash
atlas auth login
# Image
atlas generate image google/nano-banana-2/text-to-image -p "a cat astronaut, studio lighting"

# Video
atlas generate video bytedance/seedance-2.0-fast/text-to-video -p "a paper plane gliding over a neon city at dusk"

# Chat (LLM)
atlas chat "explain UUID v7"

# Browse the full catalog any time
atlas models list
atlas generate image google/nano-banana-2/text-to-image -p "a cat"
```

For CI and non-interactive environments:
First time only — authenticate with your [API key](https://www.atlascloud.ai/console/api-keys?utm_source=github&utm_campaign=cli):

```bash
atlas auth login --token "$ATLAS_API_KEY"
atlas chat "hi" --model deepseek-ai/DeepSeek-V3-0324
atlas auth login # interactive
atlas auth login --token "$ATLASCLOUD_API_KEY" # CI / non-interactive
```

Prefer environment variables? Copy [`.env.example`](.env.example) to `.env` and set `ATLASCLOUD_API_KEY`.

More end-to-end scripts (minimal call → real-world scenario → multi-step pipeline) live in [`examples/`](examples/).

## Commands

| Command | Purpose |
Expand Down Expand Up @@ -139,6 +185,18 @@ Installer checksum failure — do not run the downloaded archive. Retry the inst

Bugs and feature requests: [GitHub Issues](https://github.com/AtlasCloudAI/cli/issues). Please include `atlas version`, your OS/arch, install method, and the exact command that failed.

## More Atlas Cloud Tools

- 🧰 **Want to use it from the terminal?** → [atlascloud-cli](https://github.com/AtlasCloudAI/cli)
- 🤖 **Want to use it in Claude Code / Cursor?** → Install the [Atlas Cloud MCP Server](https://github.com/AtlasCloudAI/mcp-server)
- 🎬 **Want it as a Claude Code / Codex / Gemini CLI Skill?** → Install [atlas-cloud-skills](https://github.com/AtlasCloudAI/atlas-cloud-skills)
- 🎨 **ComfyUI nodes** → [atlascloud_comfyui](https://github.com/AtlasCloudAI/atlascloud_comfyui)
- 🔁 **n8n nodes** → [n8n-nodes-atlascloud](https://github.com/AtlasCloudAI/n8n-nodes-atlascloud)
- 💬 **Join our Discord** → [discord.gg/MWmMr4q9es](https://discord.gg/MWmMr4q9es)
- 🌐 **Website** → [atlascloud.ai](https://www.atlascloud.ai?utm_source=github&utm_campaign=cli)

## License

MIT

<!-- TODO(hero): add a terminal recording or screenshot showing atlas CLI generating an image or video. -->
12 changes: 12 additions & 0 deletions examples/01-minimal.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,12 @@
#!/usr/bin/env bash
# 01 — Minimal call: one chat completion + one image.
# Prerequisite: `atlas auth login` (once). See examples/README.md.
set -euo pipefail

echo "== Chat =="
atlas chat "Give me three taglines for a productivity app. One line each."

echo
echo "== Image =="
atlas generate image google/nano-banana-2/text-to-image \
-p "a minimalist productivity app icon, soft gradient, rounded square, 3D"
15 changes: 15 additions & 0 deletions examples/02-product-shot.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
#!/usr/bin/env bash
# 02 — Real-world scenario: e-commerce product launch.
# Generate a hero image for a product, then write its marketing copy with an LLM.
# Prerequisite: `atlas auth login` (once). See examples/README.md.
set -euo pipefail

PRODUCT="a matte-black stainless steel insulated water bottle"

echo "== 1/2 Hero image =="
atlas generate image bytedance/seedream-v4.5 \
-p "studio product photo of ${PRODUCT}, on a marble surface, soft window light, shallow depth of field, e-commerce hero shot, 4k"

echo
echo "== 2/2 Marketing copy =="
atlas chat "Write a 40-word product description and 5 bullet features for ${PRODUCT}. Tone: premium, minimal."
30 changes: 30 additions & 0 deletions examples/03-pipeline.sh
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
#!/usr/bin/env bash
# 03 — Pipeline: one idea -> LLM storyboard -> image AND video, chained.
# Uses the LLM to expand a single idea into detailed prompts, then feeds those
# prompts straight into image + video generation. Only documented commands.
# Prerequisite: `atlas auth login` (once). See examples/README.md.
set -euo pipefail

IDEA="${1:-a cozy independent coffee shop on a rainy evening}"
echo "Idea: ${IDEA}"
echo

echo "== 1/4 Expand idea into an image prompt (LLM) =="
IMAGE_PROMPT="$(atlas chat "Turn this idea into ONE vivid text-to-image prompt (single line, no preamble): ${IDEA}")"
echo "Image prompt: ${IMAGE_PROMPT}"

echo
echo "== 2/4 Generate the still =="
atlas generate image google/nano-banana-2/text-to-image -p "${IMAGE_PROMPT}"

echo
echo "== 3/4 Expand idea into a 5s cinematic video prompt (LLM) =="
VIDEO_PROMPT="$(atlas chat "Turn this idea into ONE 5-second cinematic text-to-video prompt with a camera move (single line, no preamble): ${IDEA}")"
echo "Video prompt: ${VIDEO_PROMPT}"

echo
echo "== 4/4 Generate the clip =="
atlas generate video bytedance/seedance-2.0-fast/text-to-video -p "${VIDEO_PROMPT}"

echo
echo "Done. Tip: add --json to any command to capture IDs/URLs for further automation."
29 changes: 29 additions & 0 deletions examples/README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,29 @@
# Atlas Cloud CLI — Examples

Three layered, copy-pasteable scripts. Each is self-contained and uses only
documented `atlas` commands (`auth`, `chat`, `models`, `generate`).

| Script | Layer | What it shows |
|---|---|---|
| [`01-minimal.sh`](01-minimal.sh) | Minimal call | The smallest possible chat + image generation. |
| [`02-product-shot.sh`](02-product-shot.sh) | Real-world scenario | E-commerce: generate a product hero image, then write its marketing copy with an LLM. |
| [`03-pipeline.sh`](03-pipeline.sh) | Pipeline | Idea → LLM storyboard → image **and** video, chained end-to-end. |

## Prerequisites

1. Install the CLI — see the [root README](../README.md#install).
2. Authenticate once:

```bash
atlas auth login # interactive
atlas auth login --token "$ATLASCLOUD_API_KEY" # CI / non-interactive
```

Get a free key at the [Atlas Cloud console](https://www.atlascloud.ai/console/api-keys?utm_source=github&utm_campaign=cli).

## Run

```bash
chmod +x examples/*.sh
./examples/01-minimal.sh
```
20 changes: 19 additions & 1 deletion npm/package.json
Original file line number Diff line number Diff line change
@@ -1,7 +1,25 @@
{
"name": "atlascloud-cli",
"version": "0.1.13",
"description": "AtlasCloud CLI — call LLM, image, and video models from your terminal.",
"description": "One command to generate AI images, videos & chat with 300+ models. GPT Image 2, Nano Banana 2/Pro, Kling 3, Seedance 2, Flux 2, Claude, GPT, DeepSeek API CLI.",
"keywords": [
"atlascloud",
"atlas-cloud",
"ai-api",
"ai-cli",
"sora-2",
"veo-3",
"kling-3",
"seedance-2",
"flux-2",
"nano-banana",
"gpt-image-2",
"mcp-server",
"ai-video-generation",
"text-to-image",
"text-to-video",
"generative-ai"
],
"bin": {
"atlas": "bin/atlas.js"
},
Expand Down