AlphaMoatによると、2026-09時点でNodetoolのダウンロード数は3,875、スター数は2で、AIスキル全体5,078件中2,683位、AIエージェントでは969件中530位です。

インストール数

125

ダウンロード数

3875

スター数

総合順位

#2,683

全体の上位 53% · AIエージェントの上位 55%

プラットフォーム	インストール数	ダウンロード数	スター数	コメント
ClawHub ↗	125	3739	-	-
SkillHub ↗	125	3875	2	—

プラットフォームごとに集計方法と集計時点が異なります。

このスキルでできること

CLI では、ワークフローの実行、アセットとパッケージの管理、ジョブの確認、モデルキャッシュの管理、チャット、サービスのデプロイを扱えます。インストーラースクリプトを確認し、検証済みの固定リリースを優先してください。認証トークンを、保存される可能性のあるコマンドやログに直接記載しないでください。

資料公開日 2026-10-29

できること

ローカル AI ワークフローを構築して実行する
ワークフローパッケージ、モデルキャッシュ、バックグラウンドジョブを管理する
CLI で NodeTool のサービスやデプロイを操作する

使う場面

ノードベースの AI ワークフローをローカルで構築・運用し、導入と認証情報を安全に扱える場合

プロンプト例

スキルのドキュメントをもとに生成した例であり、実際の実行結果ではありません。

NodeTool のワークフロー作成、実行、ジョブ確認に関するコマンド領域を説明して。

デプロイ前に確認するインストーラーと認証トークンの安全項目を挙げて。

月次の推移

ダウンロード数3875

スター数2

2026-09 から集計方法を変更し、同名スキルを作者ごとに分けて集計し、全スキルを対象にしました。破線は変更前の月で、変更後のデータとは直接比較せず、変更をまたぐ増減も計算していません。

月	ダウンロード数	前月比	スター数
2026-09	3875	—	2
2026-08	3663	+3.1%	2
2026-07	3552	+7.1%	1
2026-06	3315	+4.3%	-
2026-05	3179	—	1

SKILL.md 原文

作者が公開した元のファイルをテキストのまま表示しています。AlphaMoat による編集や審査はしていません。リンクはクリックできません。コマンドは内容を確認してから実行してください。取得日 2026-10-23。

9.0 KB・ClawHub v0.6.3

---
name: nodetool
description: Visual AI workflow builder - ComfyUI meets n8n for LLM agents, RAG pipelines, and multimodal data flows. Local-first, open source (AGPL-3.0).
---

# NodeTool

Visual AI workflow builder combining ComfyUI's node-based flexibility with n8n's automation power. Build LLM agents, RAG pipelines, and multimodal data flows on your local machine.

## Quick Start

すべて表示(全 468 行)


```bash
# See system info
nodetool info

# List workflows
nodetool workflows list

# Run a workflow interactively
nodetool run <workflow_id>

# Start of chat interface
nodetool chat

# Start of web server
nodetool serve
```

## Installation

### Linux / macOS

Quick one-line installation:

```bash
curl -fsSL https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.sh | bash
```

With custom directory:

```bash
curl -fsSL https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.sh | bash --prefix ~/.nodetool
```

**Non-interactive mode (automatic, no prompts):**

Both scripts support silent installation:

```bash
# Linux/macOS - use -y
curl -fsSL https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.sh | bash -y

# Windows - use -Yes
irm https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.ps1 | iex; .\install.ps1 -Yes
```

**What happens with non-interactive mode:**
- All confirmation prompts are skipped automatically
- Installation proceeds without requiring user input
- Perfect for CI/CD pipelines or automated setups

### Windows

Quick one-line installation:

```powershell
irm https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.ps1 | iex
```

With custom directory:

```powershell
.\install.ps1 -Prefix "C:\nodetool"
```

Non-interactive mode:

```powershell
.\install.ps1 -Yes
```

## Core Commands

### Workflows

Manage and execute NodeTool workflows:

```bash
# List all workflows (user + example)
nodetool workflows list

# Get details for a specific workflow
nodetool workflows get <workflow_id>

# Run workflow by ID
nodetool run <workflow_id>

# Run workflow from file
nodetool run workflow.json

# Run with JSONL output (for automation)
nodetool run <workflow_id> --jsonl
```

### Run Options

Execute workflows in different modes:

```bash
# Interactive mode (default) - pretty output
nodetool run workflow_abc123

# JSONL mode - streaming JSON for subprocess use
nodetool run workflow_abc123 --jsonl

# Stdin mode - pipe RunJobRequest JSON
echo '{"workflow_id":"abc","user_id":"1","auth_token":"token","params":{}}' | nodetool run --stdin --jsonl

# With custom user ID
nodetool run workflow_abc123 --user-id "custom_user_id"

# With auth token
nodetool run workflow_abc123 --auth-token "my_auth_token"
```

### Assets

Manage workflow assets (nodes, models, files):

```bash
# List all assets
nodetool assets list

# Get asset details
nodetool assets get <asset_id>
```

### Packages

Manage NodeTool packages (export workflows, generate docs):

```bash
# List packages
nodetool package list

# Generate documentation
nodetool package docs

# Generate node documentation
nodetool package node-docs

# Generate workflow documentation (Jekyll)
nodetool package workflow-docs

# Scan directory for nodes and create package
nodetool package scan

# Initialize new package project
nodetool package init
```

### Jobs

Manage background job executions:

```bash
# List jobs for a user
nodetool jobs list

# Get job details
nodetool jobs get <job_id>

# Get job logs
nodetool jobs logs <job_id>

# Start background job for workflow
nodetool jobs start <workflow_id>
```

### Deployment

Deploy NodeTool to cloud platforms (RunPod, GCP, Docker):

```bash
# Initialize deployment.yaml
nodetool deploy init

# List deployments
nodetool deploy list

# Add new deployment
nodetool deploy add

# Apply deployment configuration
nodetool deploy apply

# Check deployment status
nodetool deploy status <deployment_name>

# View deployment logs
nodetool deploy logs <deployment_name>

# Destroy deployment
nodetool deploy destroy <deployment_name>

# Manage collections on deployed instance
nodetool deploy collections

# Manage database on deployed instance
nodetool deploy database

# Manage workflows on deployed instance
nodetool deploy workflows

# See what changes will be made
nodetool deploy plan
```

### Model Management

Discover and manage AI models (HuggingFace, Ollama):

```bash
# List cached HuggingFace models by type
nodetool model list-hf <hf_type>

# List all HuggingFace cache entries
nodetool model list-hf-all

# List supported HF types
nodetool model hf-types

# Inspect HuggingFace cache
nodetool model hf-cache

# Scan cache for info
nodetool admin scan-cache
```

### Admin

Maintain model caches and clean up:

```bash
# Calculate total cache size
nodetool admin cache-size

# Delete HuggingFace model from cache
nodetool admin delete-hf <model_name>

# Download HuggingFace models with progress
nodetool admin download-hf <model_name>

# Download Ollama models
nodetool admin download-ollama <model_name>
```

### Chat & Server

Interactive chat and web interface:

```bash
# Start CLI chat
nodetool chat

# Start chat server (WebSocket + SSE)
nodetool chat-server

# Start FastAPI backend server
nodetool serve --host 0.0.0.0 --port 8000

# With static assets folder
nodetool serve --static-folder ./static --apps-folder ./apps

# Development mode with auto-reload
nodetool serve --reload

# Production mode
nodetool serve --production
```

### Proxy

Start reverse proxy with HTTPS:

```bash
# Start proxy server
nodetool proxy

# Check proxy status
nodetool proxy-status

# Validate proxy config
nodetool proxy-validate-config

# Run proxy daemon with ACME HTTP + HTTPS
nodetool proxy-daemon
```

### Other Commands

```bash
# View settings and secrets
nodetool settings show

# Generate custom HTML app for workflow
nodetool vibecoding

# Run workflow and export as Python DSL
nodetool dsl-export

# Export workflow as Gradio app
nodetool gradio-export

# Regenerate DSL
nodetool codegen

# Manage database migrations
nodetool migrations

# Synchronize database with remote
nodetool sync
```

## Use Cases

### Workflow Execution

Run a NodeTool workflow and get structured output:

```bash
# Run workflow interactively
nodetool run my_workflow_id

# Run and stream JSONL output
nodetool run my_workflow_id --jsonl | jq -r '.[] | "\(.status) | \(.output)"'
```

### Package Creation

Generate documentation for a custom package:

```bash
# Scan for nodes and create package
nodetool package scan

# Generate complete documentation
nodetool package docs
```

### Deployment

Deploy a NodeTool instance to the cloud:

```bash
# Initialize deployment config
nodetool deploy init

# Add RunPod deployment
nodetool deploy add

# Deploy and start
nodetool deploy apply
```

### Model Management

Check and manage cached AI models:

```bash
# List all available models
nodetool model list-hf-all

# Inspect cache
nodetool model hf-cache
```

## Installation

### Linux / macOS

Quick one-line installation:

```bash
curl -fsSL https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.sh | bash
```

With custom directory:

```bash
curl -fsSL https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.sh | bash --prefix ~/.nodetool
```

**Non-interactive mode (automatic, no prompts):**

Both scripts support silent installation:

```bash
# Linux/macOS - use -y
curl -fsSL https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.sh | bash -y

# Windows - use -Yes
irm https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.ps1 | iex; .\install.ps1 -Yes
```

**What happens with non-interactive mode:**
- All confirmation prompts are skipped automatically
- Installation proceeds without requiring user input
- Perfect for CI/CD pipelines or automated setups

### Windows

Quick one-line installation:

```powershell
irm https://raw.githubusercontent.com/nodetool-ai/nodetool/refs/heads/main/install.ps1 | iex
```

With custom directory:

```powershell
.\install.ps1 -Prefix "C:\nodetool"
```

Non-interactive mode:

```powershell
.\install.ps1 -Yes
```

## What Gets Installed

The installer sets up:
- **micromamba** — Python package manager (conda replacement)
- **NodeTool environment** — Conda env at `~/.nodetool/env`
- **Python packages** — `nodetool-core`, `nodetool-base` from NodeTool registry
- **Wrapper scripts** — `nodetool` CLI available from any terminal

### Environment Setup

After installation, these variables are automatically configured:

```bash
# Conda environment
export MAMBA_ROOT_PREFIX="$HOME/.nodetool/micromamba"
export PATH="$HOME/.nodetool/env/bin:$HOME/.nodetool/env/Library/bin:$PATH"

# Model cache directories
export HF_HOME="$HOME/.nodetool/cache/huggingface"
export OLLAMA_MODELS="$HOME/.nodetool/cache/ollama"
```

## System Info

Check NodeTool environment and installed packages:

```bash
nodetool info
```

Output shows:
- Version
- Python version
- Platform/Architecture
- Installed AI packages (OpenAI, Anthropic, Google, HF, Ollama, fal-client)
- Environment variables
- API key status