NodeTool

一款结合了ComfyUI基于节点的灵活性与n8n自动化能力的可视化AI工作流构建器。在您的本地机器上构建LLM智能体、RAG管道和多模态数据流。

快速开始

# 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

安装

Linux / macOS

快速单行安装：

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

使用自定义目录：

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

非交互模式（自动，无需提示）：

两种脚本都支持静默安装：

# 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

非交互模式下的情况：

• 所有确认提示将自动跳过
• 安装过程无需用户输入
• 非常适合CI/CD管道或自动化设置

Windows

快速单行安装：

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

使用自定义目录：

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

非交互模式：

.\install.ps1 -Yes

核心命令

工作流

管理和执行NodeTool工作流：

# 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

运行选项

以不同模式执行工作流：

# 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"

资源管理

管理工作流资源（节点、模型、文件）：

# List all assets
nodetool assets list

# Get asset details
nodetool assets get <asset_id>

包管理

管理NodeTool包（导出工作流、生成文档）：

# 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

任务管理

管理后台任务执行：

# 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>

部署

将NodeTool部署到云平台（RunPod、GCP、Docker）：

# 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

模型管理

发现和管理AI模型（HuggingFace、Ollama）：

# 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

管理

维护模型缓存和清理：

# 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>

聊天与服务器

交互式聊天和Web界面：

# 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

代理

启动带HTTPS的反向代理：

# 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

其他命令

# 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

使用案例

工作流执行

运行NodeTool工作流并获取结构化输出：

# Run workflow interactively
nodetool run my_workflow_id

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

软件包创建

为自定义软件包生成文档：

# Scan for nodes and create package
nodetool package scan

# Generate complete documentation
nodetool package docs

部署

将 NodeTool 实例部署到云端：

# Initialize deployment config
nodetool deploy init

# Add RunPod deployment
nodetool deploy add

# Deploy and start
nodetool deploy apply

模型管理

检查和管理缓存的 AI 模型：

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

# Inspect cache
nodetool model hf-cache

安装

Linux / macOS

快速单行安装：

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

使用自定义目录：

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

非交互模式（自动，无提示）：

两种脚本均支持静默安装：

# 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

非交互模式下会发生什么：

• 所有确认提示将自动跳过
• 安装过程无需用户输入
• 非常适合 CI/CD 流水线或自动化设置

Windows

快速单行安装：

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

使用自定义目录：

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

非交互模式：

.\install.ps1 -Yes

安装内容

安装程序将设置：

• micromamba— Python 包管理器（conda 替代品）
• NodeTool 环境— Conda 环境位于~/.nodetool/env
• Python 包—nodetool-core、nodetool-base来自 NodeTool 注册表
• 包装脚本—nodetoolCLI 可从任何终端使用

环境设置

安装后，以下变量将自动配置：

# 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"

系统信息

检查 NodeTool 环境和已安装的包：

nodetool info

输出显示：

• 版本
• Python 版本
• 平台/架构
• 已安装的AI软件包（OpenAI、Anthropic、Google、HF、Ollama、fal-client）
• 环境变量
• API密钥状态