npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

factory-agent-gemini

v1.0.6

Published

A Node-RED node for interacting with Google's Gemini AI API

Readme

Node-RED Gemini Agent

A Node-RED node for interacting with Google's Gemini AI models.

English | 中文


English

Overview

The Factory Agent Gemini node provides a simple way to integrate Google's Gemini AI capabilities into your Node-RED flows. This node lets you send prompts to Gemini models and receive AI-generated responses that can be used for various automation and processing tasks.

Features

  • Support for gemini-2.0-flash and gemini-2.0-flash-lite models
  • Configurable temperature and max token parameters
  • System prompt customization
  • Detailed response information including full API response
  • Flow state tracking via flow.agentstate

Installation

cd ~/.node-red
npm install factory-agent-gemini

Alternatively, you can use the Node-RED Palette Manager to install the node.

Configuration

Node Configuration

  • Name: Optional name for the node instance
  • API Key: Your Google Gemini API key (required)
  • Model: Select the Gemini model to use
  • Temperature: Controls randomness in generation (0.0-1.0)
  • Max Tokens: Maximum output tokens in the response

Input Properties

The node accepts the following message properties:

| Property | Type | Description | |-------------|---------------|--------------------------------------------------| | payload | string/object | Main content to send to Gemini | | sysPrompt | string | System prompt to guide Gemini's behavior | | envPrompt | string | Environment context (used if payload not present)| | state | string | Current state info (used if payload not present) |

Output Properties

The node outputs a message with these properties:

| Property | Type | Description | |-----------------|--------|-------------------------------------------| | payload | object | Complete API response | | result | string | Extracted text response from Gemini | | geminiRequest | object | Request object that was sent to the API | | finishReason | string | Reason why generation stopped (if provided)|

Example Flow

[
    {
        "id": "5b913f59.14274",
        "type": "inject",
        "z": "2a1c7b.4e05694",
        "name": "Ask a question",
        "props": [
            {
                "p": "payload"
            }
        ],
        "repeat": "",
        "crontab": "",
        "once": false,
        "onceDelay": 0.1,
        "topic": "",
        "payload": "Explain how Node-RED works in simple terms",
        "payloadType": "str",
        "x": 190,
        "y": 240,
        "wires": [
            [
                "7f98bab4.c8a524"
            ]
        ]
    },
    {
        "id": "7f98bab4.c8a524",
        "type": "factory-agent-gemini",
        "z": "2a1c7b.4e05694",
        "name": "Gemini Agent",
        "model": "gemini-2.0-flash",
        "temperature": "0.7",
        "maxTokens": "2048",
        "x": 390,
        "y": 240,
        "wires": [
            [
                "e92c9966.763208"
            ]
        ]
    },
    {
        "id": "e92c9966.763208",
        "type": "debug",
        "z": "2a1c7b.4e05694",
        "name": "Result",
        "active": true,
        "tosidebar": true,
        "console": false,
        "tostatus": false,
        "complete": "result",
        "targetType": "msg",
        "statusVal": "",
        "statusType": "auto",
        "x": 570,
        "y": 240,
        "wires": []
    }
]

License

MIT


中文

概述

Factory Agent Gemini节点提供了一种将Google的Gemini AI功能集成到Node-RED流程中的简单方法。该节点让您能够向Gemini模型发送提示,并接收AI生成的响应,可用于各种自动化和处理任务。

功能特点

  • 支持gemini-2.0-flashgemini-2.0-flash-lite模型
  • 可配置的温度和最大令牌参数
  • 系统提示自定义
  • 详细的响应信息,包括完整的API响应
  • 通过flow.agentstate跟踪流程状态

安装

cd ~/.node-red
npm install factory-agent-gemini

或者,您可以使用Node-RED调色板管理器安装节点。

配置

节点配置

  • 名称: 节点实例的可选名称
  • API密钥: 您的Google Gemini API密钥(必填)
  • 模型: 选择要使用的Gemini模型
  • 温度: 控制生成的随机性(0.0-1.0)
  • 最大令牌数: 响应中的最大输出令牌数

输入属性

节点接受以下消息属性:

| 属性 | 类型 | 描述 | |-------------|---------------|----------------------------------| | payload | 字符串/对象 | 发送给Gemini的主要内容 | | sysPrompt | 字符串 | 引导Gemini行为的系统提示 | | envPrompt | 字符串 | 环境上下文(在payload不存在时使用)| | state | 字符串 | 当前状态信息(在payload不存在时使用)|

输出属性

节点输出具有以下属性的消息:

| 属性 | 类型 | 描述 | |-----------------|---------|--------------------------------| | payload | 对象 | 完整的API响应 | | result | 字符串 | 从Gemini提取的文本响应 | | geminiRequest | 对象 | 发送到API的请求对象 | | finishReason | 字符串 | 生成停止的原因(如果提供) |

示例流程

[
    {
        "id": "5b913f59.14274",
        "type": "inject",
        "z": "2a1c7b.4e05694",
        "name": "提问",
        "props": [
            {
                "p": "payload"
            }
        ],
        "repeat": "",
        "crontab": "",
        "once": false,
        "onceDelay": 0.1,
        "topic": "",
        "payload": "用简单的术语解释Node-RED是如何工作的",
        "payloadType": "str",
        "x": 190,
        "y": 240,
        "wires": [
            [
                "7f98bab4.c8a524"
            ]
        ]
    },
    {
        "id": "7f98bab4.c8a524",
        "type": "factory-agent-gemini",
        "z": "2a1c7b.4e05694",
        "name": "Gemini智能体",
        "model": "gemini-2.0-flash",
        "temperature": "0.7",
        "maxTokens": "2048",
        "x": 390,
        "y": 240,
        "wires": [
            [
                "e92c9966.763208"
            ]
        ]
    },
    {
        "id": "e92c9966.763208",
        "type": "debug",
        "z": "2a1c7b.4e05694",
        "name": "结果",
        "active": true,
        "tosidebar": true,
        "console": false,
        "tostatus": false,
        "complete": "result",
        "targetType": "msg",
        "statusVal": "",
        "statusType": "auto",
        "x": 570,
        "y": 240,
        "wires": []
    }
]

使用方法

  1. 在Node-RED流程中添加Factory Agent Gemini节点
  2. 配置您的Gemini API密钥和所需参数
  3. 连接输入节点(如inject节点)来提供prompt
  4. 连接输出节点(如debug节点)来查看结果
  5. 部署您的流程并测试

许可证

MIT