Node catalog

A workflow is a chain of nodes: a trigger starts it, and each node does one step. Type what you want to do, such as “click”, “pdf” or “summarise”, or narrow the list by family, by where the node runs and by what it needs before it works. Each card opens the node’s page: its settings, what it sends to the next node, and fixes for common problems.

按名称或任务筛选节点

类别

全部 189 触发器 10页面内 27流程 18数据 32核心 11AI 65集成 24Lambda 2

适用环境

网页应用仅限扩展程序

需要

无需设置需要连接设备端 AI

仅看

智能体工具 新增

显示 189 个节点

触发器 10

• BS Browser Startup Run the flow when the browser starts. 无需设置仅限扩展程序
• CT Chat Trigger Run the flow on each chat message from the user. 无需设置
• CM Context Menu Run the flow from the browser context menu. 无需设置仅限扩展程序
• EC Element Change Run the flow when any of one or more CSS selectors on a matching page changes. 无需设置仅限扩展程序
• ET Error Trigger Run the flow when a workflow fails. 无需设置仅限扩展程序
• H Hotkey Run the flow from a keyboard shortcut. 无需设置仅限扩展程序
• N Navigation Run the flow when a browser tab is created, updated, or removed. 无需设置仅限扩展程序
• PL Page Load Run the flow when a matching browser tab finishes loading. 无需设置仅限扩展程序
• S Schedule Run the flow at a specific time. 无需设置
• WS When Started Run the flow on clicking the start button. Good for getting started quickly. 无需设置

页面内 27

• BN Browser Notification Show a system notification through the OS notification center, visible even when no tab is focused. Unlike Show Notification, which needs an open tab, this reaches the user regardless of what they are looking at, and can offer up to two action buttons. 无需设置仅限扩展程序
• CW Clipboard Write Write text to the system clipboard on the active tab. This node never reads the clipboard; reading clipboard content is a separate, permission-gated node. 无需设置仅限扩展程序
• DU Delete UI Elements Delete selected UI elements from the opened web page 无需设置仅限扩展程序
• DM Display Markdown Display markdown content in the UI 无需设置仅限扩展程序
• DO Display Object Display an object in the UI 无需设置仅限扩展程序
• FF Form Fill Fill a form on the opened web page 无需设置仅限扩展程序
• GA Get Accessibility Tree Get visible interactive and semantic elements from the opened page 无需设置仅限扩展程序
• GA Get All HTML Get all the html from the page of the actual openend tab 无需设置仅限扩展程序
• GA Get All Images Get all the images from the page of the actual openend tab 无需设置仅限扩展程序
• GA Get All Link Get all the links from the page of the actual openend tab 无需设置仅限扩展程序
• GA Get All Text Get the selected text from the page of the actual openend tab 无需设置仅限扩展程序
• GE Get Element Data Get details for a selected element in the opened page 无需设置仅限扩展程序
• GF Get Forms Schema Get schemas for one form or all forms from the opened tab 无需设置仅限扩展程序
• GH Get HTML of Selected Text Get the selected text from the page of the actual openend tab 无需设置仅限扩展程序
• GP Get Page Assets Get asset and downloadable link URLs from the opened page 无需设置仅限扩展程序
• GP Get Page Metadata Get metadata from the opened page 无需设置仅限扩展程序
• GS Get Selected Text Get the selected text from the page of the actual openend tab 无需设置仅限扩展程序
• GS Get Structured Data Extract structured data from a table or list in the opened tab 无需设置仅限扩展程序
• HE Highlight Elements Highlight selected elements in the opened page 无需设置仅限扩展程序
• SP Screenshot Page Capture a screenshot of the opened page or selected element 无需设置仅限扩展程序
• SE Set Element Attribute Style Set attributes and styles on selected elements in the opened page 无需设置仅限扩展程序
• SN Show Notification Show a native browser notification You can use this node when a background or browser-triggered workflow needs to notify the user.. 无需设置仅限扩展程序
• SF Submit Form Submit a selected form in the opened page 无需设置仅限扩展程序
• TC Tab Control Open, close, focus, reload, navigate, or group browser tabs. Operates on the active tab when no tab id is given. 无需设置仅限扩展程序
• UA UI Automation Automate UI interactions 无需设置仅限扩展程序
• WF Wait For Element Wait for an element condition in the opened page 无需设置仅限扩展程序
• WS Web Search Run a web search and return the results as JSON 无需设置仅限扩展程序

流程 18

• CD Compare Datasets Sort two collections into new, gone, unchanged and changed 无需设置
• F Filter Accept items matching the conditions 无需设置
• F Funnel Continues whenever any one of its incoming branches completes. Use it to converge multiple triggers (or parallel branches) into a single shared downstream chain. 无需设置
• GV Get Variable Emit a stored value as the item 无需设置
• I IF Route items to different branches based on conditions 无需设置
• IP In-Page Form Pause the run and ask the user to fill a form; continues with the values they enter. 无需设置
• L Loop Execute a set of actions repeatedly based on conditions 无需设置
• M Merge Merge multiple streams into one 无需设置
• NO No Operation Pass data through unchanged 无需设置
• PU Poll Until Call an endpoint on an interval until a condition is met, or give up 无需设置
• RA Record Audio Pause the run and record audio from the microphone; continue with the recording. 无需设置
• SV Set Variable Remember a value for the rest of this run 无需设置
• SI Split in Batches Loop over a list a batch at a time, running the body once per batch 无需设置
• SA Stop and Error Stop the workflow and throw an error 无需设置
• S Switch Route items to any number of named branches 无需设置
• TC Try / Catch Guard the work after it, and route a failure instead of ending the run 无需设置
• W Wait Pause the workflow for a specified amount of time 无需设置
• WF Wait For Approval Pause the run until a person approves or rejects it 无需设置

数据 32

• AT Add To A Date Add a number of days to a date 无需设置
• A Aggregate Combine many items into a single item 无需设置
• C Compression Compress or decompress binary data with gzip 无需设置
• CT Convert to File Turn items into a file (CSV, JSON, text, base64 or binary) 无需设置
• C Crypto Hash, HMAC and generate random values with WebCrypto 无需设置
• C CSV Convert between CSV text and items 无需设置
• DA Download as file Download the input data as a file 无需设置
• EF Edit Fields Modify, add or remove item fields 无需设置
• EI Edit Image Resize, crop, rotate, convert, compress or annotate an image 无需设置
• EF Extract From File Turn a file (CSV, JSON, XML, text or PDF) into items, format auto-detected 无需设置
• EP Extract Part Of A Date Extract a part of a date 无需设置
• FD Format Date Format a date 无需设置
• GC Get Current Date Get the current date 无需设置
• GT Get Time Between Dates Get the time between two dates 无需设置
• HE HTML Extract Pull values out of HTML with CSS selectors 无需设置
• J JSON Parse, build, pick from and repair JSON 无需设置
• L Limit Limit the number of items to a maximum count 无需设置
• LF Local File Read Opens a file picker at runtime and reads the chosen file(s). The file is selected by the user through the operating system picker, so the workflow can never name a file itself. 无需设置
• M Markdown Convert HTML to Markdown, or Markdown to HTML 无需设置
• M Math Calculate with numbers and format them for people 无需设置
• PP PDF Parser Extract text from a PDF document and output it as a string 无需设置
• PF Pick Field Pick a specific field from the input data 无需设置
• R Regex Match, extract and replace with a regular expression 无需设置
• RD Remove Duplicates Remove repeated items from a collection 无需设置
• RK Rename Keys Rename and move keys on an item 无需设置
• RA Round a Date Round a date up or down to a chosen unit 无需设置
• SA Save as File Save text content as a downloadable file 无需设置
• S Sort Sort items by one or more fields, or shuffle them randomly 无需设置
• SO Split Out Turn a list inside an item into separate items 无需设置
• SF Subtract From A Date Subtract a number of days from a date 无需设置
• TF Text / Formatter Transform text: case, trim, pad, replace, split, slugify, extract, count, encode and decode 无需设置
• X XML Convert between XML and JSON 无需设置

核心 11

• C Code Run custom python code 无需设置
• DS Data Store Remember values between workflow runs 无需设置
• D Debug Generate sample data, delay, or throw on demand 无需设置
• D Digest Accumulate items across runs and release them together 无需设置
• ED Execution Data Read this run’s id, trigger and timing, or attach searchable metadata to it 无需设置
• GA Get All Text from Link Get all the text content from a given URL 无需设置
• GH Get HTML from Link Get the HTML content from a given URL 无需设置
• GI Get Images from Link Get the Images content of a page from a given URL 无需设置
• GL Get Links from Link Get the Links content of a page from a given URL 无需设置
• HR Http Request Makes a HTTP request and returns the response data 无需设置
• RF RSS Feed Read Reads an RSS feed from a URL and returns the parsed data 无需设置

AI 65

• AT Analyze Text On-device sentiment / toxicity / moderation of text 设备端
• AQ Answer Question Extract an answer from a passage, on-device 设备端
• AF Auto-fixing Output Parser Wraps another output parser and retries with a model when the output fails to parse 无需设置
• BL Basic LLM Chain A simple chain to prompt a LLM and return the response 无需设置
• BT Browser Tool Lets the model click/fill/type/select/submit on the active page or navigate it. Each call requires user approval. 无需设置仅限扩展程序智能体工具
• C Calculator Evaluate arithmetic expressions. 无需设置智能体工具
• CI Caption Image Describe an image in words, on-device 设备端
• CT Character Text Splitter Breaks down text into smaller parts. 无需设置
• CA Chat Anthropic Use Anthropic Claude chat models through the Anthropic API. 需要连接
• CA Chat Azure OpenAI Use OpenAI models hosted on Azure OpenAI Service. 需要连接
• CD Chat DeepSeek Use DeepSeek chat and reasoning models. 需要连接
• CG Chat Google Use Google Gemini chat models through the Gemini API. 需要连接
• CG Chat Groq Run open models on Groq for fast, low-latency inference. 需要连接
• CM Chat Memory Lets an agent remember the conversation, across runs or within one run 新无需设置
• CM Chat Mistral Run Mistral open and frontier models for text generation. 需要连接
• CO Chat OpenAI Use OpenAI chat models (GPT) through the OpenAI API. 需要连接
• CO Chat OpenRouter Route to hundreds of models across providers through OpenRouter. 需要连接
• CX Chat xAI (Grok) Use xAI Grok chat models. 需要连接
• CA Chrome AI Leverage Chrome AI to use LLM directly on your device 设备端
• CI Classify Image Label an image on-device with any installed image-classification model 设备端
• CT Classify Text Sort text into your own labels on-device — no training needed 设备端
• CE Cohere Embeddings Leverage Cohere to create embeddings. 需要连接
• CP Current Page Document Loader Load the current tab as text to feed into the Indexer 无需设置仅限扩展程序
• DO Detect Objects Find objects + bounding boxes in an image, on-device 设备端
• FD File Document Loader Load a file (PDF, HTML, text) as text to feed into the Indexer 无需设置
• GT Generate Text Summarize, translate or transform text on-device 设备端
• GE Google Embeddings Leverage Google (Gemini) to create embeddings. 需要连接
• G Guardrails Validate text against policies using a model, and route to pass or fail 无需设置
• HR HTTP Request Tool Lets the model send HTTP requests. Each call requires user approval. 无需设置智能体工具
• HF Hugging Face Embeddings Leverage Hugging Face Inference to create embeddings. 需要连接
• I Indexer Splitting text into chunks and embedding them into a vector store 无需设置
• IE Information Extractor Extract structured information from a text using a LLM 无需设置
• IL Item List Output Parser Parse a comma-separated list of items from the model output 无需设置
• LC Local Classifier Classify text on-device: zero-shot, sentiment or toxicity 设备端
• LE Local Embeddings Turn text into vectors on this device — free and private 设备端
• LK Local Knowledge Gives the connected agent a knowledge base to search 无需设置
• LQ Local Q&A Model Answer questions on-device by quoting your Knowledge 设备端
• MC MCP Client Tool Connects to a remote MCP server and lets the model call its tools. Each call requires user approval. 无需设置智能体工具
• O Ollama Use models served by Ollama on your own computer. 设备端
• OE Ollama Embeddings Create embeddings with models served by Ollama on your own computer. 设备端
• OE OpenAI Embeddings Leverage OpenAI to create embeddings. 需要连接
• QA Q&A Agent Answer a question from the connected knowledge base, in one step. 无需设置
• RA RAG Agent Answer from your knowledge base: finds the relevant passages and replies with sources, remembering the conversation. 无需设置
• RC Recursive Character Text Splitter Breaks down text into smaller parts. 无需设置
• RA Run agent Give a task to one of your agents and get its answer 无需设置
• RL Run Local Model Run any installed on-device model for a chosen task 设备端
• SA Sentiment Analysis Analyze the sentiment of a text using a LLM, or on-device with a Local Classifier 无需设置
• SO Structured Output Parser Return data in a defined JSON format 无需设置
• S Summarization Summarize a text using a LLM 无需设置
• S Summarize Condense long text on-device 设备端
• TC Text Classifier Classify text into one of a set of given categories using a LLM, or on-device with a Local Classifier 无需设置
• T Think Give the agent a scratchpad to reason through a problem step by step. 无需设置智能体工具
• TA Tools Agent Generate an action plan and execute it. Can use external tools. 无需设置
• TA Transcribe Audio Speech-to-text on-device (Whisper) — transcript + timestamped segments 设备端
• TC Transformers Chat Run a small chat model on-device with transformers.js 设备端
• T Translate Translate text between 200 languages on-device 设备端
• UD URL Document Loader Load a web page as text to feed into the Indexer 无需设置
• VE Voyage Embeddings Leverage Voyage AI to create embeddings. 需要连接
• WL Web LLM Use LLM locally directly on your device 设备端
• WS Web Search Search the web and return results. 无需设置仅限扩展程序智能体工具
• WQ Wikipedia Query Query Wikipedia for information on a given topic. 无需设置智能体工具
• WA Workflow as Tool Expose another workflow as a callable tool. 无需设置智能体工具
• LM Local Memory Replaced by Chat Memory. Existing workflows keep running it unchanged. 已弃用无需设置
• PC Persistent Chat Memory Replaced by Chat Memory (key storage, shared scope). Existing workflows keep running it unchanged. 已弃用无需设置
• WB Window Buffer Memory Replaced by Chat Memory ("This run only" storage). Existing workflows keep running it. 已弃用无需设置

集成 24

Chat

• D Discord Integrate with Discord: post messages and rich embeds via a webhook, or read channels and messages with a bot token. 需要连接6 项操作仅限扩展程序
• S Slack Integrate with Slack to perform operations on channels, messages, users, and files. 需要连接11 项操作仅限扩展程序
• T Telegram Send messages, photos and documents to a Telegram chat via the Bot API. 需要连接3 项操作

Notes & docs

• GD Google Drive Integrate with Google Drive to manage files and folders. 需要连接10 项操作
• N Notion Integrate with Notion to perform operations on databases, pages, and blocks. 需要连接11 项操作仅限扩展程序
• O Obsidian Append, create, read, and search notes in a local Obsidian vault via the Local REST API plugin. 需要连接4 项操作仅限扩展程序

Tasks

• L Linear Create and update Linear issues, add comments, and list teams and projects — with the current page as context. 需要连接7 项操作仅限扩展程序
• T Todoist Create and manage Todoist tasks from the current page, with natural-language due dates. 需要连接6 项操作仅限扩展程序
• T Trello Create, update, and move Trello cards from the current page, and attach the page URL. 需要连接6 项操作仅限扩展程序

Sheets & databases

• A AirTable Integrate with AirTable to perform operations on tables. 需要连接7 项操作
• BN Baserow / NocoDB Create, read, update, and delete rows in a Baserow or NocoDB table — hosted or self-hosted. 需要连接5 项操作仅限扩展程序
• GS Google Sheets Integrate with Google Sheets to perform operations on spreadsheets and data. 需要连接16 项操作
• S Supabase Select, insert, update, upsert, and delete rows in a Supabase project via PostgREST, plus RPC calls. 需要连接6 项操作仅限扩展程序

CRM

• A Attio Create or update people and companies, and log notes from the current page in Attio CRM. 需要连接5 项操作仅限扩展程序
• H HubSpot Create or update contacts and companies, log notes from the current page, and list deals in HubSpot CRM. 需要连接7 项操作仅限扩展程序
• P Pipedrive Create or update persons and organizations, and log notes from the current page in Pipedrive CRM. 需要连接5 项操作仅限扩展程序

Read-later

• R Raindrop Save the current page to a Raindrop collection with title, excerpt, tags and cover — with duplicate-skip. 需要连接5 项操作仅限扩展程序
• RR Readwise / Reader Save highlights to Readwise (batch) and full articles to Reader, carrying source URL, title and author. 需要连接2 项操作仅限扩展程序

Dev

• CA Custom API Call any REST API from its OpenAPI (Swagger) spec — pick an operation and its fields are generated for you. 无需设置仅限扩展程序
• G GitHub Integrate with GitHub to work with issues, pull requests, repositories, and releases. 需要连接16 项操作

Other

• G Gmail Integrate with Gmail to perform operations on messages and drafts. 需要连接9 项操作
• GC Google Calendar Integrate with Google Calendar to create, list and update events. 需要连接7 项操作
• M3 Microsoft 365 Integrate with Microsoft 365 via Graph: send and read Outlook mail, manage OneDrive files, create calendar events and To Do tasks. 需要连接11 项操作仅限扩展程序
• PN Push Notification Send a push notification to your phone via ntfy or Pushover, with priority and a click-through URL. 无需设置仅限扩展程序

Lambda 2

• LI Lambda Input Define the inputs for the lambda workflow. 无需设置
• LO Lambda Output Define the outputs for the lambda workflow. 无需设置

缺少某个应用？

使用 HTTP Request 或 Custom API 和你自己的密钥调用任意 API，或者在需求看板中提出需求。

Start with a goal

Goal	Start with
Start by hand	When Started
Start on a schedule	Schedule
Start from the browser	Context Menu, Hotkey or Page Load
Start on each chat message	Chat Trigger
Read the page you’re on	Get Selected Text, Get All Text or Get Structured Data
Read a web address	Get HTML from Link or Get All Text from Link
Call an API	HTTP Request
Reshape data	Edit Fields or Pick Field
Branch, filter, merge, loop or wait	IF, Filter, Merge, Loop, Wait
Process many items without hitting rate limits	Split in Batches (see Rate limits)
Pause for a person’s approval	Wait For Approval
Ask an AI model	Basic LLM Chain with a chat model such as Chat OpenAI, or on-device with Summarize
Let an AI agent pick tools	Tools Agent
Send results to an app	Slack, Notion, Google Sheets and the other integrations above

How to read a node page

Every node page follows the same order, so you know where to look:

• Needs a connection: when the node signs in to a service, a box at the top links to the connection setup.
• Try it: a real workflow that uses the node, which you can open in AWFlow.
• What it does and When to use it.
• Inputs and settings: every field as the settings panel shows it. For apps with many operations, pick one to see only its settings.
• Outputs: the output ports and the fields the next node receives, with the shape of one item.
• Dependencies and credentials: the connection the node uses and the slots where other nodes plug in, such as a chat model for an agent.
• Example workflow, Common issues (named by what you see), Recipes with this node and Related nodes.

Nodes that act on web pages or the browser itself run only in the AWFlow browser extension. Their pages say so at the top.