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.
Family
Works in
Needs
Only
Showing 202 nodes
Triggers 18
- Chat Trigger Run the flow on each chat message from the user. No setup
- Error Trigger Run the flow when a workflow fails. No setupExtension only
- Evaluation Trigger Runs the workflow once per row of a test dataset, from Test runs only. NewNo setup
- From the right-click menu Adds an item to the right-click menu that starts it. No setupExtension only
- Keyboard shortcut Starts when you press the keys you choose. No setupExtension only
- New email Start the workflow when a new email arrives in Gmail (inbox, a label or a search). NewNeeds a connection
- New feed item Start the workflow when a blog or RSS/Atom feed has a new item. NewNo setup
- New issue or pull request Start the workflow when an issue or pull request is opened or updated on GitHub. NewNeeds a connection
- New Linear issue Start the workflow when an issue is created in Linear (optionally one team). NewNeeds a connection
- New or updated page Start the workflow when a page is added to or edited in a Notion database. NewNeeds a connection
- New row Start the workflow when rows are added at the bottom of a Google Sheet. NewNeeds a connection
- Schedule Run the flow at a specific time. No setup
- When a form is submitted Start the workflow when someone fills in and sends a form. NewNo setup
- When a page loads Starts when a page you choose finishes loading. No setupExtension only
- When a tab opens or changes Starts when you open a tab or its address changes. No setupExtension only
- When I press Run Starts the workflow when you press Run. Use it to try things out. No setup
- When something on a page changes Watches part of a page and starts when it changes. No setupExtension only
- When the browser starts Starts once each time the browser opens. No setupExtension only
In-page 27
- Act on the page Click, type and fill on the open page, step by step. No setupExtension onlyAgent tool
- 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. No setupExtension only
- Clipboard Write Write text to the system clipboard on the active tab. This step never reads the clipboard; reading clipboard content is a separate, permission-gated step. No setupExtension only
- Delete UI Elements Delete selected UI elements from the opened web page No setupExtension onlyAgent tool
- Display Markdown Display markdown content in the UI No setupExtension only
- Form Fill Fill a form on the opened web page No setupExtension onlyAgent tool
- Get Accessibility Tree Get visible interactive and semantic elements from the opened page No setupExtension only
- Get All HTML Get all the html from the page of the actual openend tab No setupExtension only
- Get All Images Get all the images from the page of the actual openend tab No setupExtension only
- Get all links Get every link on the open page. No setupExtension only
- Get All Text Get the selected text from the page of the actual openend tab No setupExtension onlyAgent tool
- Get Element Data Get details for a selected element in the opened page No setupExtension only
- Get Forms Schema Get schemas for one form or all forms from the opened tab No setupExtension only
- Get HTML of Selected Text Get the selected text from the page of the actual openend tab No setupExtension only
- Get Page Assets Get asset and downloadable link URLs from the opened page No setupExtension only
- Get Page Metadata Get metadata from the opened page No setupExtension only
- Get Selected Text Get the selected text from the page of the actual openend tab No setupExtension onlyAgent tool
- Get Structured Data Extract structured data from a table or list in the opened tab No setupExtension onlyAgent tool
- Highlight Elements Highlight selected elements in the opened page No setupExtension only
- Screenshot Page Capture a screenshot of the opened page or selected element No setupExtension onlyAgent tool
- Set Element Attribute Style Set attributes and styles on selected elements in the opened page No setupExtension only
- Show data Show the items in a card on the page. No setupExtension only
- Show Notification Show a native browser notification You can use this step when a background or browser-triggered workflow needs to notify the user.. No setupExtension only
- Submit Form Submit a selected form in the opened page No setupExtension only
- Tab Control Open, close, focus, reload, navigate, or group browser tabs. Operates on the active tab when no tab id is given. No setupExtension onlyAgent tool
- Wait For Element Wait for an element condition in the opened page No setupExtension only
- Web Search Run a web search and return the results as JSON No setupExtension only
Flow 21
- Compare Datasets Sort two collections into new, gone, unchanged and changed No setup
- Do nothing A placeholder that passes items through. No setup
- Evaluation Score a test run: set its outputs and metrics, or route around side effects. NewNo setup
- Filter Accept items matching the conditions No setup
- Form ending Show a closing message, open a page or close the form at the end. NewNo setup
- Get Variable Emit a stored value as the item No setup
- If Go one way when something is true, another when not. No setup
- In-Page Form Pause the run and ask the user to fill a form; continues with the values they enter. No setup
- Join branches Carry on as soon as either branch arrives. No setup
- Loop Run a set of steps repeatedly based on conditions No setup
- Merge Merge multiple streams into one No setup
- Poll Until Call an endpoint on an interval until a condition is met, or give up No setup
- Record Audio Pause the run and record audio from the microphone; continue with the recording. No setup
- Respond to Chat Send a message to the chat that started the run NewNo setup
- Route by value Send each item down the path that matches its value. No setup
- Set Variable Remember a value for the rest of this run No setup
- Split in Batches Loop over a list a batch at a time, running the body once per batch No setup
- Stop and Error Stop the workflow and throw an error No setup
- Try / Catch Guard the work after it, and route a failure instead of ending the run No setup
- Wait Pause the workflow for a specified amount of time No setup
- Wait For Approval Pause the run until a person approves or rejects it No setup
Data 33
- Add To A Date Add a number of days to a date No setup
- Aggregate Combine many items into a single item No setup
- Compression Compress or decompress binary data with gzip No setup
- Convert to File Turn items into a file (CSV, JSON, text, base64 or binary) No setup
- Crypto Hash, HMAC and generate random values with WebCrypto No setup
- CSV Convert between CSV text and items No setup
- Download as file Download the input data as a file No setup
- Edit Fields Modify, add or remove item fields No setup
- Edit Image Resize, crop, rotate, convert, compress or annotate an image No setup
- Extract From File Turn a file (CSV, JSON, XML, text or PDF) into items, format auto-detected No setup
- Format Date Format a date No setup
- Get Current Date Get the current date No setup
- Get part of a date The year, month, day or hour of a date. No setup
- Get Time Between Dates Get the time between two dates No setup
- HTML Extract Pull values out of HTML with CSS selectors No setup
- JSON Parse, build, pick from and repair JSON No setup
- Limit Limit the number of items to a maximum count No setup
- 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. No setup
- Markdown Convert HTML to Markdown, or Markdown to HTML No setup
- Math Calculate with numbers and format them for people No setup
- PDF Parser Extract text from a PDF document and output it as a string No setup
- Pick Field Pick a specific field from the input data No setup
- Regex Match, extract and replace with a regular expression No setup
- Remove Duplicates Remove repeated items from a collection No setup
- Rename Keys Rename and move keys on an item No setup
- Round a Date Round a date up or down to a chosen unit No setup
- Save as File Save text content as a downloadable file No setup
- Sort Sort items by one or more fields, or shuffle them randomly No setup
- Split Out Turn a list inside an item into separate items No setup
- Subtract From A Date Subtract a number of days from a date No setup
- Summarize items Totals, counts and lists per group, like a pivot table NewNo setup
- Text / Formatter Transform text: case, trim, pad, replace, split, slugify, extract, count, encode and decode No setup
- XML Convert between XML and JSON No setup
Core 12
- Data Store Remember values between workflow runs No setupAgent tool
- Digest Accumulate items across runs and release them together No setup
- Get All Text from Link Get all the text content from a given URL No setup
- Get HTML from Link Get the HTML content from a given URL No setup
- Get Images from Link Get the Images content of a page from a given URL No setup
- Get links from a page URL Open a page by its address and get its links. No setup
- HTTP Request Makes a HTTP request and returns the response data No setup
- JavaScript Code Sandboxed, no network · fast NewNo setup
- Python Code Pyodide · slower to start No setup
- RSS Feed Read Reads an RSS feed from a URL and returns the parsed data No setup
- Run details The id, start time and trigger of this run, or searchable notes on it. No setup
- Test helper Make sample data, wait, or fail on purpose while you build. No setup
AI 65
- Analyze Text On-device sentiment / toxicity / moderation of text On-device
- Answer Question Extract an answer from a passage, on-device On-device
- Auto-fixing Output Parser Wraps another output parser and retries with a model when the output fails to parse No setup
- Basic LLM Chain A simple chain to prompt a LLM and return the response No setup
- Browser Look at, read and use web pages. One block, your rules. NewNo setupExtension onlyAgent tool
- Calculator Evaluate arithmetic expressions. No setupAgent tool
- Caption Image Describe an image in words, on-device On-device
- Character Text Splitter Breaks down text into smaller parts. No setup
- Chat Anthropic Use Anthropic Claude chat models through the Anthropic API. Needs a connection
- Chat Azure OpenAI Use OpenAI models hosted on Azure OpenAI Service. Needs a connection
- Chat DeepSeek Use DeepSeek chat and reasoning models. Needs a connection
- Chat Google Use Google Gemini chat models through the Gemini API. Needs a connection
- Chat Groq Run open models on Groq for fast, low-latency inference. Needs a connection
- Chat Memory Lets an agent remember the conversation, across runs or within one run No setup
- Chat Mistral Run Mistral open and frontier models for text generation. Needs a connection
- Chat OpenAI Use OpenAI chat models (GPT) through the OpenAI API. Needs a connection
- Chat OpenRouter Route to hundreds of models across providers through OpenRouter. Needs a connection
- Chat xAI (Grok) Use xAI Grok chat models. Needs a connection
- Chrome AI Leverage Chrome AI to use LLM directly on your device On-device
- Classify Image Label an image on-device with any installed image-classification model On-device
- Classify Text Sort text into your own labels on-device — no training needed On-device
- Cohere Embeddings Leverage Cohere to create embeddings. Needs a connection
- Current Page Document Loader Load the current tab as text to feed into the Indexer No setupExtension only
- Detect Objects Find objects + bounding boxes in an image, on-device On-device
- File Document Loader Load a file (PDF, HTML, text) as text to feed into the Indexer No setup
- Generate Text Summarize, translate or transform text on-device On-device
- Google Embeddings Leverage Google (Gemini) to create embeddings. Needs a connection
- Guardrails Validate text against policies using a model, and route to pass or fail No setup
- HTTP Request Tool Lets the model send HTTP requests. You choose which calls need your approval. No setupAgent tool
- Hugging Face Embeddings Leverage Hugging Face Inference to create embeddings. Needs a connection
- Indexer Splitting text into chunks and embedding them into a vector store No setup
- Information Extractor Extract structured information from a text using a LLM No setup
- Item List Output Parser Parse a comma-separated list of items from the model output No setup
- Local Classifier Classify text on-device: zero-shot, sentiment or toxicity On-device
- Local Embeddings Turn text into vectors on this device — free and private On-device
- Local Knowledge Gives the connected agent a knowledge base to search No setup
- Local Q&A Model Answer questions on-device by quoting your Knowledge On-device
- MCP Client Tool Connects to a remote MCP server and lets the model call its tools. You choose which calls need your approval. No setupAgent tool
- Ollama Use models served by Ollama on your own computer. On-device
- Ollama Embeddings Create embeddings with models served by Ollama on your own computer. On-device
- OpenAI Embeddings Leverage OpenAI to create embeddings. Needs a connection
- Q&A Agent Answer a question from the connected knowledge base, in one step. No setup
- RAG Agent Answer from your knowledge base: finds the relevant passages and replies with sources, remembering the conversation. No setup
- Recursive Character Text Splitter Breaks down text into smaller parts. No setup
- Run agent Give a task to one of your agents and get its answer No setup
- Run Local Model Run any installed on-device model for a chosen task On-device
- Sentiment Analysis Analyze the sentiment of a text using a LLM, or on-device with a Local Classifier No setup
- Structured Output Parser Return data in a defined JSON format No setup
- Summarization Summarize a text using a LLM No setup
- Summarize Condense long text on-device On-device
- Text Classifier Classify text into one of a set of given categories using a LLM, or on-device with a Local Classifier No setup
- Think Give the agent a scratchpad to reason through a problem step by step. No setupAgent tool
- Tools Agent Generate an action plan and carry it out. Can use external tools. No setup
- Transcribe Audio Speech-to-text on-device (Whisper) — transcript + timestamped segments On-device
- Transformers Chat Run a small chat model on-device with transformers.js On-device
- Translate Translate text between 200 languages on-device On-device
- URL Document Loader Load a web page as text to feed into the Indexer No setup
- Voyage Embeddings Leverage Voyage AI to create embeddings. Needs a connection
- Web LLM Use LLM locally directly on your device On-device
- Web Search Search the web and return results. No setupExtension onlyAgent tool
- Wikipedia Query Query Wikipedia for information on a given topic. No setupAgent tool
- Workflow as Tool Expose another workflow as a callable tool. No setupAgent tool
- Local Memory Replaced by Chat Memory. Existing workflows keep running it unchanged. DeprecatedNo setup
- Persistent Chat Memory Replaced by Chat Memory (key storage, shared scope). Existing workflows keep running it unchanged. DeprecatedNo setup
- Window Buffer Memory Replaced by Chat Memory ("This run only" storage). Existing workflows keep running it. DeprecatedNo setup
Integrations 24
Chat
- Discord Integrate with Discord: post messages and rich embeds via a webhook, or read channels and messages with a bot token. Needs a connection6 operationsExtension only
- Slack Integrate with Slack to perform operations on channels, messages, users, and files. Needs a connection11 operationsExtension onlyAgent tool
- Telegram Send messages, photos and documents to a Telegram chat via the Bot API. Needs a connection3 operationsAgent tool
Notes & docs
- Google Drive Integrate with Google Drive to manage files and folders. Needs a connection10 operations
- Notion Integrate with Notion to perform operations on databases, pages, and blocks. Needs a connection11 operationsExtension onlyAgent tool
- Obsidian Append, create, read, and search notes in a local Obsidian vault via the Local REST API plugin. Needs a connection4 operationsExtension only
Tasks
- Linear Create and update Linear issues, add comments, and list teams and projects — with the current page as context. Needs a connection7 operationsExtension onlyAgent tool
- Todoist Create and manage Todoist tasks from the current page, with natural-language due dates. Needs a connection6 operationsExtension onlyAgent tool
- Trello Create, update, and move Trello cards from the current page, and attach the page URL. Needs a connection6 operationsExtension only
Sheets & databases
- AirTable Integrate with AirTable to perform operations on tables. Needs a connection7 operations
- Baserow / NocoDB Create, read, update, and delete rows in a Baserow or NocoDB table — hosted or self-hosted. Needs a connection5 operationsExtension only
- Google Sheets Integrate with Google Sheets to perform operations on spreadsheets and data. Needs a connection16 operationsAgent tool
- Supabase Select, insert, update, upsert, and delete rows in a Supabase project via PostgREST, plus RPC calls. Needs a connection6 operationsExtension only
CRM
- Attio Create or update people and companies, and log notes from the current page in Attio CRM. Needs a connection5 operationsExtension only
- HubSpot Create or update contacts and companies, log notes from the current page, and list deals in HubSpot CRM. Needs a connection7 operationsExtension only
- Pipedrive Create or update persons and organizations, and log notes from the current page in Pipedrive CRM. Needs a connection5 operationsExtension only
Read-later
- Raindrop Save the current page to a Raindrop collection with title, excerpt, tags and cover — with duplicate-skip. Needs a connection5 operationsExtension only
- Readwise / Reader Save highlights to Readwise (batch) and full articles to Reader, carrying source URL, title and author. Needs a connection2 operationsExtension only
Dev
- Custom API Call any REST API from its OpenAPI (Swagger) spec — pick an operation and its fields are generated for you. No setupExtension only
- GitHub Integrate with GitHub to work with issues, pull requests, repositories, and releases. Needs a connection16 operationsAgent tool
Other
- Gmail Integrate with Gmail to perform operations on messages and drafts. Needs a connection9 operationsAgent tool
- Google Calendar Integrate with Google Calendar to create, list and update events. Needs a connection7 operationsAgent tool
- Microsoft 365 Integrate with Microsoft 365 via Graph: send and read Outlook mail, manage OneDrive files, create calendar events and To Do tasks. Needs a connection11 operationsExtension only
- Push Notification Send a push notification to your phone via ntfy or Pushover, with priority and a click-through URL. No setupExtension only
Lambda 2
Start with a goal
Section titled “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
Section titled “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.