Back to home
Free Workflow Templates

AI Workflow Templates

Download or copy free AI workflow templates for email triage, RAG Q&A, multi-agent research, Slack alerts, scheduled reporting, and more. Import directly into Heym — the source-available AI workflow automation platform.

What are Heym workflow templates?

Each template is a complete, ready-to-run AI workflow automation — a pre-wired graph of nodes (triggers, LLM calls, HTTP requests, conditionals, integrations) packaged as a single JSON file. Click Import → Copy JSON on any card, switch to your Heym canvas, and press Cmd+V — the entire workflow pastes in under a second. Templates are model-agnostic: every LLM node defaults to gpt-4o but works with Claude, Mistral, or any local Ollama model. All templates are free to use and source-available.

AI

LLM-powered pipelines that triage emails, answer questions over documents, classify data, and generate structured outputs.

Multi-Agent

Coordinate multiple AI agents in sequence or parallel: researcher + writer, planner + executor, and validator + corrector patterns.

Integration

Connect Slack, webhooks, HTTP APIs, and Google Sheets — route data between services with conditional logic and automatic retries.

Automation

Scheduled and event-driven workflows: scrape pages, generate reports, monitor API uptime, and deliver results by email.

Data

Pull data from REST APIs, transform it with Set/Mapper nodes, and push it to Google Sheets, BigQuery, Grist, or Redis.

Batch LLM Status Tracker

AI

Send an array through the OpenAI Batch API, branch on live status updates, and collect the final per-item results.

#LLM#Batch API#Status Branch

IMAP Support Inbox Triage

Automation

Watch a shared mailbox, summarize incoming support email, and route urgent messages to Slack.

#IMAP#Email#Slack

Jina Web Fetcher

Integration

Fetch clean, LLM-ready text from any URL using the Jina Reader API.

#HTTP#Jina#Scraping

Cursor Post Notifier

Automation

Monitor the Cursor blog on a schedule and Slack-notify your team when a new post goes live.

#Cron#Crawler#Redis

Gemini Image Creator

AI

Generate images from a text prompt using Gemini's native image output.

#AI#Gemini#Image

PDF / DOCX Translation Agent

AI

Translate the full text of any uploaded document using an AI agent.

#AI#Translation#Document

Claude Blog Monitor

Automation

Monitor the Anthropic blog on a schedule and Slack-notify your team on new Claude posts.

#Cron#Crawler#Redis

Open-Meteo Weather Snapshot

Integration

Pull live weather (no API key) from Open-Meteo for any city coordinates — great for travel bots and dashboards.

#HTTP#Open Data#Weather

GitHub Release Radar

Automation

Compare the latest GitHub release tag against Redis and notify Slack when a project ships a new version.

#GitHub#HTTP#Redis

Meeting Notes → JSON Tasks

AI

Turn messy meeting notes into structured JSON tasks with the LLM node's JSON output mode — no image pipeline required.

#LLM#JSON#Productivity

Research Brief → Draft Writer

Multi-Agent

Two-stage pipeline: one LLM pulls facts and bullets, the next turns them into a polished paragraph for blogs or newsletters.

#LLM#Multi-Step#Content

web.dev Article Monitor

Automation

Cron + crawler + Redis dedupe + Slack: get notified when Google's web.dev blog publishes a new article.

#Cron#Crawler#Redis

ZenQuotes Random Quote

Integration

Fetch a random inspirational quote as JSON from the free ZenQuotes API — no API key, ideal for bots and UI demos.

#HTTP#JSON#ZenQuotes

JSONPlaceholder User Profile

Data

Load a sample user record from JSONPlaceholder — handy for prototyping Set/Mapper nodes and mock APIs.

#HTTP#JSON#Mock API

Set — Field Remap

Data

Map incoming text into named fields with the Set node before handing off to webhooks or databases.

#Set#Mapper#ETL

Urgent vs Standard Router

Automation

Branch on a keyword in the input line — fast path vs standard path using a Condition and two outputs.

#Condition#Routing#Support

Inbox TL;DR Summarizer

AI

Paste a long email or thread — one LLM call returns a short TL;DR with next actions.

#LLM#Email#Productivity

Wait — Debounce Handoff

Automation

Insert a configurable pause (Wait node) before the final output — useful for debouncing or human-in-the-loop pacing.

#Wait#Debouncing#Automation

Slack AI Triage Agent

Multi-Agent

Classify incoming Slack messages with an LLM and auto-route urgent tickets to a priority channel.

#Slack#AI#Triage

Discord Incoming Webhook

Integration

Post a message to a Discord channel with a single HTTP node — structured text input and webhook JSON body.

#Discord#Webhook#HTTP

Batch URL Fetcher

Data

Iterate over a JSON array of URLs with the Loop node, fetch each via HTTP, and merge all responses into one payload.

#Loop#HTTP#Batch

RAG Document Ingest

AI

Chunk and embed a document into a Qdrant vector store so it can be retrieved later by the RAG Search node.

#RAG#Vector Store#Knowledge Base

RAG Q&A Agent

AI

Search your Qdrant vector store for relevant context, then answer with an LLM — grounded in your own documents.

#RAG#Search#LLM

Language Switch Router

AI

Detect the language of incoming text with an LLM and route to the matching branch using the Switch node.

#Switch#Language Detection#Routing

Resilient HTTP + Error Handler

Automation

Attach an Error Handler node to an HTTP call and Slack-notify your team the moment a request fails.

#Error Handling#HTTP#Resilience

Google Sheets AI Enricher

Integration

Read new rows from Google Sheets, classify or enrich them with an LLM, and write the results back automatically.

#Google Sheets#AI#Spreadsheet

Playwright Visual AI Monitor

Automation

Take a full-page screenshot on a schedule, analyse it with an LLM for anomalies, and Slack-alert when something looks off.

#Playwright#Browser Automation#Visual AI

Telegram FAQ Auto Reply

AI

Reply to inbound Telegram questions with an LLM and keep the latest question in a global variable.

#Telegram#LLM#FAQ

Realtime WebSocket Alert Relay

Integration

Listen to an external WebSocket feed, audit critical events, and forward them to another realtime channel.

#WebSocket#Realtime#Relay

Async Sub-workflow Dispatcher

Automation

Validate an incoming brief and dispatch a reusable sub-workflow in the background without a response node.

#Execute#Async#Automation

Drive Share Link Mailer

Integration

Fetch a remote file into Drive, return the download link immediately, and email the same link asynchronously.

#Drive#Email#Files

Grist to BigQuery Sync Log

Data

Read qualified rows from Grist, stream them into BigQuery, and log the sync outcome in a Heym DataTable.

#Grist#BigQuery#DataTable

RabbitMQ Delayed Publisher

Integration

Publish a release message to RabbitMQ with an optional delivery delay for downstream consumers.

#RabbitMQ#Queue#Events

Self-stopping Status Monitor

Automation

Poll an incident endpoint until it resolves, then automatically disable the polling trigger for future runs.

#Cron#Disable Node#HTTP

Frequently Asked Questions

What are Heym workflow templates?
Pre-built automation workflows you download as JSON or copy to clipboard and paste onto the Heym canvas. Each template is a complete node graph — triggers, AI models, integrations, and outputs — ready to run in minutes.
How do I import a template?
Click "Import" → "Copy JSON" on any card, then press Cmd+V / Ctrl+V on the Heym canvas. Nodes and connections appear instantly. You can also "Download template" and drag the .json file onto the canvas.
Are the templates free?
Yes — all templates are source-available under Commons Clause + MIT. Use and modify them in your own deployments; commercial redistribution or paid hosted offerings require separate licensing.
Which AI models are supported?
Templates are model-agnostic. Nodes default to gpt-4o but work with any provider Heym supports: OpenAI, Anthropic Claude, Mistral, and local models via Ollama.
Do templates work on self-hosted Heym?
Yes. Heym is fully self-hosted via Docker Compose or Kubernetes. Import any template into your local instance and run it without data leaving your infrastructure.