Documentation
Browse 90+ Heym documentation pages: getting started, every node type, dashboard tabs, and platform reference. Each card links to the canonical guide on GitHub.
Comprehensive Documentation
Every node, dashboard tab, and platform feature is documented with detailed guides, configuration references, and real-world examples. The documentation is built into the Heym application and available on GitHub.
From getting started tutorials that walk you through your first workflow to advanced reference material on agent orchestration, expression DSL syntax, parallel execution, and security architecture — Heym provides the documentation you need to build production-grade AI automations. The library covers dozens of node guides, 15 dashboard tabs, and over 30 reference topics.
Getting Started
5 GuidesBegin with the introduction to understand Heym's architecture, then follow the quick start guide to deploy your first instance and build a workflow in minutes.
Node Reference
39 Node TypesEach node type has a dedicated documentation page covering configuration options, input and output schemas, expression examples, and common use cases. Nodes span seven categories: triggers, AI, logic, data, integrations, automation, and utilities. Node types overview
Input (Webhook) Node
Entry point for workflows triggered by HTTP requests. Supports custom input fields, request metadata, and both synchronous and asynchronous execution modes.
Cron Node
Schedule-based trigger using standard five-field cron expressions. Configure hourly, daily, weekly, or custom intervals for automated recurring workflow execution.
Telegram Trigger Node
Receive Telegram bot webhook updates and start workflows instantly. Exposes the full update payload, the primary message object, callback queries, sanitized headers, and the chat ID needed for replies.
IMAP Trigger Node
Poll an IMAP inbox on a configurable minute interval and start workflows for newly arrived email. Exposes subject, sender, text and HTML bodies, decoded headers, and attachment metadata.
WebSocket Trigger Node
Open an outbound client connection to an external WebSocket server and trigger workflows on message, connected, or closed events. Exposes parsed message frames plus connection and close metadata.
RabbitMQ Node
Event-driven trigger that starts workflows when messages arrive in a RabbitMQ queue or exchange. Also supports publishing messages for asynchronous processing.
Slack Trigger Node
Receive Slack Events API webhooks and trigger workflows automatically. Auto-generates a static webhook URL, handles URL verification challenge, and verifies request signatures via a signing secret credential.
Error Handler Node
Automatic error recovery node that runs when any other node fails. Provides error message, failed node label, and timestamp for notifications or retry logic.
LLM Node
Text generation with OpenAI, Ollama, vLLM, or Cohere models. Supports text completion, vision for image analysis, image generation, structured JSON output mode, and configurable temperature.
AI Agent Node
Autonomous agent with Python tools, MCP server connections, skill attachments, sub-agent orchestration, and human-in-the-loop approval checkpoints for supervised automation.
MCP Call Node
Call a specific MCP tool directly without an LLM. Configure SSE, streamable HTTP, or stdio transport; arguments are filled from the tool input schema and support workflow expressions.
Qdrant RAG Node
Retrieval-augmented generation with Qdrant vector stores. Insert documents, search by semantic similarity with metadata filters, and optionally rerank results with Cohere.
Condition Node
If/else branching based on expression evaluation. Routes execution to truthy or falsy output handles for conditional workflow logic.
Switch Node
Multi-path routing by matching a value against defined cases. Includes a default handle for unmatched values, enabling complex decision trees.
Loop Node
Iterate over arrays executing downstream nodes per item. Provides item, index, total, isFirst, and isLast context variables for each iteration.
Merge Node
Wait for multiple parallel branches to complete and combine their outputs into a single object before continuing downstream execution.
Set Node
Transform and map input data using key-value expression pairs. Supports string manipulation, arithmetic, array operations, and object restructuring.
Variable Node
Read and write workflow-local or persistent global variables that survive across executions. Shared variables accessible via $global.variableName expressions.
DataTable Node
CRUD operations on Heym DataTables with typed columns. Read, write, update, and delete rows in structured first-party storage without external credentials.
Execute Node
Call another workflow as a sub-workflow, passing input via expressions and receiving the output. Enables modular, reusable workflow compositions.
HTTP Node
Make HTTP requests with configurable method, headers, body, and authentication. Parse JSON responses and access status codes for API integration workflows.
WebSocket Send Node
Connect to an external WebSocket, send one text, JSON, or binary message, and continue with send status, payload size, and negotiated subprotocol metadata.
Telegram Node
Send Telegram bot messages with dynamic chat IDs and expression-built message bodies. Ideal for bot replies, operator alerts, and chat-first automation flows.
Slack Node
Send messages to Slack channels via Incoming Webhooks for real-time notifications, alerts, error reporting, and team communication from workflows.
Send Email Node
Send emails through SMTP with dynamic recipients, subject lines, and body content using expressions for transactional and alert automation.
Redis Node
Key-value operations including set, get, hasKey, and deleteKey with optional TTL for caching, rate limiting, and shared state between workflows.
Grist Node
Spreadsheet automation with Grist. Read, write, and manage records, tables, and columns for data-driven workflows backed by collaborative spreadsheets.
Google Sheets Node
Read ranges, append rows, update cells, clear ranges, and inspect sheet info in Google Sheets via OAuth2. Bring your own Google Cloud app — tokens refresh automatically.
BigQuery Node
Run SQL queries against Google BigQuery datasets and insert rows via the streaming insertAll API. Authenticated via OAuth2 with automatic token refresh — bring your own Google Cloud app.
Drive Node
Manage skill-generated files from the workflow: delete files or update share constraints (password, expiry TTL, max downloads) using expressions and file IDs from agent output.
Crawler Node
Web scraping with FlareSolverr proxy support. Extract content using CSS selectors, configure wait times, and retrieve raw HTML or targeted text output.
Playwright Node
Full browser automation with configurable steps: navigate, click, type, screenshot, scroll, and AI-powered auto-heal when selectors change. Includes network capture and cookie management.
Wait Node
Pause workflow execution for a specified duration in milliseconds. Useful for API rate limiting, polling intervals, and timed delay between steps.
Output Node
Return the workflow response to the caller. Supports async downstream mode where subsequent nodes continue running in the background after the response is sent.
JSON output mapper
Build a JSON object from key-value mappings like Set. When it is the only terminal node, webhook and run responses return that object as the top-level body without label or result wrapping.
Console Log Node
Log expression values to the backend console for debugging during development. Outputs appear in Docker container logs without affecting the workflow.
Throw Error Node
Stop execution immediately with a custom HTTP status code and error message. Used for input validation, access control, and conditional error handling.
Disable Node
Permanently disable another node by label at runtime. Useful for one-time operations like stopping a Cron trigger after a condition is met.
Sticky Note Node
Add markdown documentation to the canvas for team communication, workflow instructions, and implementation notes without affecting execution flow.
Dashboard Tabs
15 TabsThe Heym dashboard organizes all platform management into 15 dedicated tabs accessible from a single navigation bar. Each tab has its own documentation page explaining features, permissions, and usage patterns.
Workflows Tab
Central hub for creating, organizing, and managing workflows. Supports card and list views, folder and sub-folder organization, drag-and-drop JSON import, and one-click export.
Templates Tab
Save and reuse entire workflows or individual node configurations as templates. Share with everyone or specific users and teams for consistent automation patterns.
Variables Tab
Manage persistent global variables that survive across workflow executions. Store counters, configuration values, and shared state accessible via $global.variableName.
Chat Tab
Direct LLM chat interface for testing models, prototyping prompts, and asking questions without building a full workflow. Supports streaming, markdown, images, and voice input.
Credentials Tab
Securely manage API keys and secrets used by nodes. Values are encrypted at rest with AES-256 Fernet, masked in the UI, and shareable with individual users or teams.
Vector Stores Tab
Create and manage Qdrant vector stores for RAG pipelines. Upload documents in PDF, Markdown, CSV, JSON, and other formats, and share stores with team members.
MCP Tab
Configure Model Context Protocol integration to connect agents to external tool servers. Expose workflow tools via MCP for Claude Desktop, Cursor, and other compatible clients.
Traces Tab
Inspect LLM execution traces with full payloads and timing, plus a stats header that shows calls, tokens, cost (USD), avg latency, error %, per-model token and cost donuts, and a calls-over-time chart driven by a shared time range filter.
Analytics Tab
Execution metrics including total runs, success rates, average duration, and trend analysis. Filter by time range or workflow, and track performance across 7, 30, or 90 day windows.
Evals Tab
Create evaluation suites with test cases for systematic AI workflow testing. Run against multiple models, compare pass/fail rates, and use LLM-as-Judge scoring.
Teams Tab
Create teams and add members by email to share workflows, credentials, variables, templates, and vector stores. All members automatically gain access to shared resources.
DataTables Tab
Create structured data tables with typed columns, inline editing, CSV import/export, and read or write sharing. Includes the LLM Cost Table system table — per-model pricing synced from Helicone (with user-level overrides and custom rows) that powers the cost charts on the Traces tab.
Drive Tab
Browse all files generated by skills across your workflows. Search, download, share, or delete files with metadata including source node, creation date, type, and size.
Scheduled Tab
See all active cron workflows on a day, week, or month calendar. Each block shows the workflow name and cron expression — hover to preview, click to jump to the canvas.
Logs Tab
View Docker container logs for the entire Heym stack including backend, frontend, and PostgreSQL. Filter by container and log level for infrastructure troubleshooting.
Reference
30+ TopicsAdvanced reference documentation covering the AI assistant, agent architecture, canvas features, guardrails, parallel execution engine, expression DSL, credential sharing, portal chat UI, skills system, keyboard shortcuts, and security hardening.
AI Assistant
Natural language workflow builder inside the canvas editor. Describe what you want and the AI generates nodes and edges automatically. Supports voice input and streaming responses.
Agent Architecture
Deep dive into agent orchestration patterns including lead/sub-agent delegation, tool calling, MCP integration, skills system, and configurable execution limits.
Canvas Features
Visual editor capabilities including drag-and-drop node placement, edge routing, zoom controls, minimap, snap-to-grid, node pinning, and output inspection panels.
Guardrails
Content safety filtering for LLM and Agent nodes. Blocks violence, hate speech, sexual content, prompt injection, and other unsafe categories with configurable error routing.
Parallel Execution
DAG-based scheduling that automatically runs independent nodes concurrently in a thread pool. Downstream nodes start as soon as dependencies complete.
Human-in-the-Loop
Approval checkpoints that pause workflow execution and generate a public review link. A human reviewer can approve or reject the pending action before it continues.
Expression DSL
Reference upstream data with $nodeLabel.field syntax. Supports string interpolation, ternary operators, array methods, object access, and built-in helper functions.
Credentials and Sharing
Encrypted credential storage with AES-256 Fernet. Share API keys with individual users or entire teams while keeping secret values masked and secure.
Portal Chat UI
Turn any workflow with an Input and Output node into a public chat interface. Embed on websites or share a link for end-user self-service powered by your workflows.
Drive & Generated Files
Skill-generated files in the Drive tab: search, download, share links with optional password and expiry. Use the Drive node in workflows to delete files or update access constraints programmatically.
Skills System
Portable capability bundles consisting of SKILL.md instructions and optional Python tools. Drag and drop onto Agent nodes to extend context and toolbox.
Keyboard Shortcuts
Power user shortcuts for node selection, deletion, duplication, undo/redo, zoom, panning, and canvas navigation to speed up workflow creation.
Edit History
Track all changes to workflows with timestamps and user attribution. Restore previous versions and compare differences between workflow revisions.
Webhooks and Triggers
Configure JSON and SSE webhook endpoints, Telegram and Slack bot webhooks, cron schedules, IMAP mailbox polling, outbound WebSocket client triggers, and RabbitMQ consumers for event-driven automation.
Execution Tokens
Scoped JWTs that grant access to a single workflow's execute endpoint. Create short-lived or long-lived tokens directly from the cURL dialog, select one to embed it in the command, and revoke at any time without affecting your session.
SSE Streaming
Stream workflow execution over stream with execution_started, node_start, node_complete, and execution_complete events. The editor can generate ready-to-run cURL commands and per-node start messages.
Settings
Per-user settings dialog opened from the gear icon with four tabs: Profile and User Rules, Security and password changes, Voice for ElevenLabs TTS and STT, and Observability for read-only OpenTelemetry status.
OpenTelemetry Tracing
Emit a root span per workflow run and a child span per node over OTLP/HTTP to any backend such as Jaeger, Tempo, Honeycomb, or Datadog, with W3C trace-context propagation, token usage attributes, and no instrumentation code. Disabled by default.
Security
Security architecture overview covering JWT authentication, HttpOnly cookies, credential encryption, role-based access control, and deployment hardening recommendations.
Workflow Organization
Organize workflows with folders, sub-folders, tags, and pinned favorites. Search workflows with the command palette and filter by status or recent activity.