# Heym Heym é uma plataforma de automação de fluxos de trabalho de IA, com código-fonte disponível e hospedagem própria, para criar e executar fluxos agênticos com um editor visual. Ela ajuda equipes de automação, plataforma e IA a orquestrar agentes, RAG, aprovações e rastreamento de execução na infraestrutura que controlam. - Findings24: - Site: - Preços: Freemium - Categorias: Assistente de Código IA, Construtor de Apps IA, Automação de fluxos de trabalho com IA ## O que é Heym? Heym is an agentic AI workflow automation platform that combines a visual editor with runtime execution, traces, and review checkpoints. Users can build workflows from natural language or wire them manually from built-in nodes and integrations, then run them on their own infrastructure. It is aimed at automation, platform, and AI teams that want to coordinate agents, apply RAG, connect to external tools, and keep humans in the loop for critical steps. The platform is source-available and self-hosted, with support for Docker Compose and Kubernetes deployment. ## O que Heym pode fazer? ### Natural language workflow generation Describe a workflow in plain text or voice and the assistant generates nodes and edges on the canvas, while still allowing manual editing afterward. ### Visual workflow editor Build automations in a drag-and-drop canvas with built-in node types, version history, keyboard shortcuts, data pinning, and sub-workflow extraction. ### Multi-agent orchestration Use one orchestrator agent to delegate work to named sub-agents and sub-workflows, with support for tool calling, Python tools, and nesting. ### Built-in RAG pipeline Upload PDFs, Markdown, CSV, or JSON to managed vector stores and run semantic search against Qdrant or built-in Postgres (pgvector), with optional reranking. ### Human review and execution tracing Add approval checkpoints, inspect every run with traces and evaluations, and monitor agent calls, tool calls, latency, and outcomes. ### Self-hosted platform and deployment options Run Heym on your own infrastructure using Docker Compose, a container image, or Kubernetes, with source-available code for review and customization. ## Casos de uso ### Support triage and routing Classify incoming requests, route them to specialist agents, and add a human approval step before any action that should be reviewed. ### Knowledge-assisted automation Combine RAG with LLM or agent nodes to search internal documents and feed retrieved context into downstream workflow steps. ### Multi-step operational processes Coordinate sub-agents, tools, and sub-workflows for tasks that need branching logic, sequential execution, and shared context. ### Team dashboards and reporting Build dashboards where each chart is driven by its own workflow, making it possible to fetch, transform, and summarize operational data. ### Browser-based workflow tasks Use Playwright automation for web interactions that need page actions, with traces and review points available for inspection. ## Perguntas frequentes ### Does Heym require coding to build workflows? No. The site says workflows can be described in natural language and generated automatically, but users can also edit the canvas manually and work with built-in nodes. ### Can Heym be self-hosted? Yes. Heym is described as source-available and fully self-hosted, with deployment options including Docker Compose and Kubernetes. ### What kinds of AI workflow features does Heym include? The platform includes multi-agent orchestration, RAG, MCP client and server support, human approval checkpoints, traces, evaluations, dashboards, and agent memory. ### Does Heym support external integrations? Yes. The site mentions integrations with tools and services such as Slack, Gmail, GitHub, Jira, Notion, PostgreSQL, Redis, RabbitMQ, Google Sheets, Google Drive, BigQuery, S3, and HTTP APIs, among others. ### Is pricing publicly listed? Not in the provided sources. The pricing URL returned a page not found response, so pricing and tiers could not be verified. ## Informações rápidas - **Category**: AI workflow automation - **Deployment**: Self-hosted - **Source model**: Source-available - **Primary users**: Automation, platform, and AI teams - **Website**: heym.run - **Deployment options**: Docker Compose, container image, Kubernetes