$git clone https://github.com/heymrun/heym<br/>
| 1 | <div align="center"> |
| 2 | |
| 3 | <br/> |
| 4 | |
| 5 | <img src="./docs/readme-assets/logo.svg" width="80" height="80" alt="Heym Logo"/> |
| 6 | |
| 7 | # Heym |
| 8 | |
| 9 | ### AI-Native Workflow Automation Platform |
| 10 | |
| 11 | <p align="center"> |
| 12 | <strong>Build, visualize, and run intelligent AI workflows without writing code.</strong><br/> |
| 13 | Drag-and-drop canvas · LLM & Agent nodes · RAG pipelines · Multi-agent orchestration · MCP support |
| 14 | </p> |
| 15 | |
| 16 | <p align="center"> |
| 17 | <a href="https://heym.run">heym.run</a> |
| 18 | </p> |
| 19 | |
| 20 | <p align="center"> |
| 21 | <strong>Try locally:</strong> <code>git clone https://github.com/heymrun/heym.git && cd heym && ./run.sh</code><br/> |
| 22 | <a href="#-quick-start">Quick Start</a> · |
| 23 | <a href="#deploy--call-workflows">Deploy & Call Workflows</a> · |
| 24 | <a href="#extending-heym">Extending Heym</a> · |
| 25 | <a href="SECURITY.md">Security</a> |
| 26 | </p> |
| 27 | |
| 28 | <br/> |
| 29 | |
| 30 | [](LICENSE) |
| 31 | [](COMMONS-CLAUSE.md) |
| 32 | [](https://github.com/heymrun/heym/releases) |
| 33 | [](https://python.org) |
| 34 | [](https://fastapi.tiangolo.com) |
| 35 | [](https://vuejs.org) |
| 36 | [](https://typescriptlang.org) |
| 37 | [](https://bun.sh) |
| 38 | [](https://docker.com) |
| 39 | [](SECURITY.md) |
| 40 | |
| 41 | <br/> |
| 42 | |
| 43 | <img src="./docs/readme-assets/hero.svg" width="100%" alt="Heym animated AI-native workflow automation hero"/> |
| 44 | |
| 45 | <br/> |
| 46 | |
| 47 | </div> |
| 48 | |
| 49 | --- |
| 50 | |
| 51 | ## What Is Heym? |
| 52 | |
| 53 | Heym is an **AI-native automation platform** built from the ground up around LLMs, agents, and intelligent tooling. Wire together AI agents, vector stores, web scrapers, HTTP calls, and message queues on a visual canvas — then deploy instantly via Docker. |
| 54 | |
| 55 | Unlike platforms that started as classic trigger-action automation and layered AI on later, in Heym **AI is the execution model**. |
| 56 | |
| 57 | Explore the product site at **[heym.run](https://heym.run)**. |
| 58 | |
| 59 | ## Build, Observe, Call |
| 60 | |
| 61 | | Build | Observe | Call | |
| 62 | |-------|---------|------| |
| 63 | | Create workflows from a visual canvas, natural language, voice, templates, or Agent skills. | Inspect executions with run history, LLM traces, evals, logs, OpenTelemetry export, and real USD cost tracking. | Invoke the same workflow from the canvas, REST execution endpoints, SSE streaming, MCP clients, or a public Portal chat UI. | |
| 64 | |
| 65 | <div align="center"> |
| 66 | |
| 67 | <img src="./docs/readme-assets/workflow-canvas.svg" width="100%" alt="Animated Heym workflow canvas"/> |
| 68 | |
| 69 | </div> |
| 70 | |
| 71 | ## No Enterprise Gatekeeping |
| 72 | |
| 73 | Many automation platforms turn essential production features into upgrade pressure: global variables, execution history and search, insights, AI Builder / Motherboard capabilities, observability, audit-style logs, team controls, scaling, or customer-facing portals. |
| 74 | |
| 75 | Heym takes the opposite position. These are core workflow primitives, not enterprise bait. They ship in the free self-hostable product because serious AI automation should be inspectable, shareable, observable, and deployable from day one without any kind of weird production run limits. |
| 76 | |
| 77 | Our enterprise offering is for commercial licensing, deployment help, ded |