HEYM

@heymrun

サーバーを訪問

6 days ago

Self-hosted AI workflow automation platform with visual canvas, agents, RAG, HITL, MCP, and observability in one runtime. Expose your Heym workflows as an MCP server at /api/mcp/sse — callable from Claude Desktop, Cursor, or any MCP client.

概要ツールコメント

概要

What is Heym?

Heym is a self-hosted, source-available AI workflow automation platform built 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.

MCP Support

Heym supports the Model Context Protocol (MCP) in two directions:

As a client: Agent nodes connect to any external MCP server and gain all its tools automatically.
As a server: Your Heym workflows are exposed as an MCP server at /api/mcp/sse — callable from Claude Desktop, Cursor, or any MCP client.

Quick Start

git clone https://github.com/heymrun/heym.git
cd heym
cp .env.example .env
./run.sh

Then open the editor at http://localhost:4017.

MCP Server Config

Add this to your MCP client configuration:

{
  "mcpServers": {
    "heym": {
      "url": "http://localhost:4017/api/mcp/sse"
    }
  }
}

Key Features

Visual drag-and-drop workflow canvas with 30+ node types
AI Assistant: describe workflows in natural language
LLM & Agent nodes with tool calling and persistent memory
Multi-agent orchestration (orchestrator + sub-agents)
Human-in-the-Loop (HITL) checkpoints
Built-in RAG with QDrant vector stores
MCP client & server support
Portal: publish workflows as public chat UIs
LLM traces, cost tracking, and evals
Self-hosted — your data, your infrastructure

サーバー設定

{
  "mcpServers": {
    "heym": {
      "url": "http://localhost:4017/api/mcp/sse"
    }
  }
}

Build with ShipAny.