Self-hosted AI workflow automation platform with visual canvas, agents, RAG, HITL, MCP, and observability in one runtime.
Quick Install
Copy the config for your editor. Some servers may need additional setup — check the README.
Add to claude_desktop_config.json:
{
"mcpServers": {
"heym": {
"command": "uvx",
"args": [
"heym"
]
}
}
}
Run in terminal:
claude mcp add heym uvx heym
Add to .cursor/mcp.json:
{
"mcpServers": {
"heym": {
"command": "uvx",
"args": [
"heym"
]
}
}
}
Or install with pip: pip install heym
README Excerpt
<div align="center"> <br/> <img src="./docs/readme-assets/logo.svg" width="80" height="80" alt="Heym Logo"/> <p align="center"> <strong>Build, visualize, and run intelligent AI workflows — without writing code.</strong><br/> Drag-and-drop canvas · LLM & Agent nodes · RAG pipelines · Multi-agent orchestration · MCP support
Tools (8)
ALLOW_REGISTERBACKEND_PORTDATABASE_URLFRONTEND_PORTPOSTGRES_HOSTPOSTGRES_PORTSECRET_KEYlocalhost
Topics
aiai-agentsai-agents-frameworkai-assistantautomationautomation-toolhuman-in-the-loopmcpmcp-servermcp-toolmcpsn8n-alternativeno-codeno-code-automationpython