Heym

Self-hosted AI workflow automation with agents, RAG, and MCP

1 follower

Self-hosted AI workflow automation with agents, RAG, and MCP

1 follower

Visit website

Automation tools

•

AI Engineer

•

No-Code AI Agent Builder

Build AI workflow automations visually, with no coding required. Heym supports multi-agent orchestration, RAG pipelines, and MCP, plus a powerful AI builder for faster creation. Heym is a source-available, self-hosted AI workflow automation platform. It offers a visual canvas, many node types, multi-agent orchestration, RAG capabilities, HITL approvals, an MCP server/client, full LLM traces, and a portal that turns any workflow into a public chat UI. Ready to setup with no vendor lock-in.

Free

Launch tags:Open Source•Developer Tools•Artificial Intelligence

Launch Team / Built With

Pioneer — Fine-tune any LLM in minutes, with one prompt

Fine-tune any LLM in minutes, with one prompt

Promoted

Maker

📌

Hey Product Hunt 👋 We're Burak and Ceren two engineers based in Berlin. We built Heym because we kept running into the same wall. Every time we needed agents, document retrieval, approval steps, and observability all in the same workflow, we ended up gluing together four or five different tools. Existing platforms were built for simple, rule-based logic. The moment a workflow became AI-native, we were fighting the platform instead of building. So we built what we actually wanted to use. Heym is a self-hosted AI workflow automation platform. Visual canvas, multi-agent orchestration, built-in knowledge retrieval, human review checkpoints, full execution traces, and the ability to expose any workflow as a tool your AI assistant can call — all in one place, running on your own infrastructure. Every decision reflects a constraint we hit in practice. Review checkpoints exist because some decisions need a human sign-off before they proceed. Automatic context management exists because we watched long-running agents silently fail mid-task. The evaluation system exists because we got tired of manually checking whether a prompt change broke something downstream. This is v0.0.1 — actively developed, source-available. If you're building AI workflows and spending more time on glue code than on the actual problem this is for you. Happy to answer questions about the architecture or any design decisions. 🙏 — Burak & Ceren

Report

4d ago

Forum Threads

p/heym

•

9h ago

We open sourced Heym today — self-hosted AI workflow automation

Launching on PH tomorrow. Wanted to share here first.

Heym is source-available under MIT + Commons Clause. You can run it, modify it, self-host it.

p/heym

•

2d ago

Why we built Heym — and what we're trying to figure out

We're two engineers in Berlin who kept hitting the same wall building AI workflows. Every time we needed agents, document retrieval, approval steps, and observability in the same flow, we ended up gluing five tools together.

So we built Heym, launching Tuesday. Self-hosted, source-available, visual canvas.

One thing we're genuinely still thinking about: what's the right balance between no-code accessibility and the depth that technical teams actually need? We've leaned technical and curious what this community thinks.

View all