Heym
Build AI workflow automations with a visual canvas
Details
- Target Audience
- AI DevelopersStartupsSoftware Developers
- Pricing
- Free
n8n
ZapierAbout Heym
Hey , We've been building an AI workflow automation platform for the past several months. The repo went public today and we're launching officially tomorrow — wanted to share it here first since this community is exactly who it's built for. The tool is called Heym. The core idea: a visual canvas where you connect nodes to build AI workflows — agents, document retrieval, approval steps, scheduling, observability — all running on your own infrastructure. Single docker-compose up to get started. A few things we built specifically because self-hosting matters to us: All credentials are encrypted at rest. No telemetry, no phoning home. The entire stack is three containers. Workflows that handle sensitive documents or internal data never leave your infrastructure. The license is MIT + Commons Clause — source-available, free to use, not available for commercial resale without separate terms. Happy to answer questions about the architecture, deployment, or anything else. Site: heym.run GitHub: https://github.com/heymrun/heym
Product Insights
Heym provides a self-hosted, visual canvas for building AI-native workflows through a source-available, three-container Docker stack. It bridges the gap between simple rule-based logic and complex agentic automation by integrating document retrieval and observability on user-owned infrastructure.
- Source-available code under MIT and Commons Clause licenses.
- Data privacy via self-hosting with encrypted credentials and zero telemetry.
- Comprehensive connectivity across Web, API, MCP, and Mobile platforms.
- Simplified deployment using a single docker-compose configuration.
Ideal for: AI Developers, software engineers, and startups needing to automate complex AI agent workflows while maintaining full control over sensitive internal data.
Heym serves as a self-hosted developer alternative to existing platforms like n8n and Zapier.
Product Video
Watch a video demo of Heym.
Screenshots
Product Updates (1)
Self-hosted AI Native Workflow Automation Platform <3
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
Reviews (4)
Average 4.8 out of 5
Based on 4 reviews
the builders behind heym, are experienced builders and devotion its the product itself
Comments (1)
Visual canvas for AI workflow automations is a smart approach. Makes complex agent pipelines much easier to reason about without needing to write code for every connection.
@chaudharyarun5797 Indeed it is and thank you :)