LoomFlow
Lightweight AI-native workflow builder for individuals and small teams — describe your idea in natural language, get a runnable workflow on a visual canvas, pub
What is LoomFlow?
Lightweight AI-native workflow builder for individuals and small teams — describe your idea in natural language, get a runnable workflow on a visual canvas, publish it as an API. One-command Docker self-hosting. Open-source alternative to Dify / n8n.
Overview of LoomFlow
What it is
LoomFlow is a lightweight AI-native workflow builder for individuals and small teams. It allows users to describe an idea in natural language, generate a runnable workflow on a visual canvas, and publish it as an API. It is an open-source alternative to Dify / n8n and supports one-command Docker self-hosting.
Key features
- Natural Language → Workflow: Describe a process in plain language, and the AI generates an executable workflow directly onto the canvas.
- Visual Canvas: Tinyflow canvas editor with 12 node types (LLM, HTTP, Code, Template, Search, Excel, Loop, Human Confirm, etc.).
- Workflow as API: One-click publish a workflow as an HTTP endpoint with a global API Key.
- Shareable Workflow Pages: Generate a public link for recipients to view nodes, fill inputs, and run the workflow without signing in.
- Team & Permissions: Full data isolation, unlimited chat and API calls, audit logs.
- Self-Hosted & Private: App, data, and storage can all be deployed on your own server.
- Canvas AI Assistant: Chat with the canvas to ask about the current workflow or describe changes.
Use cases
- Indie developers: Ship an AI feature without building an orchestration platform.
- Content creators: Turn recurring production steps into one-click automated flows.
- Small studios: Deliver demos and client work faster with shareable, runnable flows.
- AI automation enthusiasts: Prototype ideas in minutes, then deploy them for real.
Getting started
bash git clone https://github.com/banmu123/LoomFlow.git && cd LoomFlow && bash scripts/init-env.sh && docker compose up -d Then open http://localhost:5000 with default admin admin / 123456 (change immediately).
License and pricing
The license is MIT. The project is open-source.
Based on the project's public README and repository metadata.