// automation · DahnM20/ai-flow

ai-flow

ai-flow is an open-source automation project by DahnM20 (DahnM20/ai-flow on GitHub). It has 291 GitHub stars and 54 forks, is released under the MIT license, and was last updated on GitHub on 26 May 2026.

Drag-and-drop builder for custom AI workflows across your favorite models.

💎 Hidden gem★ 291 stars⑂ 54 forksMITupdated 2026-05

View on GitHub ↗Official site ↗

▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.

// project facts

Project facts

Repository: DahnM20/ai-flow
GitHub stars: 291
Forks: 54
License: MIT
Last updated on GitHub: 26 May 2026
Category: Automation
Listing: Hidden gem — a shorter page for a lesser-known project
Official site: Official site

// how it works

How it works

Open the canvas
Launch AI-Flow and start with a blank workflow.
Drop in model nodes
Add text, image, or chat models from the node palette.
Connect the flow
Wire nodes together so outputs feed the next step.
Run with your keys
Add your own API keys and execute the workflow.

// features

Why people love it

Drag-and-drop canvas

Build workflows visually, no code required.

Multi-model support

Chain GPT-4o, Stable Diffusion, FLUX, and more.

Bring your own keys

Connect your own API accounts to each model.

Node-based logic

Branch, merge, and sequence AI steps freely.

Self-hostable

Run it yourself and keep data in your hands.

MIT licensed

Fully open source under the MIT license.

// run it

Run it yourself

Step 1 — Clone the repo
Download the source and move into the project folder.
```
git clone https://github.com/DahnM20/ai-flow.git
cd ai-flow
```
Step 2 — Install dependencies
Follow the README install step for the Node stack.
```
npm install
```
Step 3 — Launch it
Start the app and open the workflow canvas.
```
npm run dev
```

// use cases

What you can build

Chain chat and image models into pipelines.
Prototype AI product ideas without backend code.
Automate multi-step content generation.
Experiment with model combos on one canvas.

// faq

Questions, answered

Is AI-Flow free?

Yes — MIT licensed and free to run; you pay only for the model APIs you connect.

Which models can I use?

GPT-4o, Stable Diffusion, FLUX, and more via your own API keys.

Do I need to code?

No — the drag-and-drop canvas is built for non-coders.

Can I self-host it?

Yes, it is designed to be self-hosted.

Where do my API keys live?

The most-starred other Automation projects in the LibreAI catalogue — the realistic shortlist if ai-flow is not the right fit.

n8n★ 206.6k
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+…
Langflow★ 155.8k
Langflow — the visual builder for AI agents and workflows: drag-and-drop flows over LangChain components, deployed as APIs or MCP tools, MIT-licensed
awesome-claude-skills★ 76.4k
A curated list of awesome Claude Skills, resources, and tools for customizing Claude AI workflows
Flowise★ 55.5k
Flowise — build AI agents visually: an open-source drag-and-drop UI over LangChain and LlamaIndex, with chatflows, agentflows and a marketplace of templates
Huginn★ 50.0k
Create agents that monitor and act on your behalf. Your agents are standing by!

// more in automation

Get ai-flow

Free and open — grab the source, star the repo, and start creating.

View on GitHub ↗← More Automation tools

ai-flow

Project facts

How it works

Why people love it

Drag-and-drop canvas

Multi-model support

Bring your own keys

Node-based logic

Self-hostable

MIT licensed

Run it yourself

What you can build

Questions, answered

Similar tools

n8n

automa

Windmill

Langflow

workflowbuilder

flow-like

Alternatives in Automation

More in Automation

Get ai-flow