AI-Flow

Open-source visual builder for AI workflows across many model APIs.

Open Source Automation & Agents
Visit Website ↗

What is AI-Flow?

AI-Flow is an open-source, low-code platform for visually designing and running AI workflows by chaining calls to models like OpenAI, Claude, Stable Diffusion, and Replicate. It ships as a self-hostable MIT-licensed project with a drag-and-drop canvas, connectors for databases and services, and a Docker Compose setup. A hosted cloud version, AI-Flow Pro, adds subflows, API triggers, and managed integrations.

Key features

  • Visual drag-and-drop workflow designer
  • Support for OpenAI, Claude, Replicate, StabilityAI, DeepSeek
  • HTTP, database, and service connectors
  • Subflows, loops, and API-triggered flows
  • Docker-based self-hosting
  • AI-Flow Pro hosted cloud tier

Pros

  • Fully open source under MIT license
  • Works with many AI model providers
  • Self-hostable with Docker

Cons

  • Self-hosting requires Docker and API keys
  • Complex setup for non-technical users

AI-Flow at a glance

PricingOpen Source
CategoryAutomation & Agents
Platformsweb, linux, api
Official websitegithub.com
ai workflowsautomationopen sourcelow-codeorchestration

How to choose the right Automation & Agents tool

Automation and agent tools promise to do work for you, so judge them on reliability before cleverness. Map the exact workflow you want to automate, then check the tool's integrations cover every app in that chain — one missing connector breaks the whole flow. Look for clear triggers, sensible limits, and logs you can read when something goes wrong, because something eventually will. For agents that act on your behalf, approval controls matter: you should be able to review messages, purchases or changes before they happen, especially at the start. Pricing usually scales with runs or tasks, so estimate your monthly volume honestly. Start with one low-risk workflow, measure the time it truly saves, and expand from there.

Compare all Automation & Agents tools →

AI-Flow FAQs

What is AI-Flow?

AI-Flow is an open-source, low-code platform for visually designing and running AI workflows by chaining calls to models like OpenAI, Claude, Stable Diffusion, and Replicate. It ships as a self-hostable MIT-licensed project with a drag-and-drop canvas, connectors for databases and services, and a Docker Compose setup. A hosted cloud version, AI-Flow Pro, adds subflows, API triggers, and managed integrations.

What are the main features of AI-Flow?

AI-Flow offers Visual drag-and-drop workflow designer, Support for OpenAI, Claude, Replicate, StabilityAI, DeepSeek, HTTP, database, and service connectors, Subflows, loops, and API-triggered flows, Docker-based self-hosting and AI-Flow Pro hosted cloud tier.

How much does AI-Flow cost?

AI-Flow is open source, so the software itself is free to download, use and self-host. Your only costs are the infrastructure you run it on and any paid services you connect to it.

What are the pros and cons of AI-Flow?

Strengths of AI-Flow include Fully open source under MIT license; Works with many AI model providers; Self-hostable with Docker. On the downside, Self-hosting requires Docker and API keys; Complex setup for non-technical users.