OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

AI Flow

AI Flow is an open-source visual tool for designing, managing and monitoring repeatable workflows that connect multiple AI model APIs. Its drag-and-drop builder organizes model actions into nodes and supports workflow import and export, execution monitoring, and parallel node processing where possible.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AI Flow — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use AI Flow when you want to visually assemble and manage a repeatable process across AI model APIs, and can provide the required provider credentials and any needed storage configuration.

Who it is for

  • People building repeatable processes across multiple AI model APIs.
  • Developers and technical teams seeking a visual workflow editor with self-hosting options.

Documented uses

  • Compose AI tasks by connecting model API nodes in a visual editor.
  • Monitor workflow execution and inspect results.
  • Organize, import, export and reuse workflows.
  • Combine text, image and other supported model API tasks in a workflow.
Before you choose

Requirements & limits

The open-source project is available under the MIT License. Its README describes an additional AI-Flow Pro cloud offering with features beyond the open-source project.

  • Users provide their own API keys for model providers.
  • S3-compatible storage with suitable CORS settings is required for full functionality; without it, file upload and some provider-dependent nodes may not work as expected.
  • The Replicate node requires REPLICATE_API_KEY in app parameters or the environment.
  • The README distinguishes cloud Pro features, including API-triggered flows and subflows with loops, from the open-source project.
  • Local installation uses a Node-based UI and Python backend installed with Poetry.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Install AI Flow locally

Set up the UI and backend using the repository's documented local installation steps.

Before you start

  • Git
  • Node.js and npm
  • Python environment supported by Poetry
  • Windows users also follow the listed Windows-specific dependency step

Steps

  1. Clone the repository and change into its directory.

  2. Install UI dependencies from packages/ui with npm install.

  3. Install backend dependencies from packages/backend with poetry install; on Windows, enter the Poetry shell and install requirements_windows.txt.

  4. Start the backend with poetry run python server.py, start the UI in a second terminal with npm start, and open http://localhost:3000.

Expected outcome

The local backend and browser UI are started according to the repository instructions.

Guide limitations

  • This guide covers setup and startup only; it does not verify a successful run.
  • Full functionality requires S3-compatible storage with appropriate CORS settings; the Replicate node requires REPLICATE_API_KEY.
  • The README does not specify required Node.js or Python versions.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
8 October 2026
Original website title
DahnM20/ai-flow · Official homepage title · retained in its source language
How we review sourcesSuggest a correction