Verified project record

FlowiseAI/Flowise

Flowise provides a visual, drag-and-drop canvas for assembling and deploying AI agents and multi-agent workflows without writing code. It runs locally on Node.js or on multiple cloud hosting platforms and is intended for users who need to construct LLM-driven processes visually.

Project overview

Project type: AI Agent · RAG · Workflow
Use cases: Coding & Development · Automation
Deployment: Docker / Docker Compose
License: License pending

Best for

Developers, general users, and enterprise teams who need to build AI agents and workflows using a low-code/no-code visual interface.
Users who want to visually connect third-party services without writing code.

Key capabilities

Provides a visual canvas to drag, drop, and connect components to build AI agents and workflows without coding.
Serves API logics to support the visual flows.
Provides the web-based user interface for the application.
Offers nodes for integrating third-party services into the AI workflows.

Limitations and risks

Requires NodeJS version 20.0.0 or higher for the npm install quick start process.
Building the project from source may cause a JavaScript heap out of memory error, which requires manual heap size adjustment.

Getting started

Install globally using the command 'npm install -g flowise', then start with 'npx flowise start', and open the interface at http://localhost:3000.
Ensure NodeJS version 20.0.0 or greater is installed before running the npm install quick start.

Evidence and sources

GitHub project description: Build AI Agents, Visually
README: Build AI Agents, Visually
README: Download and Install [NodeJS](https://nodejs.org/en/download) >= 20.0.0 1. Install Flowise ```bash npm install -g flowise ``` 2. Start Flowise ```bash npx flowise start ``` 3. Ope…
README: 1. Clone the Flowise project 2. Go to `docker` folder at the root of the project 3. Copy `.env.example` file, paste it into the same location, and rename to `.env` file 4. `docker…
README: 1. Build the image locally: ```bash docker build --no-cache -t flowise . ``` 2. Run image: ```bash docker run -d --name flowise -p 3000:3000 flowise ```

Reviewed at: 2026-07-17T06:33:32Z