RemarkableCloud

Apps / Flowise

Managed Flowise hosting.
One server, no app limits.

Drag-and-drop builder for LLM apps and agents. Prototype chatbots and pipelines visually, then serve them as APIs from your own server.

What it is

Flowise is the visual builder for LLM applications: drag nodes for models, memory, retrieval, and tools onto a canvas, wire them together, and serve the result as a chatbot or API endpoint from your own server.

Minimum RAM

2 GB

Fits on SC-2GB; SC-4GB is the comfortable pick with room to stack.

What we install

Our playbook deploys Flowise with persistent flow storage, HTTPS issued and forced, and authentication enabled from the first boot. Your flows and credentials live on your server, backed up offsite twice.

What managed covers

Server updates, snapshots, dual offsite backups, monitoring, firewall, and humans on call. The flows are yours; the platform stays patched underneath them.

The app is $0. The managed server is the only bill, and everything above is part of it.

What do people build with Flowise?

Customer-facing chatbots grounded in company documents, internal Q&A tools, extraction pipelines that turn messy text into structured rows, and agent flows that call external APIs. Every flow can be embedded in a site or called as an HTTP endpoint.

Do I need to know how to code?

Not to build: flows are assembled visually from prebuilt nodes. A little JavaScript unlocks custom functions when you outgrow the standard blocks, and the underlying LangChain concepts map one-to-one if you later graduate to code.

How much RAM does Flowise need?

2 GB runs the builder and modest production flows. Heavy retrieval workloads want a real database beside it (PostgreSQL pairs well), and the cart meter sizes the server for the full stack.

Which models can Flowise use?

All the majors through your own API keys, plus local Ollama models on the same server. Route everything through a LiteLLM gateway and you add spend tracking and failover without touching the flows.

Stack it

Flowise runs well with.

Same server, no extra bill. These are the companions our team installs next to Flowise most often.

LiteLLM

+1 GB

One API gateway for 100+ LLM providers: unified OpenAI-format calls, spend tracking, rate limits, and failover, self-hosted.

Ollama

+16 GB

Run open LLMs on your own server. Honest requirement: real models want real RAM, and the meter will route you to the right plan.

PostgreSQL

+1 GB

The engineers’ database. Installed, tuned for your RAM, and backed up twice offsite.

Frequently asked questions

Is Flowise production-ready?

For chatbots and internal tools, comfortably: flows serve as APIs with authentication, and our deployment forces HTTPS from the start. For high-throughput pipelines, put PostgreSQL beside it and size the Cube honestly.

Flowise or n8n?

n8n automates workflows across hundreds of SaaS apps; Flowise builds LLM-centric apps and agents. They meet in the middle often enough that running both on one server is a common combination here, both apps at $0.

What does Flowise hosting cost?

The app is $0; a 2 GB managed Cube starts at $26.67/mo on annual billing. Model usage bills with your API provider, or costs nothing with local Ollama inference.

Sizing an app stack? The VPS sizing calculator recommends a plan from your apps and traffic, with the math shown.

Your server runs. You sleep.

Fully managed hosting from people who have been doing this since 2001.