Start here: your first agent flow
Goal. Create a free Flowise Cloud account and assemble your first working agent flow on the visual canvas.
Drag a Chat Model node onto the canvas, connect an OpenAI chat node to it, open the chat panel and ask: "Explain what retrieval-augmented generation is in two sentences."
Open flowiseai.com, start a free Flowise Cloud account, and click New Chatflow — you build and test entirely in the browser.
- 1Go to flowiseai.com and start a free Flowise Cloud account (the Free plan is $0/month, no credit card to begin). Prefer to run it yourself? The open-source version (Apache 2.0) is free to self-host with Docker or Node.js.
- 2Create a New Chatflow. You get a blank canvas: you build agents by dragging boxes called nodes and connecting them, so you can see exactly how information flows — no code.
- 3Add a chat-model node (e.g. OpenAI) and paste in your own model API key, then open the chat panel and send the prompt above. The builder is free; the model usage is billed by your provider, not Flowise.
You'll see. A two-node flow on the canvas answering your question in the chat panel — your first agent, assembled by dragging and connecting, with no code.
Cost. Flowise Cloud Free = $0/month (2 flows & assistants, 100 predictions/month, 5MB storage). Self-hosting the open-source version is free. On every plan you separately pay your own LLM API usage.
Takeaway. Flowise turns building an AI agent into connecting boxes on a canvas — the builder is free; you bring your own model key.