Flowise
Open-source, low-code visual builder for LLM apps and AI agents — drag-and-drop to assemble chains, agents, and RAG; self-host or use Flowise Cloud.
Flowise is an open-source, low-code platform for building LLM apps and AI agents on a drag-and-drop canvas. You wire nodes into chains, agents, and RAG flows, then self-host the Apache-2.0 core or run Flowise Cloud. Built flows expose an API and embed widget, so prototypes ship as real product surfaces.
Flowise is a low-code, visual builder for LLM apps and AI agents. Instead of hand-writing orchestration, you drag nodes onto a canvas and connect them into chains, agentic systems, and retrieval-augmented (RAG) flows — its homepage positions it plainly as "Build AI Agents, Visually," an open-source agentic-systems development platform.
It targets developers and technically-minded builders who want to prototype and ship LLM features fast without wiring every model call, memory store, and tool by hand. Run it locally with one npm command, self-host the Apache-2.0 core on your own infrastructure, or use the managed Flowise Cloud. Because every flow is exposed as an API and an embeddable widget, Flowise fits an AI-assisted workflow as the visual layer between a model provider and a real product surface.
Highlights
- Drag-and-drop flow builder — assemble logic visually on a canvas, inspect each node's input/output, and iterate without redeploying code.
- Agents, RAG, and chains as nodes — build multi-agent systems, retrieval pipelines over your documents, and tool-using chains from composable building blocks.
- Self-hostable with an API — own the deployment, then call any flow over its REST API or drop in the embed widget to put it in an app.
- Large integration ecosystem — connect many model providers, vector stores, document loaders, and tools, so flows reach real data and services.
In an AI-assisted workflow
Flowise sits between your model provider and your product: build a flow visually, test it on the canvas, then call its endpoint from your app. Spin it up locally in seconds:
npx flowise start
# open http://localhost:3000For where this slots against automation-first and app-first tools, see n8n vs. Dify.
TIP
Prototype the flow in the visual editor, then promote it by calling its generated API from your codebase — the canvas stays the source of truth while your app just consumes the endpoint.
Good to know
License matters here. The Community Edition is Apache-2.0 — permissive enough to self-host, modify, and use commercially, including running it as a service. A separate Enterprise Edition ships inside the repo's /enterprise directory under a commercial license and stays inactive without a license key, so confirm which edition you're deploying before building a SaaS on it. Flowise Cloud is the paid managed path — as of September 2026 flowiseai.com lists Free at $0/month, Starter at $35/month, and Pro at $65/month (5 users, then $15/user/month).
WARNING
FlowiseAI archived the GitHub repository on August 13, 2026 and wound the project down, saying capable coding agents had outrun the rigid low-code approach; core-team support in Discord and GitHub ended August 31, 2026. The Apache-2.0 code remains public and forkable, and Flowise Cloud is still selling, but there is no official successor repo and no upstream maintenance — treat new deployments as depending on a fork you own.
For how it stacks up against other visual builders, see Best AI App Builders (2026).
Frequently asked questions
- What is Flowise?
- Flowise is an open-source, low-code visual builder for LLM apps and AI agents. You assemble chains, agentic systems, and RAG pipelines by dragging and connecting nodes on a canvas instead of writing orchestration code, then run the result locally, self-hosted, or on Flowise Cloud. Every flow exposes an API and an embeddable chat widget.
- Is Flowise free, and what's the license?
- The Community Edition is free and open source under Apache-2.0 — you can self-host, modify, and use it commercially. A separate Enterprise Edition lives in the repo's /enterprise directory and is governed by a commercial license, staying inactive without a license key. Note that FlowiseAI archived the GitHub repository on August 13, 2026 and wound the project down, with core-team support ending August 31, 2026; the Apache-2.0 code stays public and forkable but is no longer maintained upstream. Flowise Cloud still sells: as of September 2026, flowiseai.com lists a Free tier at $0/month, Starter at $35/month, and Pro at $65/month.
- How does Flowise compare to Dify?
- Both are visual LLM-app platforms. Flowise's core is cleanly Apache-2.0 (only the enterprise add-ons are commercial), which makes single-tenant and SaaS self-hosting straightforward. Dify ships a broader product surface (built-in RAG pipeline, prompt IDE, LLMOps) under a modified Apache-2.0 that restricts multi-tenant operation. Pick Flowise for a permissively licensed agent/flow builder; pick Dify for a heavier all-in-one app platform.
Filed under
low-code · visual · agents · rag · workflow
Related
- Which Agent Framework in 2026? LangGraph vs CrewAI vs AutoGen vs OpenAI Agents SDK vs Claude Agent SDKA decision guide to the major AI agent frameworks — control vs. abstraction, multi-agent models, state and durability, and which fits your project.
- n8n vs Dify: Which AI Workflow Platform? (2026)Automation-first vs AI-native: n8n's 400+ integrations and agent nodes vs Dify's LLM-app platform with built-in RAG. Licenses, pricing, and the fit test.
- Building Multi-Step Agent WorkflowsPatterns for building multi-step agent workflows in Claude Code: decompose tasks, fan-out to parallel subagents, verify every step, and orchestrate.
- Best AI App Builders in 2026: v0 vs Lovable vs Bolt vs ReplitSeven AI app builders compared for 2026 — v0, Lovable, Bolt, Replit Agent, Base44, Emergent, and Rork — with a verdict, a pricing model, and a best-for each.