Flowise

Open-source visual builder for LLM apps, agents, and chatbots using drag-and-drop nodes.

4.5 (4)

Anmeldt av Daniel Nikulshyn·Oppdatert mai 2026

RAG Agents Open Source Low-Code LLM Self-Hosted API Visual Builder

Oversikt

Flowise is an open-source low-code platform for designing AI workflows by connecting nodes on a visual canvas. It wraps popular frameworks like LangChain and LlamaIndex, letting developers prototype chatbots, retrieval-augmented generation pipelines, and autonomous agents without writing extensive glue code. Built flows can be exposed as APIs, embedded as chat widgets, or integrated into existing applications. Flowise supports a wide range of model providers, vector databases, and tools, and can be self-hosted via Docker or run in the cloud for teams that need more control over data and deployment.

Nøkkelfunksjoner

Drag-and-drop flow builder
LangChain and LlamaIndex node support
RAG and vector database integrations
Agent and tool orchestration
API endpoints and chat embed
Docker-based self-hosting

Brukstilfeller

Prototype RAG chatbots visually

Connect LLM, embedding, and vector database nodes on the canvas to quickly build retrieval-augmented chatbots without writing extensive LangChain or LlamaIndex glue code.

Embed AI assistants in apps

Expose built flows as API endpoints or drop-in chat widgets to integrate custom AI assistants into existing websites and internal tools.

Orchestrate autonomous agents

Use agent and tool nodes to design multi-step workflows where LLMs call tools, query data, and make decisions across a visual pipeline.

Self-host LLM workflows on Docker

Deploy Flowise via Docker to keep model interactions, data, and flow logic under your team's control for privacy-sensitive or regulated environments.

Fordeler og ulemper

Fordeler

Open source and self-hostable
Visual canvas speeds up prototyping
Broad integrations with LLMs and vector stores
Exports flows as APIs and embeddable widgets

Ulemper

Complex flows can become hard to manage
Requires some understanding of LLM concepts
Self-hosting adds maintenance overhead

Anmeldelser

4.5

Gjennomsnitt fra 4 vurderinger.

Logg inn for å legge igjen en anmeldelse.

Esther Adeyemi

Skeptical, then convinced

I went in skeptical — most tools in this space overpromise. It actually delivers on langChain and LlamaIndex node support, and broad integrations with LLMs and vector stores caught me off guard. still, I'd recommend giving it a real trial.

Gunnar Eriksson

Compared a few options

Evaluated this against two competitors. Where it wins: docker-based self-hosting and visual canvas speeds up prototyping. Where it lags: complex flows can become hard to manage. On balance the feature set — especially drag-and-drop flow builder — justifies the 4 stars for our use case.

Carlos Mendoza

Solid for our team

We rolled this out across the team last quarter and broad integrations with LLMs and vector stores. Docker-based self-hosting fits neatly into how we already work, and docker-based self-hosting removed a step we used to do by hand. Requires some understanding of LLM concepts, which is the main caveat, but it has held up under daily use.

Priya Nair

Use it every day

Honestly didn't expect to like it this much. LangChain and LlamaIndex node support is exactly what I needed, and visual canvas speeds up prototyping. I do wish requires some understanding of LLM concepts, but I reach for it almost every day now and it just clicks.