Flowise

Flowise is an open-source, low-code platform that lets developers and non-developers assemble large language model (LLM) applications visually, by wiring together nodes on a canvas instead of writing orchestration code.^[1]

History

Flowise was co-founded by Henry Heng and Chung Yau Ong and launched in 2023, the year it went through Y Combinator's batch. It grew out of the open-source LangChain ecosystem: the platform's flows map closely to LangChain primitives such as chains, agents, memory and tools, but expose them through a graphical editor.^[2]

Because the core product is released under the MIT licence, the source code is public and the platform can be self-hosted at no licence cost. A hosted cloud version is offered for teams that prefer not to run their own infrastructure. By the mid-2020s Flowise had become one of the most widely adopted open-source builders in the LLM tooling category, alongside Dify and Langflow.^[3]

Key Concepts

The central abstraction in Flowise is the flow: a directed graph of nodes executed at runtime. Typical node types include:

• Chat models — connections to OpenAI, Anthropic, Google, Mistral, Ollama and other providers, including local open-weight models.
• Prompts and memory — prompt templates and conversation memory objects that maintain chat history.
• Document loaders and vector stores — for building retrieval-augmented generation (RAG) pipelines over PDFs, websites and internal knowledge bases.
• Tools and agents — function-calling tools, HTTP requests and autonomous agent loops that let the model decide which action to take next.
• Chains and terminators — sequencing logic, sub-flows and output parsers.

A completed flow can be published as a chatflow (a conversation interface), an agentflow (a multi-step agentic workflow with conditional branches) or an API endpoint that other applications call programmatically. Because deployment reduces to an HTTP call, Flowise is frequently used as the glue layer between a company's data and a front-end product.^[1]

Applications

Flowise is used to build customer-support bots over internal documentation, document-QA assistants, lead-capture widgets and lightweight agent pipelines that summarise emails, classify tickets or call external APIs. Its low-code nature means business analysts and citizen developers can prototype alongside engineering teams, which shortens the path from idea to working demo.

The trade-off is control versus speed. Complex, long-running production systems often outgrow a visual editor and move to code-first frameworks; Flowise is strongest where transparency, rapid iteration and maintainability by non-specialists matter more than fine-grained control of every step.^[3]

>See Also

• Dify
• LangChain
• n8n
• CrewAI
• Retrieval-Augmented Generation