Logo
Deploy Now

SaaS Alternative

Voiceflow Relevance AI Botpress Cloud Stack AI

Categories

Developer Tools AI Automation LLM Low-Code Chatbot RAG Agents

Stars

54425

Forks

24675

Watchers

362

Developer links

Last Updated: 07-08-2026 10:47 AM (UTC)

Flowise

Drag nodes onto a canvas and ship an LLM app: Flowise is an open-source visual builder for AI agents and LLM applications, written in Node.js on LangChain.js and licensed Apache-2.0. You assemble flows by dragging nodes onto a canvas: models, prompts, memory, vector stores, retrievers, and tools, then wire them together and test in the built-in chat panel. Three builder types cover increasing complexity: Assistant for simple RAG chat over uploaded files, Chatflow for single-agent systems with techniques like rerankers and Graph RAG, and Agentflow for multi-agent orchestration with branching, looping, shared flow state, and human-in-the-loop checkpoints. Over 100 integrations connect data sources, vector databases, and both proprietary and open-source models, plus MCP client and server nodes for standard tool interop. Finished flows are exposed as REST APIs, embedded chat widgets, or via JS and Python SDKs - each flow gets an endpoint the moment it is saved, removing the deployment gap between a working prototype and something your application can call. Execution logs, visual step debugging, and external log streaming trace behavior, while input moderation and rate limiting act as guardrails; RBAC, SSO, and workspaces cover team deployments. Self-hosting keeps prompts, encrypted credentials, and conversation data on your own instance, which matters when flows handle internal documents or customer data - and wiring a model, prompt, memory, and vector store on the canvas replaces the boilerplate a hand-coded LangChain project would need.

Flowise
Flowise
Flowise

Benefits

  • Prototype LLM Apps in Minutes
  • Wiring a model, prompt, memory, and vector store on the canvas replaces boilerplate LangChain code, so testing a new RAG or agent idea takes minutes instead of a coding session.
  • Every Flow Is Instantly an API
  • Each flow gets a REST endpoint and an embeddable chat widget the moment it is saved, removing the deployment gap between a working prototype and something your application can call.
  • Keys and Conversations Stay Private
  • Model credentials are stored encrypted on your instance and chat traffic never transits a third-party builder platform, which matters when flows handle internal documents or customer data.
  • From Simple Bot to Multi-Agent System
  • The same platform scales from a three-node Q&A bot to Agentflow orchestrations with multiple agents, conditional routing, loops, and human approval steps.

Features

  • Three Visual Builders
  • Assistant for guided RAG chat setup, Chatflow for flexible single-agent systems, and Agentflow V2 for explicit multi-agent workflow orchestration with shared state.
  • 100+ Integrations
  • Nodes for OpenAI, Anthropic, Google, and open-source models, vector stores like Pinecone, Qdrant, and Chroma, document loaders, memory backends, and external tools.
  • RAG Pipeline Tooling
  • Document ingestion, chunking, embedding, retrievers, and rerankers composed visually, including advanced patterns like Graph RAG.
  • MCP Client and Server Nodes
  • Connect external Model Context Protocol tool servers into flows, or expose flows as MCP tools, with SSE transport and authentication support.
  • API, SDKs, and Embedded Chatbot
  • Call flows over REST, integrate with JS or Python SDKs, or drop the customizable chat widget into any website.
  • Observability and Guardrails
  • Execution logs, visual step debugging, external log streaming, input moderation, and rate limiting; RBAC, SSO, and workspaces cover team deployments.