Flowise

Flowise is a visual builder for AI agents and chatbots that can run locally or on your own server, including through Docker. It's for developers and teams building LLM applications with connected workflow blocks. The project is archived and no longer maintained.

Its editor covers both chat assistants and workflows that coordinate multiple agents. Chatflow builds single-agent assistants with tool calling and retrieval-augmented generation (RAG), so chatbots can draw on connected data sources. Agentflow distributes work across coordinated agents. Human review can sit inside the workflow, letting people check agent tasks as part of a feedback loop.

Flowise connects to LLMs, embedding services and vector databases. Its ecosystem includes LangChain and LlamaIndex, with integrations such as AWS Bedrock and Milvus. The visual approach suits teams that want to see how models, retrieval and tools connect while developing an application.

APIs, TypeScript and Python SDKs let developers connect those workflows to other applications. An embedded chat widget provides a way to put an assistant on a website. Execution traces help inspect agent behavior, and observability support includes Prometheus and OpenTelemetry.

The application supports on-premises deployment as well as cloud infrastructure. Cloud model integrations send requests to the chosen provider; hosting Flowise locally does not make those services local. Most code uses Apache 2.0, while the enterprise directory has a separate commercial license. For larger deployments, message queues and workers support horizontal scaling.