Flowise
A self-hosted visual AI agent builder with knowledge retrieval, human review and application APIs; the project is archived and no longer maintained.
Flowise is a visual builder for developers and teams creating AI agents and chatbots from connected workflow blocks. The project is archived and no longer maintained.
- Agent workflows: Agentflow coordinates multiple agents, while Chatflow builds single-agent assistants with tool calling and knowledge retrieval from connected data sources.
- Human review: Add review steps so people can check agent tasks within the workflow's feedback loop.
- Application integration: Connect workflows to other software through APIs, TypeScript and Python SDKs, or place a chat widget on a website.
- Execution inspection: View execution traces and connect observability tools including Prometheus and OpenTelemetry to examine agent activity.
Flowise runs locally or on your own infrastructure, including through Docker. It connects to language models, embedding services and vector databases. Integrations include AWS Bedrock and Milvus, alongside LangChain and LlamaIndex workflows.
Flowise Cloud is a separate hosted offering. Self-hosting the builder doesn't make cloud model processing local: requests to external model services go to those providers. Larger deployments can distribute work through message queues and workers.
Logotyper
