Flowise

Flowise is an open-source platform for building generative AI agents and LLM workflows. It is most compelling for developers who want visual workflow design and can maintain a self-hosted project themselves. For a new production system, its announced end of life is a serious drawback.

Overview

Assistant, Chatflow and Agentflow builders cover assistants, chatbots, single- and multi-agent systems, and workflow orchestration. That breadth suits teams exploring different AI application patterns without starting from separate builder tools. But the maintenance window is short: feature development ceased on July 29, 2026, repository archival is scheduled for August 10, and end of life is scheduled for August 31, 2026. npm packages and Docker images are to be marked deprecated after archival.

The source is to remain on GitHub under the Apache 2.0 license, and Flowise encourages teams to fork it. That offers a route for organizations with engineering capacity to continue independently, not a promise of upstream fixes or continued vendor support. Official core-team presence in Discord and GitHub concluded on August 31, 2026.

Key features

Visual orchestration is backed by execution logs, visual debugging, evaluations, human review, and RAG indexing pipelines. Together, these give teams ways to inspect runs, assess outputs, and include review in workflows, rather than simply connecting components. The combination is useful for knowledge-grounded and multi-agent applications, though the scheduled wind-down means teams should account for maintenance ownership before building around it.

Flowise connects to more than 100 sources, tools, vector databases, and memories, including LangChain, LlamaIndex, and Zapier Zaps. APIs, an embedded chat widget, and TypeScript and Python SDKs give developers several ways to connect applications. Security controls include RBAC, SSO, encrypted credentials, secret managers, rate limiting, and restricted domains. For production, Flowise recommends queue mode, PostgreSQL at scale, AWS S3 storage, and AWS Secret Manager for credential key management; that guidance points to a deployment requiring operational decisions beyond the visual builder.

Deployment can be cloud or on-premises, with npm and Docker installation instructions and self-hosting options. This flexibility helps teams choose their infrastructure, but self-hosting also makes them responsible for the environment and, as the project winds down, increasingly for the software itself.

Pricing

The Free plan costs nothing and includes 2 Flows & Assistants, 100 Predictions / month, 5MB Storage, Evaluations & Metrics, Custom Embedded Chatbot Branding, and Community Support. Its flow, prediction, and storage caps make it suitable for small experiments, not an uncapped service.

Starter costs $35 a month. It adds unlimited Flows & Assistants and raises the allowance to 10,000 Predictions / month and 1GB Storage, while retaining Community Support. It fits a small project that needs more headroom but not multiple workspaces or priority support.

Pro costs $65 a month and includes 50,000 Predictions / month, 10GB Storage, Unlimited Workspaces, Admin Roles & Permissions, and Priority Support. It includes 5 Users; additional users cost $15/user/month. Those higher limits and controls are aimed at teams, but paid capacity is a harder commitment to justify while the product is winding down. A free trial is available.

Platforms

Flowise supports API, Linux, macOS, self-hosted, web, and Windows. Its deployment options suit teams that need to run software on their own infrastructure as well as those choosing cloud deployment.

Who it's for

Flowise best fits developers and organizations that value visual agent and workflow construction, need broad integration options, and can take responsibility for deployment and ongoing maintenance. It is a poor fit for teams seeking a product with a continuing core-team support presence or a long-term upstream roadmap.

Pros and cons

• Pro: Three visual builders cover assistants, chatbots, single- and multi-agent systems, and orchestration, giving teams a broad starting point for AI applications.
• Pro: More than 100 integration connections, developer APIs and SDKs, and cloud or self-hosted deployment provide several ways to connect and run projects.
• Pro: Documented security controls and production guidance address important operational needs for teams deploying beyond prototypes.
• Con: Feature development has ceased, with archival and end of life scheduled for August 2026; teams must plan for a transition or maintain a fork.
• Con: Free is capped at 100 monthly predictions and 5MB storage, while higher paid quotas do not remove the product's maintenance risk.

Alternatives

For a self-hosted open-source option with an Android platform, consider AnythingLLM; its Basic plan is $50 a month, billed monthly. For a self-hosted community edition with a free AGPL-3.0 plan, I3K RAG Enterprise is another option. RAGFlow has a free plan at no cost with 5 Apps, 1 team member, 0.1 GB dataset storage, and 500 credits / month, but no API key.

For a free Apache 2.0 project installable via pip or Docker, consider txtai. LlamaIndex is another option for teams considering open-source projects around LlamaIndex and Workflows; LlamaParse is commercial, not open source. OpenRAG offers a free AGPL-3.0 self-hosted plan with no feature held back. Quivr offers free plans for documentation management and support-data analysis. For a hosted sandbox with a free tier, Dify includes 200 message credits, one workspace, one member, five apps, and 50 knowledge documents.

Browse AI Agent Platforms and Retrieval-Augmented Generation Tools for more options.

Verdict

Choose Flowise if visual agent building, broad integrations, and deployment flexibility matter—and your team can maintain its own fork or plan a migration. Its builders and operational controls are substantial strengths, but the announced end of life makes it difficult to recommend for new production systems that depend on ongoing upstream development or official support.