Dify by LangGenius combines a visual workflow builder, knowledge pipelines, sandboxed agents, model management and app APIs. It runs as Dify Cloud or self-hosted with Docker Compose under a modified Apache 2.0 license.
For a new project, choose Dify: it is an actively developed LLM app platform with a visual workflow builder, RAG pipeline and agents, available as a self-hosted Community Edition, as Dify Cloud or as Dify Enterprise. Flowise offered a similar visual builder, but its repository was archived and made read-only on Aug 13, 2026, and active feature development has stopped. Flowise remains an option only for teams already running it who accept maintaining their own fork of the Apache 2.0 code. The deciding factor is ongoing maintenance, with Dify's modified licence terms as the main point to review.
Choose Dify if
Shortlist Dify when you need a maintained visual builder for workflows, RAG and agents, with a choice between self-hosting on Docker, Dify Cloud and an enterprise deployment.
Choose Flowise if
Shortlist Flowise when you already run Flowise flows in production and can maintain your own fork of the Apache 2.0 code while you plan a migration.
Key differences
Key differences between Dify vs Flowise
Aspect
Dify
Flowise
Project status
Dify is maintained by LangGenius, Inc. and offered as an open-source Community Edition, a hosted cloud service and an enterprise private deployment.
The Flowise repository was archived on Aug 13, 2026 and is read-only, and the team stopped reviewing or accepting new pull requests.
Licence terms
Dify uses a modified Apache License 2.0 that forbids running a multi-tenant service from the source code without written permission and forbids removing the logo from the frontend.
Code outside the enterprise directory is under the Apache 2.0 licence, and the team says that code is yours to keep building on.
Deployment options
The Community Edition is self-deployed with Docker, with Docker Compose named as the easiest way to start; Dify Cloud and Dify Enterprise are alternatives.
Flowise installs with npm or Docker, but its npm packages and Docker images are marked deprecated as part of the archive.
Building blocks
Dify combines an AI workflow builder, a RAG pipeline, agent capabilities, model management and observability in one interface.
Flowise builds multi-agent systems with workflow orchestration in Agentflow and single-agent chatbots with tool calling and RAG in Chatflow.
Model providers
Dify integrates with hundreds of proprietary and open-source LLMs from dozens of inference providers, including any OpenAI API-compatible model.
Flowise supports tool calling and retrieval from various data sources; with the project archived, new provider integrations will come only from forks.
APIs and observability
Every Dify offering has a corresponding API, and the platform integrates with Opik, Langfuse and Arize Phoenix for observability.
Flowise exposes APIs, an SDK and an embedded chat, with full execution traces and support for Prometheus and OpenTelemetry.
Support and enterprise
Dify sells an enterprise offering for organisations that need self-hosting, SSO, RBAC security and support SLAs.
Official core team presence in Discord and GitHub has ended, so support depends on your own team or a community fork.
More specifications
From the iThub profiles. “Not recorded” means the profile does not confirm it. Confirm prices and editions with each vendor.
Dify is an LLM application development platform made by LangGenius, Inc. Its web console combines a visual workflow canvas, a RAG pipeline for knowledge bases, agents, a prompt IDE, model management and logging in one workspace. Every app built in Dify is also exposed through an API, which the project describes as Backend-as-a-Service. The source code is published in the langgenius/dify repository, and the product overview, plans and editions are on dify.ai.
There are three ways to run it. Dify Cloud is the hosted SaaS operated by LangGenius. The Community Edition is the open-source code, deployed on one's own infrastructure, mainly with the Docker Compose file in the repository's docker folder. Dify Enterprise is a private deployment with a commercial license, multiple workspaces, SSO and support SLAs, sold through the sales team.
Flowise
Flowise is an open-source platform for building agentic systems visually. Its Agentflow mode builds multi-agent systems with workflow orchestration, and Chatflow builds single-agent systems and chatbots with tool calling and retrieval (RAG) from data sources. It also offers human-in-the-loop review of agent tasks and execution traces with Prometheus and OpenTelemetry support. It installs with npm and exposes a prediction API for running flows.
The project is being wound down. The Flowise site announces a sunset: active feature development stopped on July 29, 2026, the GitHub repository was scheduled to move to public archive on August 10, 2026, and the core team's presence in Discord and GitHub ends on August 31, 2026. The GitHub page now shows the repository as archived and read-only since Aug 13, 2026. The Apache 2.0 licensed source stays on GitHub, and the team encourages users to fork it. Workday acquired Flowise in 2025. The sunset notice gives the reason as a shift toward coding agents, where rigid low-code workflows reach their limits on complex tasks.
How to evaluate Dify and Flowise
Dify and Flowise are both visual builders for LLM workflows, agents and RAG applications, but they are in different states. Dify is actively offered as a self-hosted Community Edition, a cloud service and an enterprise deployment, under a modified Apache 2.0 licence. Flowise was archived on Aug 13, 2026, with feature development stopped and its Apache 2.0 code left for teams to fork. The evaluation is mostly about long-term maintenance and licence terms.
List the flows you need to build or migrate, the model providers and data sources they use, and whether you plan to offer the result to external customers. Decide who will patch and upgrade the platform over the next two years, and have your legal team review each licence against your intended use.
Criteria to verify
Active maintenance and security patch cadence
Licence fit for your commercial use
Support for your model providers
Self-hosting effort with Docker
Export and migration path for flows
Access control and audit options
Proof-of-concept plan
Take one production flow, such as a RAG chatbot over a document set, and rebuild it in Dify and in your Flowise install or fork. Run the same 30 test questions, call each through its API, and record answer quality, setup time, upgrade steps and any licence questions raised by your legal team.
Advertisements
Frequently asked questions
Is Flowise still maintained?
No. The Flowise team announced it is winding down operations, active feature development has stopped, and the GitHub repository was archived and made read-only on Aug 13, 2026. Official core team presence in Discord and GitHub has ended. The Apache 2.0 code stays on GitHub, so existing users can keep running it or maintain their own fork.
Why was Flowise discontinued?
The sunset announcement says developers increasingly rely on coding agents for complex tasks as models improve at reasoning. It states that the rigid workflow low-code approach quickly hits its limit when complexity grows, and the team decided to wind down Flowise for that reason. The source code remains available under Apache 2.0 for teams that want to fork it.
Is Dify open source?
Dify's source code is public, but it uses a modified Apache License 2.0 with extra conditions. Without written authorisation you may not use the code to run a multi-tenant service, where one tenant equals one workspace, and you may not remove the logo or copyright information from the frontend. Review these terms before building a commercial service on Dify.
Can Dify be self-hosted?
Yes. The Dify Community Edition is open source and self-deployed with Docker, and the README names Docker Compose as the easiest way to start the server. Teams that prefer not to run servers can use Dify Cloud, and Dify Enterprise offers a private deployment with SSO, RBAC and support SLAs.
What should Flowise users migrate to?
The Flowise team suggests forking the Apache 2.0 code to maintain internal updates, and notes that developers are moving toward coding agents for complex tasks. Teams that want to stay with a visual builder can evaluate Dify, which offers a workflow builder, RAG pipeline and agents with self-hosted and cloud options. Rebuild and test one critical flow before committing.
What is the main difference between Dify and Flowise?
Both are visual builders for LLM workflows, agents and RAG, but Dify is actively developed and sold as a Community Edition, a cloud service and an enterprise deployment, while Flowise has been archived and no longer receives updates. Licensing also differs: Flowise core code is Apache 2.0, while Dify uses a modified Apache 2.0 licence with multi-tenant and branding conditions.
Sources
Facts on this page come from these official pages, checked on , and from the iThub profiles. Vendors change plans and features: confirm with them before buying.