Devtoolwatch BoardDify review
Dify is an open-source LLM app development platform for building agentic workflows, RAG pipelines, and agents on a visual canvas.
TL;DR
Dify is an open-source platform for building LLM apps with visual workflows, RAG pipelines, agents, model management, and observability. Dify suits teams that want to move from prototype to production on one workspace. Teams can run Dify on Dify Cloud, in a VPC, or self-hosted with Docker Compose, and every feature has a matching API.
- 160.1kGitHub stars
- +742new stars, week of Oct 25
- #13in Agent frameworks this week
Dify at a glance
- Category
- Agent frameworks
- Maintained by
- LangGenius (organization, @langgenius on GitHub)
- Language
- Python, TypeScript, JavaScript
- Repository
- github.com/langgenius/dify
- Website
- dify.ai
- Latest release
- 1.18.0 on GitHub, Oct 23, 2026
- First published
- Apr 12, 2023
What Dify does
- Dify lets you build and test AI workflows on a visual canvas.
- Dify connects to many proprietary and open-source LLMs, including GPT, Mistral, Llama3, and any OpenAI API-compatible model.
- Dify includes a RAG pipeline covering document ingestion to retrieval, with text extraction from PDFs, PPTs, and other common formats.
- Dify agents run in their own Linux sandbox, where they run commands, install software, and handle files.
- Dify agents can use tools from Dify Marketplace, MCP servers, or your own APIs, as a chat app or workflow step.
- Dify provides a Prompt IDE for writing prompts, comparing model performance, and adding features such as text-to-speech.
- Dify monitors application logs and performance, and integrates with Opik, Langfuse, and Arize Phoenix for observability.
How it works
Dify runs as a server, most easily started with Docker Compose, and you work in it through a browser dashboard. Dify also offers a hosted Dify Cloud. Every Dify feature has a corresponding API for use in your own code. Since 1.18.0, OpenAPI and the difyctl client let you build and manage apps from the command line. Agent code execution can use a local sandbox or E2B cloud sandboxes.
How to install and start using Dify
Requirements
- CPU with at least 2 cores and at least 4 GiB of RAM.
- Docker and Docker Compose v2.24.0 or later for self-hosting.
- Python 3.13 for source installations as of 1.18.0.
First steps
- Install Docker and Docker Compose v2.24.0 or later on a machine with at least 2 CPU cores and 4 GiB RAM.
- Start the Dify server with Docker Compose from the docker directory.
- Open http://localhost/install in your browser to start the initialization process.
Who Dify is for
- Teams building LLM apps that need workflows, RAG, and agents in one shared workspace.
- Organizations that must deploy AI apps in their own VPC or on self-hosted infrastructure.
- Developers who want to embed LLM app features in their own backend through APIs.
Limitations to know
- Dify Agent services should be offered only to trusted, non-malicious users, according to the release notes.
- Upgrades can require manual steps; 1.17.1 required a staged Weaviate upgrade, and skipping it could break vector search.
- The license is the Dify Open Source License, based on Apache 2.0 with additional conditions.
- SSO, RBAC security, and enterprise support SLAs are offered through Dify Enterprise, which requires contacting sales.
Is Dify growing? Usage data
In the week of Oct 25–31, 2026, Dify ranked #131 on the Devtoolwatch Board and #13 in Agent frameworks, with a momentum score of 56 out of 100.
Show the weekly numbers
| Week of | New stars |
|---|---|
| Aug 9, 2026 | 798 |
| Aug 16, 2026 | 737 |
| Aug 23, 2026 | 685 |
| Aug 30, 2026 | 742 |
| Sep 6, 2026 | 1k |
| Sep 13, 2026 | 974 |
| Sep 20, 2026 | 813 |
| Sep 27, 2026 | 555 |
| Oct 4, 2026 | 612 |
| Oct 11, 2026 | 736 |
| Oct 18, 2026 | 815 |
| Oct 25, 2026 | 742 |
On Hacker News
- Dify, a visual workflow to build/test LLM applications, 185 points and 38 comments (Apr 22, 2024)
The Board ranks tools by four signals each week: new stars, new stars for the repo's size, added downloads and download growth beyond the market. How the ranking works.
Dify alternatives
Other AI agent frameworks on the Board in the week of Oct 25–31, 2026, by momentum:
| Rank | Tool | Stars | Downloads/wk |
|---|---|---|---|
| #1 | Harness²Harness² is a Python framework from Google Research for recursive agent harnessing, refining an agent's prompts, tools, memory and… | 21.7k | – |
| #2 | HyperFramesHyperFrames is an open-source framework that turns HTML, CSS, media, and seekable animations into deterministic MP4 videos, built for AI… | 76.6k | 1.5M |
| #3 | AgentScopeAgentScope is a Python agent framework with an SDK for building ReAct agents and an agent service backend with a web UI. | 35k | 51.4k |
| #4 | AG-UIAG-UI is an open, event-based protocol that standardizes how AI agents connect to user-facing frontend applications. | 16.9k | 4.6M |
| #5 | LangGraphLangGraph is a low-level orchestration framework and runtime for building, managing, and deploying long-running, stateful agents in… | 44.2k | 18.5M |
| #6 | BifrostOpen-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for… | 9.3k | – |
Recent Dify releases
Dify FAQ
Is Dify free and open source?
Dify's code is on GitHub (langgenius/dify), but the repository doesn't declare a standard open-source license. Check its license file before using it commercially. Its website links to a pricing page: https://dify.ai/pricing.
Is Dify still maintained?
Yes. The langgenius/dify repository was last updated on Oct 25, 2026, and the latest release, 1.18.0 on GitHub, came out on Oct 23, 2026.
How popular is Dify?
Dify has 160.1k GitHub stars as of Nov 1, 2026. It gained 742 new stars in the week of Oct 25–31, 2026, against a 12-week average of 771 a week. That made it #13 among AI agent frameworks on the Devtoolwatch Board.
Dify vs n8n: how do they compare?
Dify and n8n are both tracked by Devtoolwatch as AI agent frameworks. Dify has 160.1k GitHub stars and n8n has 209.2k. n8n is a fair-code workflow automation platform for building AI agents and workflows with a visual canvas plus custom code, self-hosted or cloud. n8n review.
Dify vs Flowise: how do they compare?
Dify and Flowise are both tracked by Devtoolwatch as AI agent frameworks. Dify has 160.1k GitHub stars and Flowise has 55.5k. Flowise is an open source TypeScript platform for building AI agents, chatbots and multi-agent workflows visually. The project is now archived. Flowise review.
What are the best alternatives to Dify?
Other AI agent frameworks on the Devtoolwatch Board in the week of Oct 25–31, 2026, by momentum: Harness² (#1), HyperFrames (#2), AgentScope (#3), AG-UI (#4), LangGraph (#5). The alternatives table above has their numbers.
What is Dify AI?
Dify is an open-source LLM app development platform. Dify combines AI workflows, a RAG pipeline, agents, model management, and observability in one interface, so you can go from prototype to production.
Is Dify open source?
Dify is open source. Its repository uses the Dify Open Source License, which is based on Apache 2.0 with additional conditions. The self-hosted Community Edition deploys with Docker.
What is Dify Cloud?
Dify Cloud is the hosted version of Dify, run by the Dify team, so you can try Dify without managing a server. Plans and usage allowances are listed on the Dify pricing page.
What is a Dify agent?
A Dify agent is an autonomous agent with its own Linux sandbox, where it runs commands, installs software, and handles files. You can give it skills and tools, then use it as a chat app or a workflow step.
How do I use the Dify API?
Dify provides APIs for all of its features, so you can integrate Dify apps into your own business logic. Version 1.18.0 added OpenAPI support and the difyctl command-line client for building and managing apps.
What is a Dify workflow?
A Dify workflow is an AI pipeline you build and test on a visual canvas. Workflows can include model calls, RAG retrieval, tools, and agent steps.
Sources
Dify README badge
Maintainers can show the tool's weekly Board rank in their README:
[](https://index.devtoolwatch.com/tools/dify/)How this page is made: Devtoolwatch writes each review from the project's README, releases, package metadata and website, with an AI model, then checks every claim against the source it cites and drops what the sources don't support. The numbers come from Devtoolwatch's daily GitHub snapshots, GitHub's stargazer history, and the npm and PyPI download APIs. Spotted an error? Email [email protected].