Skip to main content
Dify hero visualization
Dify logo

dify - open-source llm app development platform

agent-infra
Updated for 2026

About Dify

Visual platform for building LLM-powered applications, RAG pipelines, chatbots, agents, and workflows; without deep ML expertise. Self-hostable or cloud, with 154,000+ GitHub stars.

Key Capabilities

Drag-and-drop workflow builder for LLM pipelines

Built-in RAG engine: index PDFs, web pages, or databases

Agent mode with tool calling and memory management

100+ model integrations: OpenAI, Anthropic, open-source LLMs

154,000+ GitHub stars, production-ready agentic workflow platform

One-click deploy to cloud or self-host with Docker

Standout Features

Visual Workflow Builder

Drag-and-drop interface to build complex LLM pipelines with conditions, loops, and branching

Built-in RAG Engine

Index documents, websites, or databases and query them with semantic search in your app

100+ Model Integrations

Switch between OpenAI, Claude, Gemini, Mistral, or any local model without changing code

Perfect for

AI Product Builders
Backend Developers
Enterprise AI Teams
Self-Hosters

Pricing Plans

How much does Dify cost?

Sandbox

$0

per month

  • 200 message credits
  • 5 apps
  • 50 knowledge documents
  • 50MB storage
  • 1 team member
  • 30-day log history
  • API rate limit 5,000/month
Most Popular

Professional

$59

per month

  • 5,000 message credits/mo
  • 50 apps
  • 500 knowledge documents
  • 5GB storage
  • 3 team members
  • Unlimited log history

$590/year billed annually saves 17%

Team

$159

per month

  • 10,000 message credits/mo
  • 200 apps
  • 1,000 knowledge documents
  • 20GB storage
  • 50 team members

$1,590/year billed annually saves 17%

Community (Self-Hosted)

$0
  • All core features from the public repository
  • Single workspace
  • Deploy with Docker on your own infrastructure
  • Open-source license compliance required (Apache-2.0-based with additional conditions)

Compare Dify

Community Buzz

Similar Tools to Dify

Flowise logo

Flowise

Open-source drag-and-drop tool for building LLM flows and AI agents using LangChain and LlamaIndex nodes. Now sunset: the team announced in July 2026 it is winding down, the repository is archived read-only on GitHub, and official support ended 31 August 2026. The Apache 2.0 code can still be forked and self-hosted, but treat it as frozen software with no security patches coming.

free
DeepSeek Harness logo

DeepSeek Harness

MIT-licensed agent harness from DeepSeek AI, built on the idea that everything is a plugin: models, tools, skills, sessions, sandboxes, storage, loops, scheduling and the UI can each be swapped in configuration without touching the source. Start it with one command and it opens a local Web UI at 127.0.0.1:3080, with an append-only trajectory log you can resume, fork, search and replay. Read the trade-off before installing: DeepSeek calls it a developer preview, warns there will be compatibility-breaking changes, and states plainly that it has had no security audit and must not be treated as production-ready.

free
OmniRoute logo

OmniRoute

Self-hosted, MIT-licensed AI gateway that puts one OpenAI-compatible endpoint in front of a large multi-provider model catalog. Point Claude Code, Codex, Cursor, Cline, or Copilot at localhost:20128/v1 and it auto-falls back to the next provider when a quota runs out, stacks free tiers, and compresses tokens. Local-first: keys and history stay in SQLite on your machine, no telemetry, no account. Note the trade-offs: provider counts drift between official pages, and draining stacked free tiers can conflict with some upstream providers' terms.

free
OpenClaw logo

OpenClaw

Free, open-source personal AI assistant by Peter Steinberger that runs on your machine and performs real tasks autonomously. Talk to it from WhatsApp, Telegram, iMessage, Discord, Slack, or Signal. One-liner install, persistent local memory, ClawHub skills marketplace, sandbox or full system access, and support for Claude, OpenAI, DeepSeek, Qwen, or local LLMs via Ollama. 247K GitHub stars by March 2026; Steinberger joined OpenAI on February 14, 2026 with a non-profit foundation taking project stewardship.

freemium · $6+
Continue.dev logo

Continue.dev

Open-source CLI tool for Continuous AI that runs async agents on pull requests to enforce team rules, catch issues, and accelerate software shipping.

free
OpenHands logo

OpenHands

Open-source AI software engineering agent (formerly OpenDevin) that browses the web, writes and executes code, runs bash commands, and resolves GitHub issues autonomously. Backed by All Hands AI and supported by 55k+ GitHub stars.

free
Rather have someone build it with Dify for you?

Browse vetted vibe coding agencies for MVP builds, cleanups, and audits.

// start building today

ready to try dify?

go to the official site and judge Dify yourself.

try dify now
Explore options

Dify Alternatives

See how Dify compares to similar tools.