Automation
n8n
Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+…
★ 206.6k starsCustom (check repo)
View guide →LibreAI / RAG & Knowledge / Dify
// rag · langgenius/dify
Dify
Dify is an open-source rag & knowledge project by langgenius (langgenius/dify on GitHub). It has 157,773 GitHub stars and 24,895 forks, is released under the Custom (check repo) license, and was last updated on GitHub on 3 October 2026.
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or…
★ 157.8k stars⑂ 24.9k forksCustom (check repo)updated 2026-10
▦ visual — this project's README ships no embeddable screenshot,
so here's a placeholder. The guide below is complete regardless.
so here's a placeholder. The guide below is complete regardless.
// project facts
Project facts
- Repository
- langgenius/dify
- GitHub stars
- 157,773
- Forks
- 24,895
- License
- Custom (check repo)
- Last updated on GitHub
- 3 October 2026
- Category
- RAG & Knowledge
- Listing
- Full install guide
- Official site
- Official site
// how it works
How it works
- Connect your apps
Link the services you already use — chat, email, sheets, CRMs, databases — through built-in integrations or generic webhooks and API calls.
- Build the flow visually
Drag triggers and actions onto a canvas: when this happens, do that. Branch on conditions, loop over items, and transform data between steps.
- Add AI where it helps
Pipe steps through language models for classification, extraction, summarising, or drafting — most platforms here treat AI as just another node.
- Deploy and monitor
Turn the workflow on, watch executions in the run history, and get alerted when something fails.
// features
Why people love it
Visual workflow builder
Design automations on a canvas instead of writing glue code for every integration.
Hundreds of integrations
Prebuilt connectors for popular apps plus HTTP, webhooks, and database nodes for everything else.
Self-hosted & private
Your credentials and execution data stay on your infrastructure — no third-party middleman.
AI-native steps
Call LLMs mid-workflow for decisions, extraction, and content generation.
Scheduling & triggers
Cron schedules, webhooks, and event triggers keep flows running around the clock.
No per-run pricing
Open-source means the automation itself is free; you only pay for your own server.
Advertisement
// run it
Run it yourself
- Step 1 — Clone the repo
Download the source and move into the project folder.
git clone https://github.com/langgenius/dify.git cd dify - Step 2 — Install dependencies
Use the package manager the project specifies (check for pnpm or yarn lockfiles).
npm install - Step 3 — Start it
Launch the dev server or build, per the README.
npm run dev
// use cases
What you can build
- Sync data between apps without manual copy-paste.
- Turn form submissions into tickets, rows, and notifications.
- Build AI triage for inboxes and support queues.
- Schedule reports, backups, and social posts.
Also on this shelf: ai-dev-tools-zoomcamp — free hands-on course on using AI dev tools without losing engineering discipline. The Automation shelf also holds rpaframework — open-source RPA libraries for automating browsers, documents, and desktops. Readers working through the Automation shelf also stop at x-tweet-fetcher, Fetch X tweets, replies, and timelines with no login or API keys required.
Advertisement
// faq
Questions, answered
Is it really free?
The core software is open-source and free to self-host. Managed cloud versions exist for most of these if you would rather not run a server.
Do I need to code?
Most flows are built visually. Light expressions or code nodes help for advanced logic, but simple automations need none.
Who maintains Dify?
It is an open-source project at langgenius/dify with 24,895 forks. Check the repo's contributors and recent commits to see how active maintenance is.
How does it compare to Zapier?
Same idea — triggers and actions across apps — but self-hosted, with AI steps first-class and no per-task pricing.
What do I need to run it?
Typically Docker and a small VPS or home server; several offer one-command installs.
Can it call AI models?
Yes — LLM nodes are standard, working with hosted APIs or your own local models.
// keep exploring
Similar tools
Automation
Automatisch
The open source Zapier alternative. Build workflow automation without spending time and money
★ 14.0k starsCustom (check repo)
View guide →Automation
Activepieces
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI…
★ 24.9k starsCustom (check repo)
View guide →RAG & Knowledge
txtai
All-in-one AI framework for semantic search, LLM orchestration and language model workflows.
★ 13.0k starsApache-2.0
View guide →RAG & Knowledge
MinerU
MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms
★ 82.5k starsApache-2.0 + terms
View guide →RAG & Knowledge
llm-app
Ready-to-run templates for RAG, AI pipelines and enterprise search that stay in sync with live data
★ 58.8k starsMIT
View guide →// alternatives
Alternatives in RAG & Knowledge
The most-starred other RAG & Knowledge projects in the LibreAI catalogue — the realistic shortlist if Dify is not the right fit.
- MarkItDown★ 193.5k
MarkItDown — Microsoft tool that converts PDFs, Office files, images and more to clean Markdown for LLMs, MIT
- ragflow★ 91.6k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context…
- PaddleOCR★ 90.8k
Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages
- MinerU★ 82.5k
MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms
- anything-llm★ 66.7k
Stop renting your intelligence. Own it with AnythingLLM. Everything you need for a powerful local-first agent experience
// more in rag
More in RAG & Knowledge
Nearby RAG & Knowledge projects in the catalogue, closest in stars to Dify — keep exploring the shelf either side of it.
- MarkItDown★ 193.5k
MarkItDown — Microsoft tool that converts PDFs, Office files, images and more to clean Markdown for LLMs, MIT
- ragflow★ 91.6k
RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context…
- docuchat.app★ 35
Private document chat for attorneys: local LLMs, verifiable citations.
- PaddleOCR★ 90.8k
Lightweight OCR toolkit turning PDFs and images into structured, LLM-ready data in 100+ languages
- InsightPDF★ 49
Chat with PDFs and see exactly where each answer was found.
- MinerU★ 82.5k
MinerU — turns PDFs and Office documents into LLM-ready Markdown and JSON for agents and RAG pipelines, Apache-2.0 plus terms
Get Dify
Free and open — grab the source, star the repo, and start creating.