langgenius /dify
Build Agentic workflows, RAG pipelines, with rich AI model and tool support on one collaborative workspace. Deploy on cloud, VPC, or self-hosted, so teams move from prototype to production without rebuilding the stack.
★ 161,207⑂ 25,505👁 838⑃ 21,265● 19,898▤ 172
+50
Daily
+472
Weekly
161,207
stars
25,505
forks
838
watchers
21,265
prs
19,898
issues
172
releases
README
!cover-v5-optimized
Dify Cloud ·
Self-hosting ·
Documentation ·
Dify edition overview
Dify is an open-source LLM app development platform. Its intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features (including Opik, Langfuse, and Arize Phoenix) and more, letting you quickly go from prototype to production. Here's a list of the core features:
Quick start
Before installing Dify, make sure your machine meets the following minimum system requirements:
- CPU = 2 Core
- RAM = 4 GiB
The easiest way to start the Dify server is through Docker Compose. Install Docker with a running daemon, Docker Compose v2.35.0 or later, and OpenSSL.
For a new deployment, run the following commands from the repository root. For an existing deployment, preserve your .env and follow the upgrade guidance.
bash
cd docker
cp .env.example .env
openssl rand -hex 32
Open .env and set DIFY_AGENT_LOCAL_SANDBOX_AUTH_TOKEN to the generated value. Keep the default COMPOSE_PROFILES value for the bundled services. Service defaults load automatically; no additional configuration files are required.
From the same docker directory, start the services:
bash
docker compose up -d
docker compose ps --all
Once the services are running, open http://localhost/install to complete the initial setup. The one-time init_permissions service is expected to exit with code 0.
For optional settings and service overrides, see the Docker deployment guide.
Seeking help
Please refer to our FAQ if you encounter problems setting up Dify. Reach out to the community and us if you are still having issues.
If you'd like to contribute to Dify or do additional development, refer to our guide to deploying from source code
Key features
1. Workflow:
Build and test powerful AI workflows on a visual canvas, leveraging all the following features and beyond.
2. Comprehensive model support:
Seamless integration with hundreds of proprietary / open-source LLMs from dozens of inference providers and self-hosted solutions, covering GPT, Mistral, Llama3, and any OpenAI API-compatible models. A full list of supported model providers can be found here.
!providers-v5
3. Prompt IDE:
Intuitive interface for crafting prompts, comparing model performance, and adding additional features such as text-to-speech to a chat-based app.
4. RAG Pipeline:
Extensive RAG capabilities that cover everything from document ingestion to retrieval, with out-of-box support for text extraction from PDFs, PPTs, and other common document formats.
5. Agent: Autonomous agents with a sandbox of their own: they run commands, install software, and handle files to get open-ended tasks done. Describe the agent you want and itTop issues
#24645[Chore/Refactor] remove redundant-cast22 comments · 2025-08-27#33092[Refactor/Chore] replace json.load by pydantic20 comments · 2026-03-06#30269the roadmap for adapt to modern tech for backend18 comments · 2025-12-28#32679Qwen3.5 reasoning content display11 comments · 2026-02-27#40680Keyword search silently returns no results for parent-child chunks13 comments · 2026-08-13#40874v1.16 Agent mode: uploaded files not displayed in UI and file variables invalid in build12 comments · 2026-08-17#40773Model provider plugin migration error11 comments · 2026-08-14#31096AppModelConfig has so many nullable fields12 comments · 2026-01-16
Discussions
#46199Chopper: a small open model that cuts only the needed sentences out of retrieved text0 comments · 2026-11-12#46142Dify SSRF Proxy Causes High Memory Usage on ARM64 – Squid 6.13 Fails with RLIMIT_NOFILE: Operation not permitted1 comments · 2026-11-12#45755dify1.18.1, calling the https://api.dify.ai/v1/datasets/{dataset_id}/document/create-by-file API throws an error.2 comments · 2026-11-07#45739Can't dify be deployed through Kubernetes?1 comments · 2026-11-06#45704In version 1.18.1, when calling the https://api.dify.ai/v1/workflows/{workflow_id}/run API, I found that the file parameter gives an error. What could be causing this? Because the same parameter format worked fine in version 1.13.3.4 comments · 2026-11-06#45678Show and tell: an HTTP Request node that checks a workflow's draft before anyone sends it0 comments · 2026-11-05#45592In Didy1.13.3, when searching the knowledge base, it seems like metadata filtering isn't working.1 comments · 2026-11-05#45582How do you prove an AI agent's output today is the output that passed your checks?1 comments · 2026-11-04
Latest release
v1.19.0 - Trace Your Workflows, Layer by Layer 1.19.0 2026-11-04Dify 1.19.0 brings nested workflow tracing to your observability tools. Follow a workflow into the Workflow Tools it calls, inspect the steps inside each invocation, and keep the LLM context alongside the execution tree. This release also makes Workflow Tools portable with App packages, adds Skill Hub automation, and makes Agent files easier to upload and preview. The bundled plugin daemon is upgraded to 0.6.14-local. Release highlights · Upgrade guide · Detailed changes Release highlights Nested workflow tracing See what happens inside a Workflow Tool, all the way down to
相关报道 (6)
News & coverage (19)
Hacker NewsDify, a visual workflow to build/test LLM applications▲ 185 · 38 comments · 2024-04-22Hacker NewsDify 1.0▲ 2 · 0 comments · 2025-03-01Hacker NewsDify, an end-to-end, visualized workflow to build/test LLM applications▲ 2 · 0 comments · 2024-04-22Hacker NewsDify: Production-ready platform for agentic workflow development▲ 1 · 0 comments · 2026-03-09Hacker NewsDify's Open Source License▲ 1 · 1 comments · 2025-03-26Hacker NewsDify 1.0: Plugins, Marketplace, a New Agent Node, Optimized RAG and Memory▲ 1 · 0 comments · 2025-03-03noteHow Dify Experience is Viewed in Projects | The Work of Building Generative AI Apps with Low-Code and the Required Experience2026-11-01note[Generative AI Practical Guide] Gemini's Mobile Breakthrough and EU Regulations, Dify x Corporate Workflows, and the Future of Business Transformed by NVIDIA's New Models2026-10-17XDA Developersn8n, Dify, and Ollama might be the best self-hosted AI automation stack right now2026-04-13theaiinsiderDify Secures $30M Series Pre-A to Power Enterprise-Grade Agentic Workflows2026-03-10