Dify
App in the BluixApps catalog
What it is
Dify is an open-source LLM application development platform — visual workflow builder, RAG pipelines, prompt engineering, agent system, model management, monitoring. The "platform" layer for building AI applications: chatbots, agents, copilots, RAG apps.
Where Flowise/Langflow are LangChain-visual, Dify is platform-first with broader scope.
What it's for
- LLM app development — visual workflows for AI products
- RAG over your docs — full RAG pipeline visual builder
- Agent systems — define agents with tools + memory
- Chatbot deployment — embed AI apps on marketing sites
- API exposure — every flow becomes a REST endpoint
Who it's for
- AI engineering teams building LLM products at scale
- Product teams wanting visual AI workflow design
- Indie SaaS founders shipping AI features without writing chains
- Agencies delivering AI products to clients faster
- Enterprises standardizing AI workflow tooling
Why teams pick Dify over alternatives
- Apache 2.0 — fully open
- Platform-grade — beyond pure LangChain visualization
- Multi-tenant — workspaces + apps + members
- Strong RAG — document ingestion + chunking + retrieval built in
- Active development — backed by LangGenius
- Plugin marketplace — extend with tools
Integrations
- LLM providers — OpenAI, Anthropic, Google, Ollama, Mistral, Cohere, AWS Bedrock, 40+ more
- Vector stores — Weaviate (built-in), Qdrant, Milvus, pgvector, Pinecone
- Document loaders — PDF, DOCX, Markdown, HTML, web URLs, Notion, Confluence
- Tools — web search, code interpreter, custom HTTP, MCP servers
- Auth — local + OAuth (Google, GitHub, custom OIDC) + SAML
- API — REST + WebSocket for chat
- Embedded chatbots —
<script>tag for marketing sites
Notable users & community
- 60k+ GitHub stars
- Used by enterprises building internal AI tools
- Backed by LangGenius with sustainable commercial cloud
- Active Discord community
- Featured in LLM platform comparisons
Tips & operations
- Heavy stack — 10+ containers, 4 GB RAM minimum, 8+ recommended
- First-run wait — services take 5-10 min to fully boot
- Persistent storage critical — vectors + chats + workspace config
- Workspace isolation — multi-team setups need careful permission design
- API rate limit — Dify exposes API endpoints; rate-limit at proxy
- Backup is multi-volume — Postgres + Weaviate + uploads + sandbox
What we ship in BluixApps
- Official Dify docker-compose (10+ services)
- Auto-generated SECRET_KEY
- Console + API on port 8086 (mapped from nginx 80)
- Persistent volumes for all stateful services
- Pre-configured to detect Ollama on same VPS for local LLM
- Compose at
/opt/dify/repo/docker/docker-compose.yaml - Backup hook covers Postgres + Weaviate + uploads
Get this app — pick a BluixApps plan
Same catalog. Scaling tenant isolation, white-label and support tier.
| Tier | Tenants | Catalog | Support | White-label | Monthly | |
|---|---|---|---|---|---|---|
| Stacks | 1 | 19 curated stacks | Standard | — | $19/mo | DetailDeploy |
| Starter | 10 | Full catalog | Standard | +$15–25/mo | $49/mo | DetailDeploy |
| Pro | 25 | Full catalog | Priority bugfix | +$15–25/mo | $149/mo | DetailDeploy |
| Growth | 100 | Full catalog | Priority bugfix | +$15–25/mo | $349/mo | DetailDeploy |
| Scale | 500 | Full catalog | 7-day window | +$15–25/mo | $799/mo | DetailDeploy |
| Enterprise | Unlimited | Full catalog | Priority 7-day | Bundled | $1,499/mo | DetailDeploy |
