Dify
Also known as: LangGenius
Dify is an open source LLM app development platform for building agents, chatbots and workflows.
Dify is an open-source platform for building LLM applications. It brings model access, prompt engineering, retrieval, agent logic and monitoring together in a single self-hostable environment with a web interface, so teams can go from prototype to production without writing the underlying orchestration plumbing.
At its center is a visual workflow builder where you assemble multi-step AI applications on a canvas, combining language models, web search, code execution, and your own APIs with branching logic. Alongside it sits a Prompt IDE for crafting and comparing prompts across models, and a built-in RAG pipeline that handles the whole retrieval flow.
It ingests documents such as PDFs and slides, chunks and embeds them, stores them in a vector database, and retrieves and reranks the right context at query time. Knowledge is its own product surface, where teams configure chunking and indexing, test retrieval hits, build custom Knowledge Pipelines, or point Dify at an existing RAG service through the External Knowledge API.
Dify is model agnostic. It connects to hundreds of proprietary and open-source models across many inference providers, from commercial APIs to locally hosted models, and lets you switch the model behind an application without changing code. Its agent capabilities let you define agents using function calling or a reasoning-and-acting loop, equip them with dozens of built-in tools or your own, and connect external tools through the Model Context Protocol, with the option to turn a finished Dify workflow into an MCP server itself.
Rounding out the platform are LLMOps features for monitoring logs and performance and improving prompts and datasets from real usage, native integrations with observability tools, and a backend-as-a-service layer that exposes every app as an API for embedding into existing software. Dify runs as a managed cloud service, as a dedicated single tenant cluster, in the customer's own AWS, GCP or Azure VPC, or self hosted and air gapped for full data control.
Vendor details
Canonical URL
https://dify.ai
Category
Agent builder
Subcategory
Open-source visual LLM app and agentic workflow platform (Workflow Studio, Knowledge Pipeline, Marketplace)
Company status
independent
Use cases & customers
Primary use cases
Target customers
Deployment options
Integrations
Integrations connect Dify to model providers, tools, data sources and external services, installed as plugins from a public marketplace typed across Models, Tools, Data Sources, Triggers, Agent Strategies, Extensions and Bundles. In-workflow surfaces are a Tool node, an HTTP Request node for arbitrary APIs, MCP tools, Custom Endpoints, an External Data Tool extension and a Sensitive Content Moderation endpoint. Hosted models on Dify credits are OpenAI, Anthropic, Gemini, xAI and Tongyi, and customers can connect their own provider accounts and keys or, in air-gapped deployments, locally deployed models. Knowledge ingestion covers local file upload, Notion sync and website crawl, plus an External Knowledge API specification for pointing Dify at an existing RAG service. Outbound, a published workflow is exposed as a hosted web app, an iframe or chat-widget embed, a REST API with a published OpenAPI specification, the difyctl CLI, or an MCP server consumable by Claude Desktop and Cursor. Traces stream to Langfuse, LangSmith, Opik, W&B Weave, Arize, Phoenix and Alibaba Cloud ARMS over OpenTelemetry.
In practice
You want a support chatbot grounded in your own documentation without assembling a RAG stack yourself. Dify's built-in Knowledge pipeline ingests, chunks, embeds, and retrieves your docs, and you wire it into a workflow visually.
Your team is stitching together model access, prompts, retrieval, and monitoring from separate tools. Dify combines workflow building, a Prompt IDE, RAG, agents, and observability in one self-hostable platform from prototype to production.
You need to keep data on your own infrastructure and stay free to switch models. Dify is open source and self-hostable, connects to hundreds of commercial and local models, and exposes every app as an API.
Sources & related URLs
Related / legacy domains
Research sources
Agentic Index coverage score
12.0 / 14 capabilities · 86%
| Integrations & Tool Calling | Full |
|---|---|
|
Integrations connect Dify to model providers, tools, data sources and external services through a Tool node, a Dify Tools management surface, an HTTP Request node for arbitrary APIs, MCP tools, Custom Endpoints, an External Data Tool extension and a public marketplace of installable plugins typed across Models, Tools, Data Sources, Triggers, Agent Strategies, Extensions and Bundles. Agent nodes invoke tools autonomously with per-parameter control over whether values are model-generated or fixed at configuration time. Sourcedocs.dify.ai integrations and node reference, marketplace.dify.airead 2026-08-31 |
|
| Workflow Orchestration | Full |
|
Workflow and Chatflow share one node library and execution model, with If-Else branching, Iteration over arrays, Loop with progressive refinement, Question Classifier routing, Variable Aggregator convergence, Parameter Extractor, sandboxed Code execution, and Orchestration Logic covering how nodes are arranged, nested or reused. Agent nodes run a reasoning-and-tool loop as a step inside a larger flow with a configurable iteration ceiling, a published workflow can be called as a tool by another workflow or exposed as an MCP server, and version control plus Snippets support reuse across flows. Sourcedocs.dify.ai workflow, node and version-control referencesread 2026-08-31 |
|
| Knowledge Grounding & RAG | Full |
|
Knowledge is a product surface of its own. Knowledge bases come ready to use, with configurable chunking, cleaning and indexing method, and a custom Knowledge Pipeline can be built and published as its own orchestrated flow. Content comes in from local files, Notion sync and website crawl, with document metadata management, a Knowledge Retrieval node, a retrieval hit-testing tool, and an External Knowledge API specification for pointing Dify at a customer's existing RAG service. Storage and request-rate quotas are metered per tier. Sourcedocs.dify.ai knowledge tree and dify.ai/pricingread 2026-08-31 |
|
| Human Oversight & Guardrails | Full |
|
Human Input is a workflow node that pauses the workflow to request human input. In Workflow Studio, before actions that affect sensitive data, access or policy, the run pauses and a person can approve, edit, comment on or forward it before it continues, with timeout handling. A Sensitive Content Moderation endpoint extension is a separate guardrail, and workspace member roles govern who can act. Sourcedocs.dify.ai node reference and dify.ai/workflowsread 2026-08-31 |
|
| Security, Identity & Governance | Full |
|
Dify holds SOC 2 Type I and Type II and ISO 27001:2022, with the ISO assessment by auditing firm Johanson, complies with GDPR, and releases its reports to paid customers on request through security@dify.ai. A trust center at security.dify.ai has a subprocessors page, and Dify publishes a signed Data Protection Agreement PDF alongside its privacy policy, terms and marketplace agreement. Customers get SSO via SAML/OIDC, fine-grained RBAC down to workflow level, SCIM provisioning, session policies, tamper-evident audit logs streamed to the customer's SIEM, PII-redacted prompt history and bring-your-own-key encryption, and SSO and the enterprise control set come only on the Enterprise tier. Sourcedocs.dify.ai/en/policies/agreement/get-compliance-report, dify.ai/dify-enterprise and security.dify.airead 2026-08-31 |
|
| Observability & Auditability | Full |
|
A built-in analytics dashboard covers performance, cost and engagement, and conversation and run logs carry stated retention, with downloadable archived workflow logs, a Run History view, a Variable Inspector for intermediate values, and typed error metadata per node. Traces stream over OpenTelemetry to seven named external stacks, Langfuse, LangSmith, Opik, W&B Weave, Arize, Phoenix and Alibaba Cloud ARMS. Enterprise adds tamper-evident audit logs streamed to the customer's SIEM, per-call traces and PII-redacted prompt history. Sourcedocs.dify.ai monitor tree and dify.ai/dify-enterpriseread 2026-08-31 |
|
| Memory & State Persistence | Partial |
|
State persists within a conversation but not across them. A Variable Assigner node manages persistent conversation variables in Chatflow applications, Chat Web Apps keep persistent history, and the Agent node has a Memory toggle with a configurable window size, implemented as a token buffer over recent messages. Log history is retained and browsable per tier, 30 days on Sandbox and unlimited on the paid plans, and workflow runs can be inspected after the fact. Dify offers no memory that carries across sessions or learns over time. Sourcedocs.dify.ai node reference and dify.ai/pricingread 2026-08-31 |
|
| Deployment & Data Residency | Full |
|
Dify runs as hosted Dify Cloud, as a Dify-managed single-tenant dedicated cluster in the customer's region, as a customer-managed deployment into the customer's own AWS, GCP or Azure VPC through a Helm chart or Terraform modules, or fully air-gapped on-prem with locally deployed models and no egress. The open-source Community Edition self-deploys with Docker Compose and has its own 277-page self-hosting guide. Data stays inside the customer's VPC, region and perimeter, with bring-your-own-key encryption and multi-tenant isolation offering tenant-level quotas and access policies. Sourcedify.ai/dify-enterprise and docs.dify.ai self-host treeread 2026-08-31 |
|
| Prebuilt Agents, Templates & Packs | Full |
|
Dify Marketplace carries a named templates catalog of ready-to-use workflows that open in Dify with one click, filterable by Marketing, Sales, Support, Operations, IT and Knowledge and by partner, with entries such as Daily AI News Digest by langgenius, Competitive Landscape Intelligence, AI Technical Research Assistant and a Qdrant upsert on a Google Drive trigger, each showing its publisher and usage count, alongside a plugin catalog typed across Models, Tools, Data Sources, Triggers, Agent Strategies, Extensions and Bundles and a Creator Center. Customers can publish their own apps through Publish Apps to Marketplace, workflows export and import as DSL, and Snippets reuse groups of nodes. Sourcemarketplace.dify.ai/templates and docs.dify.ai publish-to-marketplaceread 2026-09-29 |
|
| Triggers & Channel Coverage | Full |
|
A dedicated Trigger family has three members, Schedule Trigger, Integration (plugin) Trigger and Webhook Trigger, and the Start node sets whether a workflow begins on demand or automatically from a user message, API call, scheduled trigger, webhook, plugin event or uploaded payload. On the output side, channels are a hosted web app, an iframe or chat-widget embed, the REST API, the difyctl CLI and a published MCP server. Trigger Events are metered on every tier, 3,000 on Sandbox with a cap of two triggers per workflow and 20,000 a month on Professional with unlimited triggers per workflow. Sourcedocs.dify.ai node reference, dify.ai/workflows and dify.ai/pricingread 2026-08-31 |
|
| Model Flexibility & Routing | Full |
|
Model Providers lets the customer either spend Dify credits on hosted models or connect its own provider accounts and API keys, and the LLM node selects the model per node, so different steps of one workflow can run on different models. OpenAI, Anthropic, Gemini, xAI and Tongyi are available on credits, and once credits run out the customer switches to its own key. Model providers install as marketplace plugins, and air-gapped deployments connect locally deployed models. Sourcedocs.dify.ai model-providers, dify.ai/pricing and dify.ai/dify-enterpriseread 2026-08-31 |
|
| APIs, SDKs & MCP Extensibility | Full |
|
A REST API with a published OpenAPI specification integrates Dify applications into the customer's own product, with app credentials, streamed responses and session management. The difyctl CLI runs Dify apps from terminals, scripts, CI and other AI agents, and a plugin development kit lets third parties build tools, models and integrations. Published workflows are exposed as MCP servers that Claude Desktop, Cursor and other MCP clients can use, inbound webhooks, custom endpoints and an External Knowledge API specification round out the options, and the whole platform is open source on GitHub. Sourcedocs.dify.ai API reference and CLI overview, dify.ai/workflowsread 2026-08-31 |
|
| Testing, Debugging & Optimization | Partial |
|
Customers can run a single node or the whole flow against sample input, inspect intermediate variable values before real traffic arrives, review run history, read typed error metadata and configure predefined error-handling logic so nodes stop, return defaults or route to a recovery branch. Knowledge retrieval has its own hit-testing tool, an Annotation System curates approved answers with a quota per tier, and version control restores any published build. Dify offers no evaluation, scoring, regression suite or benchmarking product. Sourcedocs.dify.ai debug tree, knowledge test-retrieval and version-control referencesread 2026-08-31 |
|
| Browser & Computer Use | Not documented |
|
The node library has no browser, desktop or computer-use node. An Import Data from Website crawl feeds the knowledge base, and a tutorial scrapes a public profile through a third-party crawling tool. Both reach content over HTTP. Dify acts on external systems through APIs, HTTP requests, MCP tools and installed plugins. Sourcedocs.dify.ai node reference and knowledge import treeread 2026-08-31 |
|
The Agentic Index coverage score grades every vendor Full, Partial or Not documented against the same 14 buyer facing capabilities, from public evidence only. Each capability links to how all vendors in the index score on it. How this evidence is graded
Product updates
Dify 1.18.0 adds Output Routes, so an Agent node can choose which workflow branch runs next based on a selection condition set for each route. Plain Agent v2 nodes now stream text as it is generated. Workflow Tools called from a workflow run as child graphs that pause, resume and stop together, and their steps can be opened from run history.
Bears on: Agent capability
View sourceDify launched New Agent, which allows agents to operate as standalone and independent applications. These agents can also be utilized as reusable resources within larger workflows.
Bears on: Agent capability
View sourceDify introduced new agent features including an E2B Sandbox for secure code execution, Home Snapshots, and Skill Management. These updates expand the execution environment and tool orchestration capabilities for agents.
Bears on: Agent capability
View sourcePricing
From $59 a month on Professional, or $590 per workspace a year. Sandbox is a free demo, and the Community Edition is free to self host.
A flat fee per workspace for each tier, billed monthly or yearly, with a monthly allowance of message credits that meter calls to Dify hosted models. Connecting your own model API key bypasses the credits.
Included quota
Sandbox is free with 200 message credits stated without a monthly qualifier, 1 workspace, 1 member, 5 apps, 50 knowledge documents, 50MB knowledge storage, 10 knowledge requests a minute, standard document processing, 3,000 trigger events, up to 2 triggers per workflow, standard workflow execution, 10 annotations, 30 days of log history and 5,000 API calls a month. Professional, at $590 per workspace a year, includes 5,000 message credits a month, 1 workspace, 3 members, 50 apps, 500 documents, 5GB storage, 100 knowledge requests a minute, priority document processing, 20,000 trigger events a month, unlimited triggers per workflow, faster workflow execution, 2,000 annotations, unlimited log history and no Dify API rate limit. Team, at $1,590 per workspace a year, includes 10,000 credits a month, 1 workspace, 50 members, 200 apps, 1,000 documents, 20GB storage, 1,000 knowledge requests a minute, top priority document processing, unlimited trigger events, unlimited triggers per workflow, priority workflow execution, 5,000 annotations, unlimited log history and no API rate limit. Enterprise is custom, with scalable deployment, commercial license authorization, multiple workspaces and enterprise management, SSO, negotiated SLAs, advanced security and controls, official updates and maintenance, and professional support. Community is free, with all core features in the public repository and a single workspace, subject to the Dify open source license.
What is public
Dify, by LangGenius, publishes four cloud tiers metered by message credits, plus a free self hosted Community Edition. Sandbox is free with 200 message credits, 1 member, 5 apps and 50 knowledge documents. Professional is $590 a year per workspace with 5,000 credits a month, 3 members and 50 apps, and the stated 17% annual saving puts its monthly list at about $59. Team is $1,590 a year with 10,000 credits a month, 50 members and 200 apps, about $159 a month on monthly billing. Enterprise is custom and carries SSO and the enterprise security controls. Customers can bring their own model provider keys and pay the provider directly.
Billing mechanics
Fixed cloud tiers with included message credits. A credit is one model call on a Dify hosted model, and consumption varies by model type. Connecting your own API key bypasses the credit system, so the subscription then covers only the platform. Tiers also differ by members, apps, knowledge storage and documents, and rate limits, and annual billing saves about 17%.
Cost watchouts
Sandbox's 200 message credits carry no monthly qualifier and read as one time, so it is a demo rather than a free production tier. Message credits meter model calls, not user messages, and are consumed at different rates by model type. LLM inference is never included in the platform fee. It is paid either in credits or to the provider directly under BYOK, and it is often the largest line. SSO is Enterprise only, so single sign on is not part of the $1,590 a year Team tier and goes through a sales conversation. Trigger events are a metered quota, so scheduled and webhook driven automation consumes plan capacity independently of message credits. The modified Apache 2.0 license bans multitenant resale, so embedding self hosted Dify in a SaaS product requires a commercial license from LangGenius.
Variable cost rationale
The platform fee is a flat price per workspace tier. Model calls on Dify hosted models draw down the tier's monthly message credits at different rates by model type, so the bill grows with call volume and with the models chosen. Trigger events are a separate metered quota for scheduled and webhook driven automation. When the credits run out, the workspace moves up a tier or connects its own model API key. With its own key the customer pays the model provider directly, outside Dify's fee and outside any Dify limit. The self hosted Community Edition has no credit system, so its cost is the hosting and the model provider bills.
Additional watchouts
Under the modified Apache 2.0 terms, running self hosted Dify as a customer facing multitenant SaaS needs a commercial license from LangGenius. Sandbox's 200 credits carry no monthly qualifier, so it works as a trial rather than a production tier. Credit use varies by model, self hosting is free but carries Docker, operations and monitoring overhead, and model costs paid to providers can exceed the platform fee.
Overage / add-ons
When monthly credits run out, the workspace upgrades a tier or connects its own LLM API key (BYOK), which bypasses credits entirely and is paid to the provider directly. Professional resources (vector storage, seats) can be topped up independently. The self hosted Community Edition has no credit system at all. Enterprise is custom.
Sales call required
Mixed (some tiers require a call)
Free / trial
Free Sandbox plan with 200 message credits, and a free self hosted Community Edition
Lowest paid plan
Professional at $590 per workspace a year ($49.17 a month), or about $59 a month billed monthly
Commercial notes
Dify is open source on GitHub with a large community (about 139K GitHub stars) and more than 1M deployed apps, combining a visual workflow builder, RAG, an agent framework, model management and observability as a backend as a service. The Community Edition uses a modified Apache 2.0 license that restricts multitenant commercial self hosting.
Key ambiguities
SSO comes only with Enterprise. Sandbox's 200 message credits are stated with no monthly qualifier while paid tiers read per month, which suggests a one time allowance but is not stated outright. Enterprise has no public figure. Credit rates per action beyond the statement that consumption varies by model type are not published, and the $59 and $159 monthly figures are inferred from the stated 17% annual saving.
Cancellation / refund
Professional and Team are self serve, billed monthly or annually, and annual billing saves 17%. Enterprise is a custom contract, and no refund or cancellation terms are published.
Support SLA / resale
Sandbox and self hosted users get community support, and Professional and Team get priority processing and execution. Enterprise adds SLAs negotiated through Dify partners, official updates and maintenance, professional support, a dedicated CSM, a Slack Connect channel, a one hour Sev 1 response and quarterly business reviews. Multitenant resale of self hosted Dify needs a commercial license from LangGenius.
Missing data
Whether Sandbox credits renew monthly is not stated. Enterprise pricing is custom, with no public figure. Credit rates per action by model are not published.
Related vendors
- Lindy — Lindy is an AI teammate that lives in Slack, answers from your tools…
- Activepieces — Open source, MIT licensed automation platform where every one of 700…
- Agenta — Agenta is an open source workspace where teams build AI agents by…
- AgentX — No code platform to build, evaluate, and deploy multi agent…
- AI Library — No code platform for building and running AI agents, with a…
- Aigensei — Enterprise agentic workflow platform that runs business processes…
Alternatives to Dify
The closest documented capability profiles to Dify among agent builders tracked by Agentic Index, ordered by similarity on the same 14 point evidence the rankings use. No vendor pays for placement.
- LuMay12.0 / 14Matches Dify across all 14 documented capabilities
- Activepieces11.5 / 14A lighter documented profile than Dify
- Budibase11.5 / 14A lighter documented profile than Dify
- Elastic11.5 / 14A lighter documented profile than Dify
- Mendix12.5 / 14Fuller documented coverage on Testing, Debugging & Optimization
- OutSystems12.5 / 14Fuller documented coverage on Testing, Debugging & Optimization
Similarity is computed from each vendor's Agentic Index coverage score evidence, axis by axis, not from the totals. How this evidence is graded