- Reach approvers where they work. Configure email and an IM platform—Slack, Feishu/Lark, Microsoft Teams, DingTalk, or WeCom—to deliver workflow review requests through your team's existing channels.
- Manage recipients in Contacts. Sync IM directories and select approvers from a shared contact list. Workflows can also address the initiator or use one-time and dynamic email recipients.
- Approve in cards or forms. Recipients can review requests directly in supported IM cards or open standalone forms, with Dify login or email verification to verify their identity.
- Customize notifications with workflow context. Use templates and workflow variables to include essential context in notification subjects and bodies.
- Test and track delivery. Send test notifications to verify your setup and inspect delivery records to troubleshoot requests that did not arrive as expected.
- Adopt New HITL in existing workflows. Use opt-in migration to upgrade legacy Human Input nodes when your workflow is ready.
Dify by LangGenius
An open-source platform for building agentic workflows, retrieval pipelines and LLM applications with a visual builder. Available self-hosted or as a cloud service.
Use it in: Web app Self-hosted API / SDK CLI Works with: MCP Headless / CI
On this page
Usage data: latest readings Nov 18 to Nov 19, 2026, last checked Nov 19, 06:29 UTC. Date of each number
What Dify does
Dify is a LLM app and agent platform from LangGenius, first released in May 2023. You use it through a web app, self-hosted, REST API and a command-line tool on macOS, Windows and Linux. Its documentation covers MCP servers and a non-interactive mode for scripts and CI. Paid plans start at $59 a month; there is a free tier.
Key facts
| Maker | LangGenius |
|---|---|
| Type | LLM app and agent platform |
| First released | May 2023 |
| License | Apache-2.0 with additional conditions |
| Interfaces | Web app, Self-hosted, REST API, CLI |
| Platforms | macOS, Windows, Linux |
| Main language | Python |
| Open issues and PRs | 1,445 |
| Docker Hub pulls | 26,249,155 |
Pricing
Dify Cloud offers a free tier with 200 message credits, plus Professional at $59/month or $590/year billed annually (about $49.17 a month; 5,000 message credits a month) and Team at $159/month or $1,590/year (10,000 credits). Enterprise (self-hosted, with SSO and dedicated support) is priced through sales. Community Edition remains free and open-source for self-hosting.
Source: official pricing page, checked Oct 28, 2026. Prices change often; confirm before you buy.
Dify pricing history since 2024 · Compare prices of all agents
Quick answers
- Free to start?Yes
- Open source?Yes (Apache-2.0 with additional conditions)
- Runs onmacOS, Windows, Linux
- Where you use itWeb app, Self-hosted, REST API, CLI
- Supports MCP?Yes
- Model providersany OpenAI-compatible
- Runs in scripts / CI?Yes
- Feature comparisonAll agents
- Closest alternativen8n · all alternatives
What's new in Dify: November 2026 so far
November brought major improvements to workflow observability and human-in-the-loop approvals. Tracing now displays nested execution steps, while new notification channels let teams review requests directly in Slack, Teams, and other platforms they already use.
- Workflow Tools now show their internal execution steps nested under the invoking Tool span in traces.
- Configure email and IM platforms (Slack, Teams, Feishu, DingTalk, WeCom) to deliver workflow review requests directly to approvers.
- Contact management lets you sync IM directories and select approvers from a shared contact list.
- File scanning for malware and sensitive content now covers knowledge bases, RAG Pipeline sources, and Agent Knowledge Base uploads.
2 releases this month · summarised from the official release notes · all months
AgentGid articles about Dify
n8n vs Zapier Agents vs Dify: AI Workflow Automation Tools Compared (2026)
Workflow automation with AI agents: n8n, Zapier Agents, Dify, Microsoft Copilot Studio and open-source builders compared on hosting, pricing, integrations and who each one suits.
How to Build an AI Agent: No-Code Builders, Frameworks and SDKs
A practical guide to building your first AI agent: choosing between no-code builders, open-source frameworks and model vendors' SDKs, the core agent loop, tools, guardrails and testing, with live usage data for each option.
AI Agent vs Chatbot vs Agentic AI: What Is the Difference?
Plain-language definitions of AI agents, chatbots, agentic AI, LLMs, workflows and skills, how they relate, and how to tell which one you are looking at, with real examples.
Get started with Dify
| Docker | docker pull langgenius/dify-api |
|---|
These commands use the packages tracked on this page. The vendor may recommend a different installer; see the official documentation.
What Dify users report right now
Where is the option to publish a Dify workflow as an MCP server, without installing a plugin?
It is built in: open the app's Access Point tab and find the MCP Server card, which is off by default. Turning it on generates a unique MCP server URL for the app; the URL carries credentials, so treat it like an API key and regenerate it if it leaks.
How do I move a self-hosted Dify knowledge base from the default Weaviate vector store to another vector database?
Set VECTOR_STORE to the new database in .env or docker-compose.yaml, then run flask vdb-migrate (with Docker: docker exec -it docker-api-1 flask vdb-migrate). The docs list Qdrant, Milvus and AnalyticDB as the tested targets.
The most discussed problems in its GitHub repository, checked Nov 12, 2026. Written by AgentGid in its own words; statuses and fix versions come from the project's own pages. Reports are users' accounts, not AgentGid tests.
Dify alternatives
Best Dify alternatives compared · All agent builders and workflow automation
| # | Agent | Gid Score | Downloads 7d | 7d | 30d | Stars | Latest release | Price | |||
|---|---|---|---|---|---|---|---|---|---|---|---|
| 4 |
n8nn8n |
79 | 107K | down 28.5% | up 4.9% | 211K+167/day | 1.123.982d ago | Free | |||
| 44 |
AnythingLLMMintplex Labs |
50 | — | — | — | 68.4K+35/day | 1.20.03d ago | Free + $50/mo | |||
| 50 |
LangflowLangflow (DataStax, an IBM company) |
47 | 13.2K | down 19.0% | up 13.8% | 157K+36/day | 1.13.33d ago | Free (OSS) | |||
| 79 |
|
412/4 | — | — | — | 32.6K+19/day | usage-counter11d ago | Free (OSS) | |||
| 100 |
Coze StudioByteDance |
382/4 | — | — | — | 21.8K+2/day | 0.5.19mo ago | Free (OSS) | |||
| 109 |
ActivepiecesActivepieces |
36 | — | — | — | 25.6K+20/day | 0.93.012d ago | Free + $20/mo | |||
Head to head: Dify vs n8n · Dify vs AnythingLLM · Dify vs Langflow · Dify vs Jobs Applier AI Agent · Dify vs Activepieces
Ratings from people who use Dify
No ratings yet. Used Dify? Rate it and say what it is good and bad at.
Dify news
-
Dify 1.20.0 released
Reach approvers where they work. Configure email and an IM platform—Slack, Feishu/Lark, Microsoft Teams, DingTalk, or WeCom—to deliver workflow review requests through your team's existing channels.; Manage recipients in Contacts. Sync IM directories and…
What changed: recent Dify releases
5 stable releases in the last 90 days · Monthly summary · Full changelog
- Follow the hierarchy. Expand called Workflow Tools to see their internal execution steps under the invoking Tool span.
- Understand each invocation. Repeated calls and failures retain their place in the trace.
- Keep the LLM context. Inspect formatted prompts and responses, token usage, and project, trace, and observation links.
- Storage-cleanup indexes (d7e9a1c3f502). Add reference indexes on message_files.upload_file_id, workflow_node_execution_offload.file_id, and workflow_draft_variable_files.upload_file_id.
- Tracing configuration uniqueness (53c10126d551). Keep one configuration per app/provider and add a unique index.
- Extraction changes affect newly processed content. Re-import or re-index documents whose stored content was affected by the EPUB, EML, DOCX, CSV, Markdown, or Notion fixes.
Earlier releases
- Published triggers: the draft-sync fix does not repair subscriptions already removed before upgrading. Rebind missing subscriptions and republish affected workflows as needed.
- Document extraction: re-import/re-index affected content to apply extraction fixes to existing documents.
- Built-in document metadata: toggling built-in fields rewrites only enabled, non-archived documents whose indexing is complete.
- Add the Beta knowledge-space experience with local upload preview, connected-source management, document availability and metadata, retrieval history/research, and quality evaluation.
- Knowledge Retrieval v2 and Agent knowledge bindings use scoped capabilities; published Explore runs reuse published bindings without requiring ordinary viewers to reconfigure access.
- Classic Dataset upgrades have durable checkpoints, availability/metadata reconciliation, retry protection, and recovery through Beat.
- Knowledge base service-API keys were scoped to the whole workspace: one key could read and write every knowledge base in the tenant, so giving an integration access to a single knowledge base…
- The workflow canvas required a mouse to reposition anything. Nodes, multi-node selections, comment markers, and draft comments can now be moved with the arrow keys — hold Shift for larger steps —…
- Plugin authors now have public profile pages at /marketplace/creator/<handle>, listing their creations with a publisher sidebar, reachable from a new Creator Center entry in the sidebar help menu.
- The Markdown form field-name limit was hard-coded at 128 characters, with no way to accommodate longer generated field names.
- CSV cells were passed through pandas type inference before indexing. Leading-zero codes became floats (00123 → 123.0), empty cells became the literal string nan, and cells containing NA or NULL…
- Notion table rows lost or gained columns. Each rich-text segment inside a cell was emitted as its own Markdown column, so any cell with mixed formatting — bold, links, mentions — produced extra…
- E2B sandbox backend: agent shell/code execution can now run on E2B cloud sandboxes in addition to the local sandbox. Select the backend with DIFY_AGENT_RUNTIME_BACKEND.
- Build-time Home Snapshots: when an agent build is applied (published), the agent's sandbox home directory — installed packages, prepared files, working state — is captured and subsequent runs of…
- Workspace-level Skill management: Skills are reusable, versioned capabilities packaged with code and tool definitions that agents can discover and invoke.
- Context-aware history compaction: long agent conversations no longer blow past the model's context window — Dify resolves each model's effective window and tiers compaction…
- Define a shared provider/model/mode/parameter configuration once (e.g. for_summarize, for_research) and reference it from any LLM node.
- Human-in-the-loop forms now work inside Loop and Iteration nodes, pausing and resuming correctly across page refreshes for both debug and installed apps — enabling review/approval steps within…
- Workflow tool nodes now support multi-select dropdown inputs, allowing users to choose multiple values from a predefined list when configuring tool parameters.
- You can now click a node_id in workflow run logs or error messages to locate and highlight the corresponding node in the workflow editor canvas.
- The block selector panel now features improved keyboard navigation, category previews, and a more intuitive search experience when adding nodes to workflows.
- Agent apps can now be exported as DSL YAML directly from the app sidebar menu, making it easy to back up or version-control agent configurations.
- Added more observability traces to knowledge/RAG document processing operations, improving visibility into indexing pipelines.
- Fixed hidden-tab collaboration leader saving stale drafts when the tab is inactive
Dify prices over time
Dify popularity and usage data
The GitHub repository has 161K stars, 2,904 of them added in the last 30 days. The latest stable release is 1.20.0, published Nov 18, 2026; there were 3 stable releases in the past 30 days.
Download the raw daily series: dify.csv
Gid Score breakdown
Gid Score shows public popularity and activity (usage, GitHub stars, mentions, growth), not the quality of the product. Each component is scored 0 to 100 from public signals; a dash means no data for it. How the Gid Score works.
How fresh these numbers are
| Number | Latest reading | Last checked |
|---|---|---|
| GitHub stars | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Docker pulls | Nov 19, 2026 | Nov 19, 06:26 UTC |
| Website rank (Tranco) | Nov 18, 2026 | Nov 19, 06:29 UTC |
We fetch every source once a day. Registries publish downloads and page views a day or two late, so their latest reading trails the check. A reading more than 4 days old is marked out of date; the Gid Score still uses it until a newer one arrives.
Dify FAQ
How much does Dify cost?
Dify Cloud offers a free tier with 200 message credits, plus Professional at $59/month or $590/year billed annually (about $49.17 a month; 5,000 message credits a month) and Team at $159/month or $1,590/year (10,000 credits). Enterprise (self-hosted, with SSO and dedicated support) is priced through sales. Community Edition remains free and open-source for self-hosting.
Is Dify open source?
Yes. Dify is open source, released under the Apache-2.0 with additional conditions license.
How popular is Dify?
The GitHub repository has 161K stars, 2,904 of them added in the last 30 days. The latest stable release is 1.20.0, published Nov 18, 2026; there were 3 stable releases in the past 30 days.
What is the latest version of Dify?
The latest stable release we track is 1.20.0, published on Nov 18, 2026.
What are the alternatives to Dify?
The closest alternatives in the same category by Gid Score are n8n, AnythingLLM, Langflow, Jobs Applier AI Agent.
For the makers of Dify badges, corrections
Add a live badge to your README or site:
[](https://agentgid.com/agents/dify/)
[](https://agentgid.com/agents/dify/)
Something wrong or outdated on this page? Send a correction with a link to the official source. More for makers.
Where these numbers come from
GitHub: langgenius/dify. Site rank: dify.ai on the Tranco list. See data sources for how each one is collected.