{"slug":"dify","name":"Dify","vendor":"LangGenius","tagline":"Open-source platform for building agentic workflows, RAG pipelines and LLM apps on one canvas","url":"https://agentboards.org/agent/dify","website":"https://dify.ai","docs":"https://docs.dify.ai","repo":"https://github.com/langgenius/dify","category":"framework","execution":["local","cloud"],"license":"Dify Open Source License (Apache-2.0 with additional conditions)","open_source":true,"pricing":{"model":"mixed","summary":"Community edition free to self-host; Dify Cloud Sandbox free, Professional $590/year, Team $1,590/year, Enterprise on request","from_usd":null,"free_tier":true,"byok":true},"models":{"backbone":["any"],"bring_your_own_model":true,"local_models":true},"protocols":{"mcp_client":true,"mcp_server":false,"openapi":true},"capabilities":{"terminal_exec":false,"browser":false,"multi_file_edit":false,"git_ops":false,"docker_sandbox":false,"multi_agent":true,"headless_ci":false},"context_window":null,"platforms":["macos","linux","windows","web"],"install":[{"label":"docker","command":"cd docker && cp .env.example .env && docker compose up -d"}],"benchmarks":[],"tags":["low-code","workflow","rag","self-hosted","mcp"],"github_stars":157708,"metrics":{"stars":157708,"pushed_at":"2026-10-02T03:35:21Z","archived":false,"open_issues":922,"latest_version":"1.17.1","latest_version_at":"2026-09-10T10:04:06Z","latest_version_url":"https://github.com/langgenius/dify/releases/tag/1.17.1","version_source":"github","checked_at":"2026-10-02T05:05:37.644Z"},"sources":{"license":"https://github.com/langgenius/dify","install":"https://github.com/langgenius/dify","pricing":"https://dify.ai/pricing","protocols":"https://dify.ai","models":"https://github.com/langgenius/dify"},"verified_at":"2026-09-04","adoption":{"score":9.1,"signals":{"github_stars":157298,"hn_mentions_1y":11},"measured_at":"2026-09-28"},"scores":{"panel":7.7,"adoption":9.1,"spread":0.8,"facts":8.3,"board":8,"dimensions":{"reliability":7.5,"usefulness":7.8,"cost":7.5,"longevity":7.8},"per_persona":{"amigo":8,"critico":7.3,"profesor":7.8,"inversora":8,"jefa":7.3,"hacker":7.8},"community":null},"rank":null,"category_rank":3,"panel_reviews":[{"persona":"juez","persona_name":"El Juez","ai_generated":true,"verdict":"Three quarters of a point covers the panel and the low mark is 7.25, the strongest agreement here; the cost is El Crítico's question, which nobody priced.","scores":null,"evidence":[]},{"persona":"amigo","persona_name":"El Amigo","ai_generated":true,"verdict":"Pick Dify when people who are not engineers need to build and change LLM applications; pick n8n if the hard part is connecting systems rather than handling documents and prompts.","scores":{"reliability":8,"usefulness":8,"cost":8,"longevity":8},"evidence":["https://dify.ai","https://docs.dify.ai"]},{"persona":"critico","persona_name":"El Crítico","ai_generated":true,"verdict":"The canvas is the source of truth, and a graph edited by dragging does not appear in a pull request, so the review culture around it has to be invented from nothing.","scores":{"reliability":7,"usefulness":7,"cost":7,"longevity":8},"evidence":["https://docs.dify.ai","https://github.com/langgenius/dify"]},{"persona":"profesor","persona_name":"El Profesor","ai_generated":true,"verdict":"Retrieval, model management and orchestration are separated into distinct subsystems, and finished workflows are exposed over OpenAPI, so an application becomes a callable service.","scores":{"reliability":8,"usefulness":8,"cost":7,"longevity":8},"evidence":["https://docs.dify.ai","https://dify.ai"]},{"persona":"inversora","persona_name":"La Inversora","ai_generated":true,"verdict":"One hundred and fifty thousand stars is the largest open-source distribution in this class, and LangGenius monetises it with annual cloud plans from $590 rather than a meter.","scores":{"reliability":8,"usefulness":9,"cost":7,"longevity":8},"evidence":["https://dify.ai/pricing","https://github.com/langgenius/dify"]},{"persona":"jefa","persona_name":"La Jefa","ai_generated":true,"verdict":"Self-hosting costs infrastructure and an owner; the hosted Team plan is $1,590 a year, which is trivial, and everything my security review needs sits in the tier priced by conversation.","scores":{"reliability":7,"usefulness":7,"cost":7,"longevity":8},"evidence":["https://dify.ai/pricing","https://docs.dify.ai"]},{"persona":"hacker","persona_name":"El Hacker","ai_generated":true,"verdict":"The licence is not plain Apache-2.0, it is Apache with additional conditions, so read it before you fork; the compose file and any OpenAI-compatible endpoint are the good parts.","scores":{"reliability":7,"usefulness":8,"cost":9,"longevity":7},"evidence":["https://github.com/langgenius/dify","https://docs.dify.ai"]},{"persona":"comediante","persona_name":"El Comediante","ai_generated":true,"verdict":"It integrates hundreds of models, which is one very effective way to avoid ever choosing one.","scores":null,"evidence":[]}]}