deer-flow vs Dify
Two of the top projects in Agent platforms, side by side: who leads on each score part and who each one suits, then setup, license, activity and what each review found.
deer-flow
Agent harness that runs sub-agents, memory and sandboxed skills for long tasks
Dify
Visual builder for LLM workflows, RAG pipelines and agents, with APIs
Verdict
deer-flow ranks higher, 75 to 74. Of the 5 score parts we measure for both, deer-flow leads on 2, Dify on 2 and 1 is even.
- AdoptionDify leads by 13 points, 95 to 82.
- FreshnessEven at 100.
- MaintenanceDify leads by 17 points, 93 to 76: a wide gap.
- Easy to rundeer-flow leads by 17 points, 50 to 33: a wide gap.
- Agent-readydeer-flow leads by 25 points, 70 to 45: a wide gap.
Pick deer-flow if you are
Engineers self-hosting a multi-agent harness for research and long-running tasks
- Interactive `make setup` wizard generates config.yaml and .env in about 2 minutes
- Web UI model registration for OpenAI, Anthropic, DeepSeek, Qwen, Doubao, Kimi, Zhipu, MiniMax
Pick Dify if you are
Teams building and self-hosting LLM apps, RAG and agent workflows
- Visual workflow canvas, prompt IDE and RAG pipeline in one platform
- Every app exposes an API, so it works as a backend service
| What we compare | deer-flow | Dify |
|---|---|---|
| Score parts, out of 100 | ||
| Adoption | 82, widely used | 95, widely used |
| Freshness | 100, active | 100, active |
| Maintenance | 76, fair | 93, healthy |
| Easy to run | 50, easy | 33, some setup |
| Agent-ready | 70, partly | 45, minimal |
| Facts from GitHub and the README | ||
| Stars | 83.9k | 158.5k |
| License | MIT (permissive) | custom license (read the license) |
| Last commit | Oct 2026 | Oct 2026 |
| Last release | Sep 2026 | Sep 2026 |
| Language | Python | TypeScript |
| Docker | Yes | Yes |
| GPU | Not needed | Not needed |
| arm64 or Apple Silicon | Mentioned | Not stated |
deer-flow
DeerFlow 2.0 is a ByteDance agent harness where a lead agent delegates to sub-agents, backed by long-term memory, a sandboxed file system and extensible skills. It includes a web UI, a Gateway, MCP support, IM channels, scheduled tasks, a terminal UI and an embedded Python client. It is a ground-up rewrite that shares no code with v1.
Who it is for: Engineers self-hosting a multi-agent harness for research and long-running tasks
Strengths
- Interactive `make setup` wizard generates config.yaml and .env in about 2 minutes
- Web UI model registration for OpenAI, Anthropic, DeepSeek, Qwen, Doubao, Kimi, Zhipu, MiniMax
- Tracing via LangSmith, Langfuse and Monocle, plus `make doctor` and `make support-bundle`
- Many search and fetch backends: Brave, Tavily, Jina, Firecrawl, Crawl4AI, InfoQuest
Weaknesses
- README warns improper deployment carries security risks; Gateway admin equals code execution
- Local development needs Python 3.12+ and Node.js 22+
- README is dense with config detail; RAM and hardware needs are not stated
- v2 shares no code with v1; v1 users must stay on the 1.x branch
- no GPU
- Docker + Compose
- Needs LLM provider API key, Python 3.12+, Node.js 22+
- Models: OpenAI, Anthropic, DeepSeek, Qwen, Doubao
Dify
Dify is an LLM app development platform with a visual workflow canvas, a prompt IDE, a RAG pipeline that extracts text from PDFs and PPTs, and agents that run in their own sandbox. Every app is exposed through an API. Model providers include GPT, Mistral, Llama3 and any OpenAI-compatible endpoint. It runs via Docker Compose or as the hosted Dify Cloud.
Who it is for: Teams building and self-hosting LLM apps, RAG and agent workflows
Strengths
- Visual workflow canvas, prompt IDE and RAG pipeline in one platform
- Every app exposes an API, so it works as a backend service
- Supports hundreds of LLMs plus any OpenAI API-compatible model
- Agents can use Marketplace tools, MCP servers or your own APIs
Weaknesses
- License is the Dify Open Source License (Apache 2.0 plus extra conditions)
- SSO, RBAC and support SLAs are in the Enterprise edition
- Docker Compose self-hosting needs at least 2 CPU cores and 4 GiB RAM
- Observability relies on external tools such as Opik, Langfuse and Arize Phoenix
- RAM ≥ 4 GB
- no GPU
- Docker + Compose
- Needs Docker, Docker Compose v2.24.0+
- Models: GPT, Mistral, Llama3, OpenAI API-compatible models
- port 80
More in Agent platforms
Building with these?
We help teams pick an open-source AI stack and run it in production. Client work never changes a rank.