difyvsflowise-ai
Two self-hosted projects, compared on the numbers selfhost.directory tracks live: score, popularity, release cadence and setup effort.
| dify | flowise-ai | |
|---|---|---|
| Score | 90/100 | 74/100 |
| Rank in category | #1 of 7 in AI Workflows | #22 of 209 in AI Agents |
| GitHub stars | 160 657 | 55 561 |
| Stars, last 30 days | +2 805 | +72 |
| Stable releases, 12 months | 16 | 5 |
| Latest release | 1.19.0 · 4 Nov 2026 | flowise@3.1.4 · 29 Jul 2026 |
| Setup | Moderate | Easy |
| Official Docker image | Yes | Yes |
| License | Other | Apache-2.0 |
| Main language | Python | Typescript |
Which one should you pick?
dify scores 90/100 against 74/100 for flowise-ai, so it is the safer default.
dify ships more often: 16 stable releases in the past year, against 5 for flowise-ai.
If you want the quickest setup, flowise-ai is easier to run; dify needs more configuration.
dify is growing faster right now (+2 805 stars in 30 days).
flowise-ai is archived, so it won't get fixes. Prefer the other one for anything long-lived.
Key differences
- License: dify is Other, flowise-ai is Apache-2.0.
- Language: dify is written mainly in Python, flowise-ai in Typescript.
- Platforms only dify lists: Linux.
- Platforms only flowise-ai lists: Docker, Kubernetes, Node.js.
- Features only dify lists: Autonomous Agents, Backend-as-a-Service APIs, Comprehensive Model Support, LLMOps Observability and 7 more.
- Features only flowise-ai lists: Broad LLM/vector-store support, Custom MCP tool support, Execution traces and metrics, Horizontal scaling with queue and 6 more.
dify details →flowise-ai details →