head to head · open source
Dify vs cangjie-skill
Dify has 156,215 GitHub stars, 24,668 forks, 1,067 open issues and last shipped today. cangjie-skill has 10,225 stars, 1,185 forks, 23 open issues and last shipped 5 days ago. Dify leads on adoption by 1,428% (156,215 vs 10,225 stars). Dify is written in TypeScript under a custom or non-standard licence; cangjie-skill is written in Python under MIT. Dify has attracted 16% as many forks as stars, cangjie-skill 12%. Dify was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 1 topic tag (automation), so they are genuine substitutes rather than adjacent tools.
Two open source projects, one decision. Both are free and self-hostable — the differences are community size, license terms, language stack and release pace.
← all 8884 open source comparisons
Side by side
| Dify | cangjie-skill | |
|---|---|---|
| GitHub stars | ★ 156K | ★ 10K |
| License | Custom / other | MIT |
| Written in | TypeScript | Python |
| Last push | 2026-09-18 | 2026-09-13 |
| Forks | ⑂ 25K | ⑂ 1.2K |
| Self-hosting | Yes | Yes |
| Data ownership | Your server | Your server |
pick Dify if
- You weight community size — 156K stars and counting
- You want the Custom / other license terms
- Your stack matches TypeScript
- You value the larger contributor base for long-term maintenance
pick cangjie-skill if
- You want the cangjie-skill feature set and don't need the biggest community
- You prefer the MIT license terms
- Your stack matches Python
- You evaluated both and cangjie-skill fits your workflow better
About Dify
Dify is an open source LLM application development platform built in TypeScript. It provides a visual interface for designing, testing, and deploying AI workflows, RAG pipelines, and agentic systems without writing extensive code. The platform lives in the generative AI development ecosystem and targets teams needing to move from prototype to production using consistent tooling across environments.
About cangjie-skill
Cangjie Skill is an MIT licensed Python tool that distills methodologies from books, long form videos, and podcasts into callable AI Skills, built for developers and knowledge workers who assemble agent workflows on OpenClaw, Claude Code, or DeepSeek Harness.
read the full cangjie-skill overview →
More in AI & Machine Learning
Related comparisons
More AI Development Platforms projects
Compare either of these against the rest of the AI Development Platforms field.
Frequently asked questions
Is Dify or cangjie-skill more popular?
Dify has 156,215 GitHub stars and cangjie-skill has 10,225. Dify has the larger community by that measure.
Are Dify and cangjie-skill free?
Both are open source. Dify has no licence declared in this registry, and cangjie-skill is licensed under MIT. Both are free to self-host.
What is the difference between Dify and cangjie-skill?
Dify is written in TypeScript and cangjie-skill in Python. The practical differences are community size, licence terms, language stack and release cadence — all compared in the table above.
Which should I choose, Dify or cangjie-skill?
Choose Dify if you want the larger community (156,215 stars) or its Custom / other licence terms. Choose cangjie-skill if its feature set, stack or MIT licence fits better. Both are self-hostable.