head to head · open source

Dify vs Foundry

Dify has 156,167 GitHub stars, 24,658 forks, 1,067 open issues and last shipped yesterday. Foundry has 872 stars, 129 forks, 5 open issues and last shipped 29 days ago. Dify leads on adoption by 17,809% (156,167 vs 872 stars). Dify is written in TypeScript under a custom or non-standard licence; Foundry is written in Python under Apache-2.0. Dify has attracted 16% as many forks as stars, Foundry 15%. Dify was the more recently maintained of the two, and both are self-hostable with no licence fee. The two share 2 topic tags (agentic-ai, ai), 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.

Dify ★ 156K Foundry ★ 872 category AI & Machine Learning

← all 8884 open source comparisons

Side by side

Dify Foundry
GitHub stars ★ 156K ★ 872
License Custom / other Apache-2.0
Written in TypeScript Python
Last push 2026-09-17 2026-08-20
Forks ⑂ 25K ⑂ 129
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

full Dify profile →

pick Foundry if

  • You want the Foundry feature set and don't need the biggest community
  • You prefer the Apache-2.0 license terms
  • Your stack matches Python
  • You evaluated both and Foundry fits your workflow better

full Foundry profile →

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.

read the full Dify overview →

About Foundry

Foundry is a Python, Apache 2.0 licensed agentic engineering framework from Promptise that gives developers one install for building AI agents, the tools they call, the reasoning they follow, and the governed runtime that serves them to customers.

read the full Foundry overview →

More in AI & Machine Learning

OpenClaw ★ 390K Hermes Agent ★ 246K Ollama ★ 181K Open WebUI ★ 152K langchain ★ 147K ponytail ★ 141K

Related comparisons

dify vs langchain dify vs ponytail dify vs graphify dify vs claude-mem dify vs ragflow langchain vs ponytail langchain vs graphify ponytail vs graphify openclaw vs hermes-agent openclaw vs open-webui openclaw vs lobechat openclaw vs anythingllm openclaw vs cherry-studio openclaw vs nanobot openclaw vs jan openclaw vs librechat ollama vs llama-cpp ollama vs vllm ollama vs gpt4all ollama vs llama-index ollama vs localai llama-cpp vs vllm ollama vs pageindex ollama vs langfuse

More AI Development Platforms projects

Compare either of these against the rest of the AI Development Platforms field.

Dify vs langchain Dify vs ponytail Dify vs generative-ai-for-beginners Dify vs graphify Dify vs claude-mem Dify vs ragflow Dify vs PaddleOCR Dify vs Agent-Reach Dify vs headroom Dify vs Mem0 Dify vs daily_stock_analysis Dify vs LiteLLM

Frequently asked questions

Is Dify or Foundry more popular?

Dify has 156,167 GitHub stars and Foundry has 872. Dify has the larger community by that measure.

Are Dify and Foundry free?

Both are open source. Dify has no licence declared in this registry, and Foundry is licensed under Apache-2.0. Both are free to self-host.

What is the difference between Dify and Foundry?

Dify is written in TypeScript and Foundry 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 Foundry?

Choose Dify if you want the larger community (156,167 stars) or its Custom / other licence terms. Choose Foundry if its feature set, stack or Apache-2.0 licence fits better. Both are self-hostable.