Hey Product Hunt! 👋
I'm V, and I built OpenFlowKit because I was tired of two things:
1. Diagram tools that look like they're from 2005, locked colors, rigid templates, enterprise beige everywhere.
2. Paying $20/month for something that should be a text file.
OpenFlowKit is my answer: a diagram engine where you can write code (Mermaid or DSL), drag-and-drop, or just tell the AI what you want. It runs 100% in your browser — no signup, no cloud, no data leaving your machine.
Some things I'm proud of:
* Flowpilot AI — BYOK with Gemini. It actually understands diagram context.
* Figma export — Copy-paste gives you editable vectors, not flat images.
* The aesthetics — I spent way too long making sure diagrams look beautiful by default.
It's MIT licensed and completely free. I'd love your feedback, what would make this your go-to diagram tool?
🚀 Big Update: Flowpilot Now Supports 6 AI Providers + Custom Endpoints
Hey Product Hunt 👋
We just shipped a major upgrade to OpenFlowKit, it’s now fully multi-provider.
Flowpilot used to be Gemini-only. Now you can bring your own key from:
Gemini
Groq
Cerebras
NVIDIA NIM
OpenAI
Claude
Or any OpenAI-compatible endpoint (Ollama, LM Studio, Together, etc.)
Why this matters
Most AI tools lock you into one provider. We went the opposite direction.
You choose:
⚡ Speed (Groq, Cerebras)
🧠 Reasoning (Claude)
💰 Free tiers (Gemini, Groq, Cerebras)
🏠 Local/self-hosted models
And your API key stays in localStorage, it never touches our servers. BYOK by design.
If you're building architecture diagrams, system flows, or product docs, I’d love your feedback.
We’ll be around all day answering questions 🙌
— Varun
Congrats on the launch @vrun! Love the open source approach for diagram tooling. The craft-focused positioning is smart. How are you planning to drive adoption among enterprise engineering teams?
Varun Congratulations on the launch. The clean interface looks great and the ease of dragging and dropping nodes offers a very pleasant experience. I'm sure it will be a guaranteed success since it has the necessary options to create robust flows. What you have created is wonderful, congratulations! Also, the attention to detail in the design really makes a difference and demonstrates a very professional approach.
And the best part is that it is open source and completely free. Wow!
Moreover, being open source means any developer can adapt and customize the tool according to their specific needs, enhancing its flexibility and reach. This also fosters a collaborative ecosystem where improvements and updates can come from multiple sources, ensuring the software’s constant evolution. Without a doubt, this feature opens many doors for future innovations and greater accessibility in using the tool.
I have a question: is BYOK only with Gemini? I ask because, for now, I only have OpenAI. I would like to know if there is any compatibility or planned support for other platforms or cloud service providers. It would also be helpful to understand if there are significant differences in the implementation or management of BYOK between Gemini and OpenAI, so I can properly prepare the integration depending on the environment used.
Do you have any plans for a dark mode option?
It would be great to know if you are considering adding more integrations in the future to expand its reach and functionality.
Looks beautiful! What are your plans for the AI mode? I just entered an API key and prompted something relatively simple and got a less-than-optimal result. Would be cool if I could back-and-forth with the AI to refine my result.
