Launched this week
OpenFlowKit
100% Free and Open Source Diagram Creator with Total Control
88 followers
100% Free and Open Source Diagram Creator with Total Control
88 followers
OpenFlowKit is a 100% free, open-source diagram engine for engineers, architects, and product teams who care about craft.










@vrun Hey Varun. Can OpenFlowKit ingest architecture definitions automatically? Is there support for live system introspection?
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.
@martin_hernandez4
Thank you so much for the incredibly kind words! Really glad you’re enjoying the UI and the open-source aspect, it’s the core of why we built this.
Regarding your questions:
AI Providers: Currently it’s BYOK for Gemini only, but we built the service layer to be modular. OpenAI and Claude support are the top priorities for our next update. The experience will be identical, just pop in your key and go.
Dark Mode: 100% on the roadmap! We're planning to ship 'Dark mode' soon. You can expect this and more model support by early next week.
P2P Collaboration: One big thing we're planning is P2P Multiplayer via WebRTC. This will allow two people on the same Wi-Fi to brainstorm on one canvas with zero database or cloud infra required, just browser-to-browser sync.
UX & Core: We're also working on a more persistent Flowpilot AI sidebar for better back-and-forth refinement, along with improved node components, auto-layouts, and higher export fidelity.
Thanks again for the support! 🚀
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.
@wilco_kruijer1
Thanks so much for the kind words on the design! We just pushed a few updates specifically to address your experience with Flowpilot (AI mode).
Model Selector is LIVE: We just added a model selector in Settings > Brand Kit > Flowpilot. You can now choose between 2.5 Flash, 2.5 Pro, and even the new Gemini 3 Pro/Flash (Preview) for much better reasoning on designs. We’re also working on adding OpenAI and Claude models to give users more flexibility across top AI providers.
Optimized Layouts: We’ve switched our auto-layout engine to a dedicated Tree algorithm (mrtree) for AI results. This produces significantly cleaner, more professional hierarchies than before.
Refinement is supported: You can actually keep chatting with the AI to tweak the result (e.g., 'add a retry loop' or 'change the theme to blue'). However, we realized the current UI (closing the modal after generation) makes this feature feel hidden. We're working on a persistent sidebar chat so you can refine side-by-side with the canvas.
If you’re open to sharing the prompt that gave you a less-than-optimal result, I’d love to test it against our new layout and model updates!
Please use this form: CLICK HERE
Really appreciate the candid input, it helps us move way faster. 🚀
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?
@austinelvis
Appreciate that a lot 🙌
For enterprise, we’re thinking bottom-up first.
Engineers already create diagrams in docs, wikis, and whiteboards. If OpenFlowKit becomes the fastest way to go from idea → clean, AI-assisted system diagram (without vendor lock-in), adoption can spread organically inside teams.
For enterprise specifically, three things matter:
• Privacy-first — API keys stay client-side. No added AI vendor risk.
• Multi-provider flexibility — teams can use OpenAI, Claude, Gemini, etc. We plug into what’s already approved.
• Open-source foundation — inspectable, forkable, self-hostable. Low lock-in from day one.
The wedge is: make engineers love it. Then layer in enterprise rails (SSO, access control, deployment options).
— Varun
🚀 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