This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Wayflow
Embeddable AI workflow builder for your app
An embeddable visual workflow editor for your app. Your users build workflows and actually run them — powered by AI when you want it, plain logic when you don't. Works in any framework.
In many agentic products that support workflows (including one I worked on), I noticed they either don't support node-based editors, or use React Flow and go through the difficult work of integrating it into their product to run it and work with their existing logic.
So I thought about creating a tool that could help with this by closing the gap between the editor and the runtime. That's why I created Wayflow.
The architecture is simple: you create a graph (a JSON object) that the runtime knows how to run, and the editor helps you build that graph. The runtime doesn't care where the graph comes from, it just needs the right schema.
After you create the graph in the editor, you can then export it or directly save it on your backend in your database. And then when you want to execute it, you just hand it to the runtime.
The runtime can either stream the execution (which is useful for the editor), or give you the final result. How you execute the graph is up to you: through an API endpoint, a cron job, or any other way you want.
Wayflow comes with a number of built-in nodes like Input, Output, LLM, Image Generation, Array Operations, Conditional, ... and I spent a lot of time making sure they cover most of the common cases your app needs. But you can easily add your custom nodes that work for your specific app.
One of the main challenges (and one of the fun parts) was making it provider-neutral. So it's not locked to a specific LLM provider. I did this by targeting the OpenAI-compatible API, which almost all frontier models support. The same thing for frameworks and libraries. It has zero dependencies and it's framework-agnostic.
There are many things I didn't cover here, like tool calling, converting full workflows into tools, human-in-the-loop, etc. You can read all about this in the docs.
One important thing I'd like to mention is that even though LLMs are a huge part of the workflows you create, they are completely optional. You can literally build any workflow (with the help of more custom nodes) with zero AI, for full deterministic execution.
I hope this is something you'll find helpful to use in your projects. Happy coding!
About Wayflow on Product Hunt
“Embeddable AI workflow builder for your app”
Wayflow was submitted on Product Hunt and earned 0 upvotes and 2 comments, placing #74 on the daily leaderboard. An embeddable visual workflow editor for your app. Your users build workflows and actually run them — powered by AI when you want it, plain logic when you don't. Works in any framework.
On the analytics side, Wayflow competes within Open Source, Developer Tools, Artificial Intelligence and GitHub — topics that collectively have 1.1M followers on Product Hunt. The dashboard above tracks how Wayflow performed against the three products that launched closest to it on the same day.
Who hunted Wayflow?
Wayflow was hunted by Taha Shashtari. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Wayflow including community comment highlights and product details, visit the product overview.
Taha Shashtari
Hi everyone!
In many agentic products that support workflows (including one I worked on), I noticed they either don't support node-based editors, or use React Flow and go through the difficult work of integrating it into their product to run it and work with their existing logic.
So I thought about creating a tool that could help with this by closing the gap between the editor and the runtime. That's why I created Wayflow.
The architecture is simple: you create a graph (a JSON object) that the runtime knows how to run, and the editor helps you build that graph. The runtime doesn't care where the graph comes from, it just needs the right schema.
After you create the graph in the editor, you can then export it or directly save it on your backend in your database. And then when you want to execute it, you just hand it to the runtime.
The runtime can either stream the execution (which is useful for the editor), or give you the final result. How you execute the graph is up to you: through an API endpoint, a cron job, or any other way you want.
Wayflow comes with a number of built-in nodes like Input, Output, LLM, Image Generation, Array Operations, Conditional, ... and I spent a lot of time making sure they cover most of the common cases your app needs. But you can easily add your custom nodes that work for your specific app.
One of the main challenges (and one of the fun parts) was making it provider-neutral. So it's not locked to a specific LLM provider. I did this by targeting the OpenAI-compatible API, which almost all frontier models support. The same thing for frameworks and libraries. It has zero dependencies and it's framework-agnostic.
There are many things I didn't cover here, like tool calling, converting full workflows into tools, human-in-the-loop, etc. You can read all about this in the docs.
One important thing I'd like to mention is that even though LLMs are a huge part of the workflows you create, they are completely optional. You can literally build any workflow (with the help of more custom nodes) with zero AI, for full deterministic execution.
You can try it in your browser (no signup, bring your own key) at https://wayflow.build. It's also on npm (npm install wayflow), and the code is on GitHub (https://github.com/TahaSh/wayflow).
I hope this is something you'll find helpful to use in your projects. Happy coding!