Create AI pipelines by connecting nodes. Bring together Hugging Face Spaces, models, datasets, and your own Python functions on a visual canvas - or let AI agents build workflows programmatically. Inspect intermediate inputs and outputs, and swap in better models without rebuilding your workflow. No downloads needed! Share with a URL or run via a REST API.
every multi-step ai thing i've built ends up as something that works on my machine and nowhere else.
gr.workflow changes that! you build the pipeline as a graph, inputs and steps and outputs, and that graph is the thing you share. there's no separate ui to write afterwards. it taps straight into the hugging face hub. any model served by inference providers, anyone's public space, datasets, all of them drop onto the canvas as nodes. nothing to download, nothing to wrap. your own python functions sit right next to them.
it's built on gradio, so if you've shipped a gradio app you already know most of it. hope you find this tool helpful, and I can't wait to see what you built with it! it is still in beta, so feel free to report any issues via our github repo or our discord. happy building!
No comment highlights available yet. Please check back later!
About Gradio Workflow on Product Hunt
“connect nodes to build AI pipelines, powered by Hugging Face”
Gradio Workflow launched on Product Hunt on September 21st, 2026 and earned 85 upvotes and 1 comments, placing #17 on the daily leaderboard. Create AI pipelines by connecting nodes. Bring together Hugging Face Spaces, models, datasets, and your own Python functions on a visual canvas - or let AI agents build workflows programmatically. Inspect intermediate inputs and outputs, and swap in better models without rebuilding your workflow. No downloads needed! Share with a URL or run via a REST API.
Gradio Workflow was featured in Productivity (661.2k followers), Developer Tools (519.8k followers), Artificial Intelligence (479.1k followers) and GitHub (41.4k followers) on Product Hunt. Together, these topics include over 398.7k products, making this a competitive space to launch in.
Who hunted Gradio Workflow?
Gradio Workflow was hunted by hannah. 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.
Want to see how Gradio Workflow stacked up against nearby launches in real time? Check out the live launch dashboard for upvote speed charts, proximity comparisons, and more analytics.
hannah
hey product hunt 👋
every multi-step ai thing i've built ends up as something that works on my machine and nowhere else.
gr.workflow changes that! you build the pipeline as a graph, inputs and steps and outputs, and that graph is the thing you share. there's no separate ui to write afterwards. it taps straight into the hugging face hub. any model served by inference providers, anyone's public space, datasets, all of them drop onto the canvas as nodes. nothing to download, nothing to wrap. your own python functions sit right next to them.
it's built on gradio, so if you've shipped a gradio app you already know most of it. hope you find this tool helpful, and I can't wait to see what you built with it! it is still in beta, so feel free to report any issues via our github repo or our discord. happy building!