Giselle
Build and run AI workflows. Open source.
977 followers
Build and run AI workflows. Open source.
977 followers
Built to design and run AI workflows that actually complete. Zero infra setup—just build and run. Handle complex, long-running tasks with a visual node editor and real-time tracking. Combine models from multiple providers in one canvas.
Giselle
Hey Product Hunt 👋
I’m part of the Giselle team now, but I actually started as an external contributor.
Giselle is fully open source. My journey began with a simple typo fix. From there, I started contributing small features, got feedback, and gradually understood the system. Eventually, I was invited to work closely with the team on the core product.
We want to create that same experience for everyone. Whether you write code, share ideas, or report bugs, every contribution moves Giselle forward.
If you want to help shape the future of AI workflows, come join us! Giselle is the perfect place to start contributing to an AI project.
Giselle
I also shared a blog post diving deeper into this, if anyone’s interested:
https://giselles.ai/blog/from-oss-contributor-to-team-member-at-giselle
Giselle
@washizuryo san, Thanks for sharing this one too!
It was great to read about your journey from OSS contributor to team member. Really glad to have you on the team!
Giselle
@washizuryo san, Thank you for all your contributions!
Your journey from a typo fix to a core team member is exactly the kind of story we want to create with Giselle. Let's keep building together! 🙌
Giselle
Hi Product Hunt 👋
I’m one of the creators of Giselle. Thanks for checking us out.
When we looked at existing AI workflow tools, they mostly fell into two camps.
Some are extremely easy to start with. You can build something quickly and see results right away — but once you try to use them for real work, they start to feel fragile. Long-running jobs and failures make you nervous, and it’s hard to understand what’s happening while they run.
Others are built for durable execution, with strong telemetry and observability. They’re powerful and reliable, but the first step is heavy, often requiring engineering effort before you can even try an idea.
We couldn’t find something that was easy to start and still safe to rely on.
That gap is exactly why we built Giselle.
Giselle lets you design AI-powered apps and workflows intuitively, while treating them as real jobs — with clear progress, structure, and visibility, even when they run for hours across many steps.
If you’ve ever felt that your AI workflow works “until you actually need to depend on it,” we’d love to hear your thoughts and feedback.
Giselle
@toyamarinyon san, Thank you for writing so much code as a Core committer and driving the development all the way to launch. Giselle wouldn't be where it is today without your contributions. Excited to keep building this together!
Giselle
@samtheanalyst Thanks for the feedback!
Our website seems to be loading fine on our end, but we'll look into it just to be sure.
We expect most early users to start by experimenting with Chain of Models. Once they get comfortable, we'd love for them to try out workflows with GitHub integration—that's actually how we use it internally. We're also planning to add more tool integrations and APIs down the road.
So far, the visual canvas has been getting the most appreciation. That said, we know there's room to make things simpler and more intuitive, and we're planning to improve our documentation and guidance going forward
Giselle
@samtheanalyst san, Thank you for the kind words!
Sorry to hear about the website loading issue. If you're still experiencing problems, please reach out to us at support@giselles.ai, or you can also report bugs directly on our GitHub at https://github.com/giselles-ai/giselle/issues/new/choose — we'll look into it right away.
Thanks also for the suggestion about improving onboarding — we'll definitely take that to heart!
Vercel
Congrats on the launch!
Giselle
@rauchg Thanks so much, Guillermo!
We build and deploy Giselle on Vercel, and make extensive use of Next.js and the Vercel AI SDK — really appreciate all the work behind them.
Looking forward to exploring Workflow DevKit and Vercel Queues as we continue building.
Giselle
Thank you so much, @rauchg san! This means a lot coming from you.
As I shared in our Build with Vercel review, Giselle truly wouldn't exist without Vercel's ecosystem—Next.js as our foundation, the AI SDK powering our multi-model orchestration, and AI Gateway ensuring reliable model access.
https://www.producthunt.com/products/vercel/reviews?review=418558
Your comment just made our launch day even more special. 🙌
Giselle
@rauchg Thank you so much! Vercel and the AI SDK are absolutely essential to what we do. I personally recommend Vercel to many people around me.
v0 is also getting great feedback from our customers here in Japan!
What stands out to me is the emphasis on making workflows understandable, not just runnable.
When people can clearly see how decisions flow and how state evolves, AI becomes something teams can actually rely on day to day. That’s usually where these tools either stick or fade.
Nice work. Curious to see how this holds up as usage grows.
Giselle
@petter_magnusson Thank you for this comment — it really resonates with us.
Making workflows understandable, not just runnable, is exactly what we're focused on. We dogfood Giselle ourselves and feel this pain firsthand, which drives a lot of our design decisions.
As for scale, that's definitely an area we're actively working on. Appreciate you keeping an eye on us!
@gyu07 Makes sense.
We’ve run into the same thing. Once workflows get opaque, teams stop trusting them, even if they technically “work.”
We’re tackling a nearby problem with purposewrite, but through a more step-by-step, interview-style model with Human In The Loop, rather than graphs and running tasks.
If it’s useful, we’ve open-sourced a few concrete workflow examples here:
https://github.com/Petter-Pmagi/purposewrite-examples
Hey love the design and functionality. How does it differentiate itself from n8n, make , zapier and other tools ?
Giselle
@siraj_hassan2 Thanks! Design is something we really care about, so that means a lot.
A few key differences:
First, we focus on making it easy to access the latest AI models. We've already integrated major APIs — OpenAI, Anthropic, Gemini, and more — so users can start using the latest models right away without managing their own API keys.
Second, we currently have strong integrations with tools like GitHub, making it easy to build agents that support product development workflows — things like generating release notes, drafting PRDs, or automating code reviews.
Looking ahead, we're focused on helping users turn their knowledge work into workflows through experimentation. We're also exploring ways to support end-to-end agentic flows, from structured data analysis to KPI reporting.