Build any app and use your existing ChatGPT, Claude Code, Gemini, Github Copilot subscription or any API key.
This is the 2nd launch from Orchids. View more
Orchids 1.0
Launched this week
Build any app, any stack + use your existing ChatGPT, Claude Code, Gemini, Github Copilot subscription or any API key to build for free.
Free Options
Launch Team / Built With
v0 by Vercel
Claude Code
Orchids
MedReport AI
MedReport AI
Orchids
@adam_sardo Hey yes can you send in an email to hello@orchids.app? Did you explicitly click the "Fix with Orchids" button?
Clown Spotting
@kevinlu12 The BYOK feature is awesome- I can't wait to play more with it. Keep building great features for us "indie" folks
Orchids
@durjoy 🚀
Hi Kevin,
Congratulations again on the Orchids 1.0 launch — it’s exciting to see an AI app builder designed without constraining architectural flexibility.
I’ve started exploring Orchids using Naveen@prismatom.com while building Prismatom, which is assurance infrastructure for regulated financial systems. We’re particularly interested in evaluating Orchids for building and iterating on internal infrastructure components.
To properly evaluate Orchids in a real-world infrastructure context, it would be helpful to have access to additional usage credits. This would allow us to meaningfully test system boundaries and share more substantive feedback from a fintech and security-focused use case.
We’d be happy to provide detailed product feedback and insights from our evaluation, which could be valuable as Orchids continues to evolve. Either way, I’d love to stay close and share what we learn as we build.
Warm regards,
Naveen Bharti
Co-Founder, Prismatom
https://prismatom.com/
Atomic Bot
Congrats on your launch!
I’ve been using your app for ~2-3 months, and over the last month I’ve been really disappointed last month.
Example: 50 minutes ago I started a task (Opus 4.6) and the agent froze. It stayed “running” with no progress or output. After I reloaded the page, it resumed for ~20 minutes, used ~95k tokens, then froze again. When I stopped the task and started it again, it began from scratch. Over the last month, my agent consumed ~3M tokens in these loops with no expected output.
Support hasn’t replied at all.
I really wanted this to work (I like the design), but right now it feels unreliable.
Can you share when you plan to fix these issues (support responsiveness, freezing, and token burn with no results)?
Orchids
@andrew_dyuzhov3 Can you send an email to hello@orchids.app with your project link (orchids.app/projects/...) so we can investigate this problem?
Congrats on the launch guys! Looking forward to trying this out. Question for you: Does it support OpenRouter API keys and if so, how reliably does it work?
Orchids
@cinemachine Yep supported and quite reliable from our testing!
@kevinlu12 🙌
The "bring your own subscription" model is the right call — most vibe-coding tools charge separately on top of what you're already paying for Claude or GPT, which adds up fast. Curious how Orchids handles context management on complex multi-file projects — does it surface context window limits to the user or try to manage that automatically in the background?
Congrats, Kevin!
I have two questions regarding the long-term side of things:
1. Vendor Lock-in: If I build a project with Orchids, can I export the full source code to host it independently? It’s crucial to know if we truly own what we build.
2. Maintenance: How does Orchids handle updates months later? Does the AI maintain the full context of the existing codebase to ensure that adding new features doesn't break old ones as the app grows?
Thanks for the insights!
Great work with the BYOK man! I truly think this is how we should start shipping software now. What's the most interesting piece of tech you've seen that's come out of Orchids yet