82 comments found.
Is this a web application with full source code that can manage and adding every model in Hugging Face and support rag, database vertex and text/image/video, allow multiple users to run chatbots simultaneously, and be implemented on localhost for offline use
Hi, yes it’s a web application with the full source code available. You can add any model (LLM) via OpenRouter, and image/video generation models via Replicate. There’s no rag, vertex, or simultanoeous chatbots at the moment. You can run it via localhost with a local dev server if you want.
Is it possible to combine two different AI models to leverage their best attributes simultaneously—for example, merging a general-purpose model with a specialized coding model? Additionally, can we perform deep fine-tuning to train the AI with more specialized knowledge?
So my objective, I want to build an internal knowledge base using an offline, on-premise AI model. My goal is to keep the data private and accessible without internet, but with the flexibility to connect it to an API or a chatbot for remote access when needed. I want to be able to download the model, set it up locally, and fine-tune it with our own data. Could you provide a documentation to know better about this apps
Thanks
The features you mentioned are not currently available, but we can implement any custom features for an additional fee. If you’re interested, feel free to reach out to us via email (via the contact form on our codecanyon profile).
What does the March 24 update include???
Hi, the biggest change is a refactor of the authentication system to a more modern Authentication library. If you’re an existing customer, make sure to follow the instructions provided with the 2.5.0 version files, since it’s a breaking change if you have a database with existing users.
Other big change is performance optimizations, both user-facing pages and admin pages now load much faster when navigating between them, even on serverless environments.
There’s other changes like bug fixes and new AI models as well.
Will provide the full changelog soon.
{status}} not showing UI.
Hello, can you elaborate? What kind issue are you experiencing?
so how do we set the pricing plan quotas? is it still based on the number of questions we assign or is it token based? because different models have different pricing…or do we set limits per model per plan?
Yes, right now it’s based on the number of messages you assign. We do have plans on our roadmap to improve the quota system since as you said not all models cost the same.
Still waiting for latest update changelog… When is it coming?
Hi, just uploaded v2.1.0, will combine the changelog with that version too. Apologies for not providing sooner!
Yeah I just got a noti about the update! Waiting for the changelog!
Full changelog will be available by the end of tomorrow or Friday. Sorry once again for being a bit late with the changelogs.
Changelog has been released
Hi, What technology are you using for backend webapi, is it node.js?
Hi, yes- it’s a Nodejs app built with Svelte/SvelteKit
Since the app uses multiple llm’s does it use something like openrouter or vercel ai to do this? instead of signing up for each individually?
Yes, correct. It uses unified API providers:
- For LLMs it uses OpenRouter
- For Image/Video gen models it uses Replicate
- For Audio gen tools it uses ElevenLabs
So, you only need 3 API keys in total.
Feb 2026 new features + complete Changelog please
Hi, just uploaded v2.1.0, will combine the changelog with that version too. Apologies for not providing sooner!
need suport
Hello, please send us an email via the contact form: https://codecanyon.net/user/enigmaworld
1. Can this handle high‑volume cold calling plus inbound AI calls (sales + appointments)?
2. Is telephony locked to Twilio, or can I use my own SIP trunk/local numbers?
3. Can I route calls through Twilio SIP/Browser/App calling at around $0.0040/min instead of standard Twilio numbers?
4. Any current or planned WhatsApp integration for pre/post‑call messages without meta API?
5. Is Arabic fully supported for AI voice conversations?
Hello Team, I have gone through your product and it seems the bugs and all are not fixed. I am really excited and interested to get this product if you could release the nexr 2.0 version. Could you please let me know if you are really working on the feature improvement and when it can be ready?
Hello, the known issues will be fixed in the next version (2.0). We’ve delayed the update to next week so we can test it better to ensure there’s no bugs since it introduces major changes.
Thank you for the update. We are all waiting for the new Gen 2.0 version to purchase.
NOTE: In order to use the platform as a SaaS and charge other end-users, you need to purchase the Extended license. Could you please explain a bit more about it? Why we need to purchase the Extended License?
It’s a CodeCanyon license policy.
Its already next week, so are you releasing the next version or any updates please? Please confirm me either the Regular license is having full codebase for full SAAS Ready or not, or it is available in Extended License>
Hello Team, May i expect a reply for the update? Because i need to decide to purchase which App.
Hi, it’s not ready yet. Keep an eye on the product page and you will know once it’s released.
Thank you. So, when i purchase with Regular license, i will get a different code base and when i purchase with Extend support, i will get full SAAS based more featured source code?
Yes, you need to purchase the Extended License if you plan on using it as SAAS. Also, version 2.0 has been uploaded, it is currently under review by the CodeCanyon team.
New update released?
Version 2.0 is ready, we’re just doing some final tests before releasing it. Should be very soon.
How is it going? I saw the last update is from Dec 12, 2025. Is there any new update set to be released anytime soon?
Hi there, new major update (v2.0) is coming by the end of this week. Lots of new features and improvements!
also need to have other or local storeage option for logo and other things.
You can use local storage if you’re hosting the app on a VPS or any type of traditional hosting (e.g. cPanel).
If you’re hosting on a serverless platform (e.g. Vercel), you will need to integrate cloud storage since file writing is not supported on serverless platforms.
Generally, it is highly recommended to use cloud storage for a production app, due to increased security (signed URLs) and better loading speeds.
Also, we tried to reply to your email but it got rejected. Please provide us privately with a different email address we can reach you on.
i am using vps, but when uploading logo or branding its broken and showing: Cloud Storage must be configured before uploading logos or favicons.
This will be fixed in the next version.
Hi, if need razorpay payment gateway. how can be done.
Hi there, thanks for your purchase. You get full access to the source code after purchase therefore you can customize it or implement new features/integrations however you see fit.
We can also implement Razorpay for you. Feel free to reach out to us via https://codecanyon.net/user/enigmaworld and we can discuss it further if you’re interested.
The product looks strong, but sales may be constrained because the General License isn’t currently SaaS-friendly (e.g., it doesn’t clearly allow end users to charge customers). That limitation likely reduces adoption. I’d suggest offering a SaaS-ready General License—covering billing/payments and related permissions. I believe this change could materially increase your product sales.
Hi there. The licenses and what they allow are set by Envato/CodeCanyon. It is their rule that in order for you, as a buyer, you need to purchase the Extended license if you wish to charge other users.
Just think about it. it will boost your sale and you will earn more
Hi is this need API to connect for each model? For exmple if i need google nano banana dose it need to coonect thier API to script?
If i connect the API dose it going to be free to use for script as admin? or need to buy after APIs after i install the script to my server.
Yes, the app integrates with unified API providers such as OpenRouter for LLMs (GPT, Claude, Gemini, etc…), while for image and video generation models (nano banana, veo, etc…), the app integrates with Replicate.
So in summary, you need:
- API Key from OpenRouter for LLMs (GPT, Claude, Gemini, etc…)
- API Key from Replicate for image & video gen models (nano banana, veo, etc…)
You will need to add balance/credits to your OpenRouter and Replicate accounts in order to use the paid models.
Great. Dose the script support Arabic text model ?
Also can be support AI design. Like if want to design a post ? That generate AI model to design it.
Arabic language is currently not available, but can be easily added. In terms of AI design, if you’re referring to image generation and editing, yes this is supported.
cool, I mean when ask AI to design post with text I add like, ( design me a post size 9:16 with text Affliate buisness website to make money)
Dose it work like that as gemini nano banana
also can i write arabic text to design i want to generate by ai?
Thanks
If i can test it before i buy it, it will be great only test it 24 hrs
At the moment, when designing images it will use the default 16:9 aspect ratio. In the future, you will be able to configure other parameters including the aspect ratio.
Yes, you can use any language to design images.
You can test it on https://demo.weaveai.cc
Thank you. Demo won’t me generate images.
After I purchase. Can you install it to my server ?
Sorry for lots of questions
Yes image and video generation is disabled in the demo due to high cost. Installation services cost $30.
Cool. How can I contact you for installation
You can reach us via the contact form on our codecanyon profile.
Done
I would like to test the script on my own server. I don’t want to charge users, but I still want to verify how the payment setup and configuration work end-to-end.
Could you please confirm whether this is possible with the regular license (if options are available for payment etc ) ?
Regards,
Hi there, yes you can purchase the regular license to test this out, however once you decide you start charging users, you will need to upgrade/purchase the extended license.
So does this mean I’ll be able to add Stripe test credentials and run a test checkout?
Yes.
I’m using Vercel and I’ve configured R2, but I’m getting the same error that’s already been reported here:
Error: Stability AI image generation error: write EPROTO 804C5091FE7D0000:error:0A000410:SSL routines:ssl3_read_bytes:sslv3 alert handshake failure:../deps/openssl/openssl/ssl/record/rec_layer_s3.c:1605:SSL alert number 40
Hello there, have you updated to version 1.4.0? The issue with storage on serverless hosting has been fixed in the latest version.
Hi, will there be New Year’s discounts? Is there documentation on installation and setup? Thanks.
Hello- no plans for a discount at the moment. Yes, the docs can be found here: docs.weaveai.cc
