A programmer who loves to secure and break the code.
A programmer who loves to secure and break the code.
Full-Stack Developer | SaaS, Business Website, Web Apps
- 5.0
- Rating
- 9
- Followers
Full-Stack Developer | SaaS, Business Website, Web Apps
Tailor-Made iOS Solutions with a Decade of Expertise
- $1k+
- Earned
- 4x
- Hired
- 5.0
- Rating
- 71
- Followers
Tailor-Made iOS Solutions with a Decade of Expertise
Turn Your Ideas Into AI powerd SaaS with @Sunstroke
Most small brands lose sales in their DMs, not their ads. Someone asks "price?", you reply 6 hours later, and they've already bought somewhere else.
I set up DM automation for your Instagram: instant replies to comments and DMs, price and FAQ answers, and a link to buy, all running while you sleep.
Done-for-you setup: $149. Comment SETUP and I'll send you the details.
0
35
Built Cronos because I was spending more time managing projects than building them. It runs on Gemini 2.5 Pro and actually understands the context of your work — generates tasks, summarizes progress, flags blockers before they happen. "Project Manager in a Box."
Try it, link - https://lnkd.in/dnGBgd_U
hashtag#indiehacker (https://www.linkedin.com/search/results/all/?keywords=%23indiehacker&origin=HASH_TAG_FROM_FEED) hashtag#saas (https://www.linkedin.com/search/results/all/?keywords=%23saas&origin=HASH_TAG_FROM_FEED) hashtag#productivitytools (https://www.linkedin.com/search/results/all/?keywords=%23productivitytools&origin=HASH_TAG_FROM_FEED) hashtag#buildinpublic (https://www.linkedin.com/search/results/all/?keywords=%23buildinpublic&origin=HASH_TAG_FROM_FEED) hashtag#aitools (https://www.linkedin.com/search/results/all/?keywords=%23aitools&origin=HASH_TAG_FROM_FEED) hashtag#solofounder (https://www.linkedin.com/search/results/all/?keywords=%23solofounder&origin=HASH_TAG_FROM_FEED)
2
109
Fullstack Developer - Mobile App, Web, UI/UX & No-Code build
Fullstack Developer - Mobile App, Web, UI/UX & No-Code build
Full Stack Engineer
Web, mobile and enterprise application development expert
- 5.0
- Rating
- 11
- Followers
Web, mobile and enterprise application development expert
Full Stack AI Engineer | Building AI-Powered SaaS, LLM Apps
Full Stack AI Engineer | Building AI-Powered SaaS, LLM Apps
One AI integration. Multiple providers. Two languages. Meet Xoin.
Building AI-powered applications often means dealing with multiple provider SDKs, different response formats, structured output validation and provider-specific implementations.
I wanted to make that experience simpler.
Introducing Xoin, an open-source, multi-provider LLM client available for both JavaScript/TypeScript and Python.
Instead of managing completely different integration patterns for every provider, Xoin gives developers a consistent interface to work with multiple LLM providers.
Two libraries. One developer experience.
01. Xoin for JavaScript / TypeScript
@xoin/xoin-js
Unified multi-provider LLM interface
Structured outputs with Zod validation
Text embeddings for semantic search and RAG
Reusable prompt templates
Automatic provider fallback
Multi-provider routing
02. Xoin for Python
xoin-py
Async-first architecture
Structured outputs with Pydantic
Multi-provider chat completions
Embeddings with supported providers
Automatic retries and provider fallback
Reusable prompt templates
Supported AI providers
OpenAI · Anthropic · Gemini · Mistral · DeepSeek · OpenAI-compatible APIs
Why does this matter?
Imagine building an AI application that uses OpenAI today but needs to switch to another provider tomorrow.
You shouldn't have to redesign your entire integration layer.
Xoin helps abstract provider differences, validate model outputs and make provider fallback easier to manage.
The goal is simple:
Less provider-specific glue code. More time building actual AI products.
Get started
JavaScript / TypeScript:
npm install @xoin/xoin-js zod
GitHub: https://github.com/kanha95/xoin-js
Python:
pip install xoin-py
GitHub: https://github.com/kanha95/xoin
Both projects are open source.
If you're building AI agents, RAG pipelines, LLM-powered SaaS products or backend AI services, I'd love to hear your thoughts.
One question for developers:
When building multi-LLM applications, do you prefer a unified abstraction layer or direct integration with each provider?
Let's discuss.
#OpenSource #ArtificialIntelligence #LLM #Python #JavaScript #TypeScript #AIEngineering #RAG #DeveloperTools #BackendDevelopment
0
10
Camsur AI Studio - An AI-Powered Photo Creation Platform
Transform everyday selfies into professional-looking photos with AI.
Camsur AI Studio is a complete AI photo generation and editing platform designed to make professional photo creation accessible through a simple mobile experience.
The platform allows users to explore specialized photo tools, upload a selfie, select a desired transformation, and generate images using AI-powered editing workflows.
I built the product as an integrated mobile application and backend ecosystem, with user authentication, image processing, credit-based usage, secure storage, and administrative capabilities.
The Product Experience
Users can access a collection of AI photo tools designed for different needs:
AI Headshots: Create professional-looking profile photos from casual selfies.
LinkedIn Photos: Generate polished professional profile pictures.
Passport Photos: Prepare clean, plain-background portrait images.
Background Editing: Remove or change image backgrounds.
Creative Photo Editing: Explore different photo styles and transformations.
Key Product Features
Mobile-first application with an intuitive user experience.
AI image generation and editing powered by Black Forest Labs FLUX.
Photo uploads through the camera or gallery.
User authentication with email, Google, and Apple.
Credit-based wallet with top-ups and transaction history.
Generation history and before-and-after comparisons.
Automatic credit refunds when image generation fails.
Private image storage with expiring signed URLs.
Administrative APIs for users, tools, packages, analytics, and refunds.
Usage limits, rate controls, and AI generation cost management.
Product Architecture
The application connects a Flutter mobile experience with a Python FastAPI backend, using Supabase for authentication, PostgreSQL, and storage.
The architecture includes a dedicated AI provider layer, credit accounting, backend-controlled pricing, and safeguards against duplicate credit charges.
My Contribution
I worked across the product lifecycle, including application development, backend functionality, AI integration, credit management, database workflows, and product infrastructure.
The result: A complete, extensible AI photo application demonstrating how an AI-powered consumer product can combine an intuitive mobile experience with real business and billing workflows.
Project focus: AI Photo Generation · AI Image Editing · AI Headshot Generator · Mobile Applications · AI SaaS · Credit-Based Platforms · Product Engineering
0
40
Sinpoura AI - A Unified Workspace for Multiple AI Models
One workspace. Multiple AI models. Organized conversations.
Sinpoura AI is a modern multi-model AI chat application designed to bring AI conversations, saved discussions, and model integrations into one clean, productive workspace.
Instead of building around a single AI provider, Sinpoura uses a structured multi-provider architecture that connects different language models through one consistent application experience.
Users can create an account, start conversations, organize chat history, configure AI providers, and continue working from a responsive interface.
What the Platform Offers
Multi-Model AI Chat: Connect with supported AI providers, including OpenAI and Anthropic.
Persistent Conversations: Create, retrieve, manage, and delete saved chat threads.
Personal Workspace: A dedicated conversation sidebar and organized chat experience.
Bring Your Own Key (BYOK): Allow users to configure their own supported AI provider credentials.
Quick Prompts: Ready-to-use prompts for writing, studying, debugging, summarizing, and more.
Model Configuration: Manage provider settings and model preferences.
Secure Authentication: Registration, credentials-based sign-in, and protected chat access.
Responsive Experience: Interfaces designed for desktop, tablet, and mobile.
Personalization: Light, dark, and system appearance modes.
Behind the Product
Sinpoura uses xoin-js as its structured multi-provider LLM integration layer.
The application uses server-side chat handling, conversation persistence, input validation, and provider configuration to keep the chat experience organized and extensible.
It also includes browser-based BYOK configuration. User-provided API keys are kept in browser local storage and sent with chat requests; they are not persisted in MongoDB.
Search & Sharing Foundations
The application includes structured page metadata, Open Graph and Twitter images, JSON-LD WebApplication data, sitemap and robots configuration, and public-route SEO foundations.
My Contribution
I developed the application experience and its supporting architecture, including the chat workspace, authentication, conversation management, multi-provider AI integration, and responsive user interface.
The result: A functional multi-model AI chat application and an extensible foundation for building customized AI assistants, internal AI tools, and conversational products.
Project focus: AI Chat Application · Multi-LLM Integration · OpenAI · Anthropic · AI Workspace · Next.js Application · MongoDB · BYOK · Conversational AI
0
45
SuriComAI - Exploring a Decentralized AI Inference Network
Rethinking how AI computation can be coordinated, executed, and verified.
SuriComAI is an experimental infrastructure project exploring a decentralized approach to AI inference using distributed computing nodes, cryptographic verification, and an open-hardware-oriented architecture.
The vision is to create an alternative to relying entirely on centralized AI infrastructure: users submit inference jobs, computing nodes execute approved models, and independent verification mechanisms check the resulting proofs.
I developed the project's Rust-based protocol and reference implementation, exploring the foundations of secure job execution, model approvals, proof verification, and distributed coordination.
Core Concepts & Implemented Components
Sealed Job Envelopes: Cryptographic mechanisms for protecting job payloads during the reference execution flow.
Proof Verification: Independent Rust and Python verifiers for checking inference-job receipts and proofs.
Model Approval System: Signed model manifests and approval records with expiration and revocation.
Node Execution: A local reference node and client for running inference workflows.
Secure Communication: Authenticated communication channels between the reference client and node.
Job Settlement Logic: Reference escrow rules and an in-process settlement simulator.
Replay Protection: Receipt and job checks designed to prevent replay and invalid settlement.
Developer Interfaces: Rust workspace, command-line tools, and a local desktop application.
Technical Exploration
The project explores decentralized AI inference, confidential computing, cryptographic job envelopes, distributed execution, and independently verifiable computation.
The implementation includes Rust-based protocol components, a Python proof verifier, shared test vectors, and reference smart-contract code.
My Contribution
I designed and implemented the project's core reference architecture, including the Rust workspace, cryptographic job flow, model approval mechanisms, proof verification components, and local development experience.
Current Development Status
SuriComAI is an early-stage prototype, not a launched decentralized network.
The reference implementation can demonstrate local sealed-job execution and proof verification, but public network nodes, hardware-backed privacy using Intel TDX or AMD SEV-SNP, deployed audited escrow, wallets, and real payments are not yet implemented.
It is not currently suitable for protecting real sensitive data or handling real funds.
Project focus: Decentralized AI · AI Infrastructure · Distributed Computing · Rust · Cryptographic Verification · Confidential Computing Research · Peer-to-Peer Systems
0
56