The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Back to feedPost
:Nikit — Local-First AI Desktop Application
Nikit is a local-first AI desktop application I designed and built around my custom ZaqX language model. The project combines a modern desktop interface with local AI inference, context handling, tool controls, and a privacy-focused architecture.
I built the application with React, TypeScript, Vite, Tauri, and CSS Modules, with a modular architecture designed for performance and maintainability. The project also includes a custom small language model and supporting AI infrastructure.
The goal was to create a practical AI workspace that feels like a real product rather than a simple chatbot, while keeping the experience fast, focused, and local-first.
The network for creativity
Join 1.25M professional creatives like you
Connect with clients, get discovered, and run your business 100% commission-free
Creatives on Contra have earned over $150M and we are just getting started
Related posts
Making components with an AI agent for my new Framer project. So far, I’ve made a background with adjustable square sizes, gaps, spacing, and colors, plus an animated text box, put them together in a little shot. I’m enjoying experimenting with small animations that don’t make the screen feel too busy.
The dotted gradient stays quiet while the coral on “recurring work” carries the hero. That small text motion feels like a system, not extra noise.
Introducing AgroGPT 🌱 An AI agriculture assistant built for farmers across Bangladesh.
AgroGPT brings farming guidance and local information together in one mobile experience:
🌾 Six AI specialists covering crops, cattle, poultry, aquaculture, soil, and research
🌦️ Weather forecasts focused on crop risks
📊 Live bazar prices to support market decisions
📰 Agricultural news and updates
💬 AI chat for everyday farming questions
The design pairs a fresh green palette with clear navigation and dedicated specialist tools, making a wide range of information easier to explore.
What feature would you find most useful in an agriculture app?
Two ways to build the same fitness app.
A: AI-first. No tabs, no dashboards. The app is one conversation with a coach that already knows you slept six hours and squatted heavy on Tuesday. You log sets by talking. The plan rewrites itself mid-workout.
B: The modern standard. Home, today's workout, set-by-set logging, class booking, progress. Everything a member expects, done properly.
Same brand, same components, same build quality. The only real difference is how much you're asking the user to unlearn.
Most gyms should ship B. A few should bet on A.
Which one would you open tomorrow morning?
1 voted
25%
3 voted
75%
4 votes
Closed
Going with A here, the idea of the plan rewriting itself mid-workout instead of you scrolling a dashboard feels like where fitness apps eventually land. Would you actually ship the AI-first version to real users right now, or is it more of a thought experiment at this stage?