From ‘We Should Hang Out’ to Actually Going

Sakshi Pathrikar — Sun, 11 Oct 2026 21:47:17 +0000

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass

What I Built

It’s easy to say “we should hang out sometime” and never make a plan. TouchGrass helps turn that idea into a real group outing: find a place, choose a mood and budget, check availability, and put together an itinerary with optional mini-quests.

It’s for friends and groups who want to spend more time together offline without making the planning itself a project. The app uses real place results from OpenStreetMap and can include a forecast when one is available. It also treats disconnected calendar availability as unknown, not as proof that someone is free.

Code

pathrikarsatwit / TouchGrass

TouchGrass

Less scrolling. More living. A cross-platform social adventure planner for turning “we should hang out sometime” into a real plan.

TouchGrass is an Expo + TypeScript app with a FastAPI service, a local SQLite demo mode, optional Supabase-backed persistence, Google and native device-calendar availability, friend/group invitations, push notifications, and private quest-photo storage. OpenStreetMap place discovery, optional Ollama itinerary generation, and forecast-aware planning round out the hangout flow.

Integration status: these provider flows are implemented but require your own Supabase project, Google OAuth credentials (for Google Calendar), EAS/APNs/FCM configuration (for push), and an iOS/Android development build (for native calendar access). They have not been validated against your provider accounts or a production deployment. The backend uses its Supabase service-role key, which bypasses RLS; keep it server-only and complete deployment hardening and multi-user authorization testing before using real users or private data.

The current Expo/Metro dependency tree still reports upstream moderate/high…

View on GitHub

How I Built It

The app is built with Expo and TypeScript, with a FastAPI backend and local SQLite demo mode. Supabase-backed persistence is optional.

The itinerary generator has an optional integration with Qwen3 8B via Ollama, an open-weight model that can run locally. The backend first verifies the destination, then sends the model only the place name, address and category, along with non-sensitive preferences such as mood, budget and outing length. The model returns a constrained JSON draft that the app validates before it can be used.

A note on the current demo: Ollama is optional and wasn’t configured for the local run, so the app uses a clearly labeled deterministic fallback instead of presenting it as AI-generated. The model integration is implemented, but still needs to be tried with a configured Ollama instance.

Why Does Open Innovation Matter?

For a planning tool, people’s calendars and preferences can be personal. An open-weight model gives developers the option to run inference locally or on infrastructure they control, rather than making a closed AI API the only path. It also makes the model choice replaceable as the project evolves.

Just as importantly, the app remains useful without a model. Open innovation here means being able to inspect and adapt the AI path, while keeping a predictable fallback for people who don’t have the model—or the hardware—to run it.

Prize Categories

Best Use of GitHub Copilot — I used Copilot CLI while getting the Expo app running, including troubleshooting and fixing the missing react-native-web dependency that blocked the web build

Daywell: A More Realistic, AI-Powered Planner

Sakshi Pathrikar — Sun, 04 Oct 2026 21:54:59 +0000

What I Built

I built Daywell, a personal planner for my friend who has trouble keeping a track of their daily activities and ends up over scheduling. It combines tasks, reminders, a daily schedule, and productivity insights to help make busy days more manageable.

Daywell calculates planned and available time, flags overloaded schedules, and suggests tasks to move. Over time, it tracks what gets completed or postponed, so its monthly analytics can reveal patterns—like which days or hours tend to be most productive.

Demo

There isn’t a hosted demo yet. You can run the app locally by following the instructions in the README.

Code

View the Daywell GitHub repository: https://github.com/pathrikarsatwit/AI-Reminders

How I Built It

Daywell is a responsive React, TypeScript, and Vite web app. Tasks and productivity history are stored in the browser. Scheduling and analytics are calculated by deterministic application code—not by an LLM.

For AI insights, I built a provider boundary around Google’s open-weight Gemma, served locally with Ollama. When someone requests insights, Daywell sends aggregated statistics and supporting evidence to their local inference server; it does not send raw task names or notes. This keeps the AI optional and leaves room for other local inference setups in the future.

I also used GitHub Copilot during development to help build the app incrementally and refine its features.

Why Does Open Innovation Matter?

Productivity data is personal. Using an open-weight model with local inference makes it possible to get AI-generated observations without making a proprietary cloud AI API the core of the app. The app can keep task history in the browser and share only aggregate data with a local model when the user asks for insights.

Open tools and models also make the AI layer easier to inspect, adapt, and extend as local inference options evolve.

Prize Categories

• Best Use of GitHub Copilot

DEV Community: Sakshi Pathrikar

From ‘We Should Hang Out’ to Actually Going

What I Built

Code

pathrikarsatwit / TouchGrass

TouchGrass

How I Built It

Why Does Open Innovation Matter?

Prize Categories

Daywell: A More Realistic, AI-Powered Planner