This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built
What if we used AI for the opposite of what we normally use it for?
Instead of giving people another reason to stay on their screens, AI Outdoor Quest gives people a reason to go outside.
AI Outdoor Quest is an open-source AI-powered outdoor mission generator.
You tell it something simple like:
"I have 30 minutes and want to do something outside."
AI Outdoor Quest turns that into a personalized outdoor quest based on your time, interests, and activity.
For example:
- 🌳 Find three different types of trees
- 🚶 Walk for 10 minutes
- 👂 Stop and notice three different sounds
- 📸 Find something you've never noticed before
- 🧭 Explore a different route
- 🧘 Spend five minutes outside without looking at your phone
The idea is simple:
Start a quest → put the phone away → go outside. 🌿
The screen should be the shortest part of the experience.
Code
💻 GitHub: - AI Outdoor Quest
The project is being developed openly as part of Hacktoberfest 2026.
How I Built It
AI Outdoor Quest is built around open-weight AI.
The AI is used as the quest-planning engine. It takes the user's available time, preferences, and activity goals and turns them into a structured outdoor experience.
The broader application is being designed around:
- 🤖 Gemma — personalized outdoor quest generation
- 🌐 SerpApi — live information for context-aware quests
- 🧠 MongoDB Atlas — storing quest history and user preferences
- 🔊 ElevenLabs — voice guidance so users don't need to constantly look at their screen
- ⏱️ Temporal — durable and resumable outdoor quests
- 📊 Sentry — AI agent tracing and observability
- ☁️ DigitalOcean — application and AI infrastructure
Each technology has a specific role in the application rather than being added just for the sake of using another tool.
Why Does Open Innovation Matter?
AI is increasingly becoming something we interact with through a screen.
I wanted to try the opposite:
What if AI helped us spend less time with technology?
Using open-weight AI gives the project the flexibility to experiment with different models, customize how quests are generated, and run the AI locally where practical.
It also means the project can evolve for different types of outdoor activities and communities.
The AI doesn't need to keep you talking to it.
Its job is to give you something to do in the real world.
Prize Categories
- 🟢 Gemma — using an open-weight Gemma model for personalized outdoor quest generation.
- ☁️ DigitalOcean — deploying the application and supporting AI infrastructure on DigitalOcean.
- 🔊 ElevenLabs — providing voice guidance so users can follow quests without constantly looking at their screen.
- 🌐 SerpApi — using live search to make outdoor quests more relevant to the user's surroundings.
- 🧠 MongoDB Atlas — storing outdoor experiences and preferences for longer-term personalization.
- 📊 Sentry Agent Tracing — tracing and understanding the AI agent's execution.
- ⏱️ Temporal — making longer-running outdoor quests durable and resumable.
🌿 Start a quest. Put the phone away. Go outside.
Top comments (0)