🌿 TrailMate AI — Your Offline AI Outdoor Companion
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built
TrailMate AI is an offline-first AI outdoor companion designed to help people spend less time looking at screens and more time exploring the real world.
The idea is simple:
Discover → Get a mission → Put the phone away → Explore → Return → Record your discovery → Earn XP.
TrailMate allows users to take or upload a photo of a plant or natural object. A local open-weight AI model analyzes the image and provides information about the discovery.
Instead of keeping the user inside the application, TrailMate then creates a short outdoor mission.
For example:
🌿 Outdoor Mission
Find another tree nearby and compare its leaves with the plant you just discovered.
+20 Explorer XP
The user can activate Touch Grass Mode, put their phone away, and complete the mission outside.
After returning, they can record what they discovered in their Nature Journal and earn Explorer XP.
Who is it for?
TrailMate is designed for:
- 🌱 Students
- 🥾 Hikers and walkers
- 🌳 Nature lovers
- 🐦 Outdoor explorers
- 👨👩👧 Families
- Anyone who wants a reason to spend more time outdoors
The goal isn't to make people spend more time using an AI app.
The goal is to make them stop using it and go outside.
Demo
🎥 Demo Video:
[Add your YouTube/Loom/demo video link here]
🌐 Live Demo:
[Add your deployed Streamlit link here]
The demo shows:
- Opening TrailMate AI
- Uploading a plant photo
- Local AI analyzing the image
- Receiving plant information
- Generating an outdoor mission
- Activating Touch Grass Mode
- Recording the outdoor discovery
- Earning Explorer XP
- Viewing the Nature Journal
Note: The full offline experience requires Ollama and the selected local model to be installed on the user's machine.
Code
💻 GitHub Repository:
[Add your GitHub repository link here]
The repository contains the complete source code, setup instructions, AI prompts, database implementation, and documentation.
Main technologies
- Python
- Streamlit
- Ollama
- Gemma / open-weight AI
- Pillow
- SQLite
- Git & GitHub
How I Built It
TrailMate AI is built around local open-weight AI rather than a proprietary cloud AI API.
The core architecture is:
🌿 TRAILMATE AI
│
↓
Streamlit UI
│
↓
Python App
│
┌─────────────┴─────────────┐
↓ ↓
Image Input User Input
│ │
└─────────────┬─────────────┘
↓
Ollama Runtime
│
↓
Open-Weight AI Model
│
┌─────────────┼─────────────┐
↓ ↓ ↓
Identification Missions AI Feedback
│ │ │
└─────────────┼─────────────┘
↓
Nature Journal
│
↓
XP System
│
↓
🌳 GO OUTSIDE
Local AI
I use Ollama to run the AI model locally.
The model handles tasks such as:
- Nature image analysis
- Plant identification assistance
- Outdoor mission generation
- Nature observation feedback
- Nature journal assistance
The application communicates with the local Ollama service instead of requiring a paid cloud AI API for its core AI functionality.
Application
The user interface is built with Streamlit.
Python handles:
- Application logic
- Image processing
- Ollama communication
- Mission generation
- XP calculations
- Database operations
Storage
TrailMate uses SQLite for local storage.
It stores information such as:
- Discoveries
- Missions
- User observations
- XP
- Progress
Why Does Open Innovation Matter?
Open innovation is especially important for TrailMate because the application deals with personal observations, images, and outdoor exploration.
Using local open-weight AI provides several advantages.
🔒 Privacy
The core AI processing can happen locally.
A user's nature photos and observations don't need to be sent to a proprietary AI server just to receive an answer.
📴 Offline Potential
Once the required model and dependencies are installed, the core AI experience can work without continuously requiring an internet connection.
This is especially useful for outdoor environments where network connectivity may be weak or unavailable.
🔄 Model Freedom
Because the system is built around a local model runtime, the AI model can be changed as better open models become available.
The project isn't locked into a single proprietary API.
💰 Lower Running Cost
There is no per-request cloud AI API cost for the core local inference.
This makes experimentation and personal use much more accessible.
🛠️ More Control
Using open-weight AI allows developers to experiment with:
- Prompts
- Models
- AI behavior
- Local inference
- Future fine-tuning
- Custom nature datasets
A closed API could provide image analysis, but the open approach gives TrailMate much more control over where the AI runs and how it can evolve.
The "Touch Grass" Philosophy
The most important design decision in TrailMate is that the AI should not become another reason to stay on the screen.
Many AI applications encourage users to keep chatting.
TrailMate does the opposite.
The application gives the user a short interaction:
📷 Discover something
↓
🤖 AI explains it
↓
🥾 AI gives you a mission
↓
📱 Put the phone away
↓
🌳 Go outside
↓
👀 Explore
↓
📔 Record what you discovered
↓
🏆 Earn XP
The screen is only a tool to start and finish the experience.
The real product is the outdoor experience.
Example Outdoor Mission
After identifying a plant, TrailMate might generate:
🌳 Explorer Mission
Find two other plants within your surroundings.
Compare their leaf shapes and sizes.
Don't search for the answer online.
Observe first.
Difficulty: Easy
Reward: +20 XP
This encourages curiosity and direct observation rather than immediately searching the internet.
Explorer XP
TrailMate includes a simple gamification system.
Examples:
🌿 Identify a plant +10 XP
🥾 Complete a mission +20 XP
📔 Add a journal entry +10 XP
🐦 Observe a bird +15 XP
🌳 Make a new discovery +25 XP
Explorer levels can grow from:
🌱 Beginner Explorer
↓
🌿 Nature Explorer
↓
🌳 Trail Explorer
↓
🥾 Outdoor Adventurer
↓
🏆 Nature Master
My Agent Session
🤖 DevRelay Agent Session:
[Add your DevRelay agent session link here]
The session shows how TrailMate was developed and how the AI-assisted development process was used.
Prize Categories
I am entering this project for:
🌿 Touch Grass
TrailMate is specifically designed around the challenge theme by encouraging users to leave the screen, explore their surroundings, and complete real-world outdoor missions.
🤖 Open-Source AI
The core AI experience is built around an open-weight model running locally through Ollama rather than relying on a proprietary cloud AI API.
📴 Local / Offline AI
TrailMate is designed with an offline-first architecture so that the core AI experience can operate locally after the required model and dependencies are installed.
What's Next?
The current project focuses on the core outdoor exploration experience.
Future versions could add:
- 🐦 Offline bird-call identification
- 🌱 More advanced plant recognition
- 🗺️ Nature trail recommendations
- 🌦️ Weather-aware outdoor missions
- 🎙️ Voice interaction
- 📍 Local biodiversity information
- 📴 Better offline maps
- 🏆 Group/family outdoor challenges
- 🧠 Fine-tuning with local nature datasets
The long-term goal is to make TrailMate a personal AI guide for exploring the physical world.
Final Thought
AI doesn't always need to keep us in front of a computer.
Sometimes the best thing an AI can do is tell us:
"You've learned enough. Put the phone down and go see it yourself." 🌳
That's what TrailMate AI is trying to build.
👥 Team
Project: TrailMate AI
Challenge: Hacktoberfest Open-Source AI Challenge — Week 1: Touch Grass
Creator: Root Kevadiya
Top comments (1)
This concept is so refreshing! Too‑many AI apps want you glued to your screen, but TrailMate AI’s whole goal is to get users outside and put the phone away. I really like the offline‑first Ollama‑powered design, plus the XP and nature journal gamification loop. Running everything local keeps plant photos from hitting third‑party servers, which is a huge privacy win for outdoor hobbyists.