
Hacktoberfest Hack Day Jaipur x Hack IT Sapiens
About
Hacktoberfest Hack Day Jaipur x Hack IT Sapiens is a one-day, in-person hackathon bringing together students, developers, working professionals, and early-stage builders to turn ideas into working prototypes using open-source and open-weight AI.
The event features Four prize categories:
- Best Use of Gemma 4
- Best Open-Source AI Project
- Best Local Agentic Tool
- Edge & Physical AI: Intelligence Beyond the Cloud
Your project can address any problem domain, with open-source or open-weight AI at its core. Explore the category descriptions below for their specific technical and submission requirements.
The day includes 5 hours of dedicated hacking time, alongside registration, team formation, technical guidance, project demonstrations, judging, and closing activities.
Participate in teams of 2–4 members. Every team member must register individually.
Whether this is your first hackathon or you’ve built at many before, come ready to learn, experiment, collaborate with fellow builders, and ship something over tea.
Looking for teammates or have questions? Join our event WhatsApp group to meet other participants, find your build crew, and connect with the organisers:
https://chat.whatsapp.com/E0MzKXIhwC9ErysJQJ9vLt?s=sh&p=a&mlu=4&ilr=4
Prize Categories
4 categories- View Best Open-Source AI Project

Best Open-Source AI Project
Exclusive Hacktoberfest 2026 Winner DEV Badge & MLH Swag Bag
Build an original project that uses open-source or open-weight AI as an important part of how it works. Teams could create an agent skill, build with an open-weight large or small language model, or build or adapt an open-source model harness.
Build with DigitalOceanView category - View Best Local Agentic Tool/ Edge AIEvent prize
Best Local Agentic Tool/ Edge AI
Build a narrow, single-purpose agentic tool that reliably replaces one real task, with the model generating responses running entirely on your own hardware.
- Local inference only: no hosted/frontier model APIs (OpenAI, Anthropic, Gemini, etc.) in the final submission
- Open-source or open-weight model
- Non-generative external tools (web search, APIs) are allowed
- One clearly defined task, not a general assistant
- Public GitHub repo, open-source license
- State the model used, its parameter count, and minimum hardware tested on
- Show 3 repeated runs demonstrating consistent output
- Scored on task success rate, reliability, and practical usefulness, with tokens-per-second as a tie-breaker
View category - View Best Use of Gemma 4
Best Use of Gemma 4
It’s time to see how much you can build with a lightweight, open model. Gemma 4 packs multimodal intelligence into an open-weights model that you can access through the Gemini API. So, what can Gemma 4 bring to your project?
- Multimodal Experience: Work with text and images to create an assistant that understands more of what users share.
- Focused AI Tools: Build a focused AI tool for learning, creativity, productivity, or your community.
- Rapid Prototyping: Experiment with an open model while using the Gemini API to move quickly from an idea to a working prototype.
Bring your idea to life… what will you build with Gemma 4 today?
Build with Gemma 4View category - View Physical AI: Intelligence Beyond the CloudEvent prize
Physical AI: Intelligence Beyond the Cloud
Build AI systems that run completely offline on a separate physical device. Use Raspberry Pi, ESP32, Arduino-compatible boards, or other embedded hardware to create intelligent systems that interact with the real world through sensors, cameras, motors, and other components.
What can you build?
- Offline AI devices that sense and respond to their surroundings.
- Smart systems using cameras, sensors, or embedded hardware.
- TinyML applications running on resource-constrained devices.
Challenge Requirements
- AI inference must run locally on the device, without internet or hosted AI APIs.
- Use an open-source or open-weight model meaningfully.
- Submit a public GitHub repository with an open-source license and demonstrate a working prototype.
View category