Devpost
Participate in our public hackathons
Devpost for Teams
Access your company's private hackathons
Grow your developer ecosystem and promote your platform
Drive innovation, collaboration, and retention within your organization
By use case
Blog
Insights into hackathon planning and participation
Customer stories
Inspiration from peers and other industry leaders
Planning guides
Best practices for planning online and in-person hackathons
Webinars & events
Upcoming events and on-demand recordings
Help desk
Common questions and support documentation
Sort by:
A 500M-parameter LLM triaging live sensor data on a $80 Raspberry Pi 5. Hybrid threshold+LLM pipeline holds p99 at 1,841ms with zero budget misses — 3.2x faster after systematic ARM optimization.
A portable, high efficiency photoelectric effect simulator for research purposes. Matches the Physical AI Track
Give me an Arm phone and a GGUF. ENTITY reads the silicon, tunes itself to it and proves which decision earned the speedup.
Flutter, Dart, ExecuTorch, MediaPipe, TensorFlow Lite, Sentence-Transformers, ChromaDB, FAISS, Whisper-tiny, Arm Compute Library, KleidiAI, XNNPack, Python
llama.add removes attention work a model can afford to lose, making llama.cpp faster and lighter on Arm with no retraining, no new model file, and one runtime flag.
A local RTL design agent on an 8GB ARM Mac was used to benchmark KleidiAI and quantization. Finding: Q4_0 beats the default Q4_K_M by 43% because KleidiAI has no kernel for Q4_K_M.
A fully offline Igbo speech-to-text tool on a mid-range Android phone. No cloud, no server. It runs on a Snapdragon 678 and is CPU-only.
AI vision agent that converts real-world text into instant actions — call numbers, open links, detect hazards — all fully offline on ARM devices with zero cloud dependency. ( apk link provided)
Doom online desde la comodidad de tu salon hasta el espacio.
We created a skin cancer classifier that takes an image from any part of the body, classifies it, and then outputs an interactive LLM with a diagnosis, next steps, etc.
Imagine a space where you have complete focus, entering flow-state is easy, and productivity skyrockets. That's FocusField. FocusField creates a distraction-free forcefield around you for deep work.
A small implant that quietly watches over the heart of high-risk patients. It learns each person’s normal heartbeat and gives early warnings to admins quick action before serious heart attack happens
Infinite quests. Zero prep. Pure adventure.
vibe-composer is a platform where users can give natural language prompt to generate a midi file and mp3 file.
Green Box: The 7.5ms Decision Engine. Autonomous Edge AI that predicts failure before it happens, on any plane , ship ,port , airport , factory and remote site. Renewable-powered. Arm NPU speed
Twyns — Your private AI brain built with Kiro IDE. Think smarter, create faster, and chat with AI in your own voice using Pulse Mode, fully private and personalized.
AI Helmet is a smart, edge-powered safety system that gives bike riders real-time awareness of their surroundings, detecting hazards and improving decision-making.
A tiny, low-power ARM-friendly model trained on 1.2M images for fast, private, on-device human-presence detection in the wild
An on‑device Arm AI tutor for math and basic ML that runs a tiny transformer entirely on your phone, delivering fast, private explanations and quick checks with zero network.
Bringing professional photo restoration to mobile with on-device AI
ArmVision: Real-time AI image recognition, optimized for mobile Arm devices—fast, local, and cloud-free.
Hawker-ID bridges street vendors and communities through intelligent audio detection, empowers ARM edge devices to recognize hawker calls, enabling real-time notifications and local commerce support.
Guiding your focus with subtle cues,never your data.
TwynAI is your second AI brain, an on-device Llama powered companion built with ExecuTorch + Flutter, fully optimized for ARM, with Cartesia AI for Voice Cloning and running privately with zero cloud.
