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:
Video in, SQL out. An OpenCV 5 agent turns video into tables you can query with SQL, every row traced to a second of footage.
Perception-to-Action with OpenCV 5 on AWS
OmniGuard AI is an autonomous, multi-hazard computer vision system and real-time public safety monitoring hub designed for smart city infrastructure.
Phone photo in, OpenCV triage out. LookAgain uses vision metrics to pick the next tool—retake, compare, or bounded diagnose - across LEDs, brakes, and leaf spots. Bedrock + SIFT on AWS COOL.
A camera watches a home, but nobody watches the camera. Hearthwatch turns that camera into an agent that perceives, decides, acts — and then checks its own work.
QRensic: An AI-powered visual fraud investigation system that analyzes QR-code evidence using OpenCV 5 and orchestrates forensic checks with an agent designed for Amazon Bedrock.
An honest Arm workload benchmark and comparison studio
A CNN trained from scratch on real breast-ultrasound images, with Grad-CAM heatmaps showing exactly where it looked — explainability you can see.
An automated AI WhatsApp assistant for smart message processing and instant auto-replies.
⚡ Zero-config, self-evolving local AI agent framework — multi-agent orchestration, GraphRAG memory, IDE integration. Runs 100% locally with Ollama.
🚀 Autonomous test-time compute scaling & dynamic KV-cache sparsification for edge LLMs — pure-PyTorch MCTS reasoning engine, −65% VRAM. R1-style thinking on consumer hardware.
SafeSight AI is an Agentic Vision system designed to improve industrial workplace safety using OpenCV 5 and AWS. It analyzes video footage to detect people entering restricted .
A fail-closed coating inspector: OpenCV 5 measurements choose the next tool. Empty detections cannot auto-PASS. Inpaint is reconstruction, not a new capture.
DeskZen uses OpenCV 5 and AWS Bedrock (Amazon Nova Pro) to score workspace visual entropy, detect liquid/cable hazards, generate interactive triage cards, and verify decluttering in an agentic loop.
Generate the art as a paper doll - parts drawn separated and completem then let an agent run a perception-decision-action loop, assembles and renders the rig.
An OpenCV 5 and AWS-powered agentic vision system that detects crop diseases, explains its predictions, and delivers actionable insights to help farmers protect crops and improve food security.
Aegis sees people and boats in the water, then dispatches help, reroutes rescue, or calls a human.
FlowSense helps governments prioritize mobility interventions, coordinate road access across agencies, and build evidence for better public investment.
Sight Companion Live A privacy-first visual copilot that turns live camera perception into actionable guidance for blind and visually impaired people.
Verified-action visual operations with OpenCV 5 and AWS: See → Reason → Ask → Act → Verify → Prove.
An AI tool using OpenCV and AWS to monitor construction sites and detect safety helmet compliance in real time.
AI-powered intelligence that turns complex information into clear, actionable insights.
MediCompare — Compare medicines, prices, and alternatives in one place, helping users make informed and affordable healthcare choices.
An OpenCV 5 privacy agent that catches faces, QR codes, and text regions before a screenshot becomes a public incident.
