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:
An AI-powered personalized learning assistant that turns any topic into interactive lessons, quizzes, visual explanations, and adaptive study plans based on each learner's level, goals, and progress.
Adaptive Socratic AI learning studio featuring 5 interactive mental model sandboxes, Web Speech voice tutoring with misconception diagnostics, and a 4-tier Feynman Simplifier (ELI5 to PhD).
"CineDirector AI: Directing the future of automated filmmaking with intelligent agent workflows."
Helping farmers reduce post-harvest food waste by connecting produce to timely market opportunities with AI-powered intelligence.
Beyond tracking. Understand your health.
AI-powered emergency response through USSD, automated alerts, and an IoT-ready responder network—even without mobile internet.
Autonomous StreamOps platform that uses ClickHouse real-time telemetry and Gemini to diagnose and fix video audience retention drop-offs.
Turn any material into a personalized learning journey.
PROVENANCE make AI conclusions traceable and trustworthy by linking sources evidence claims and conclusions while detecting contradictions testing whether conclusions survive changes
Care When Doctors Aren’t Around.”
Document your tennis serve, track your progress and improve your game.**
A local-first conversational shopping agent that tracks changing intent and finds the right product earlier.
An offline, evidence-aware conversational shopping search agent that follows evolving intent and constraints to surface the right product faster.
Give it a benchmark and walk away. An agent that does the part of ML research nobody enjoys: 40 experiments at 2am. It found a feature we'd missed, and stopped itself when it stopped learning.
A stateful shopping agent that asks smarter questions, adapts to changing intent, and ranks the right products quickly and reliably.
A universal autonomous RecSys research agent with adversarial peer-review & 4-pillar taxonomy that iteratively invents, optimizes, and converges PyTorch models.
An autonomous recommender research agent that safely proposes, tests, and audits model improvements inside an isolated sandbox.
Agent AI-yoh is an autonomous AutoML research agent that designs, runs, and audits recommender-system experiments, helping teams discover better models with reproducible, trustworthy evidence.
A shortcut-resistant AIGC image ranker built to retain evidence across real-world redistribution and unseen generator families.
An autonomous ranking agent that tests ideas across time, rejects fragile gains, and preserves reproducible evidence.
An autonomous ML research agent for recommender systems that tries to disprove its own findings. It found a +0.0314 result, proved it was worth +0.0023, and reported the smaller number.
We built a 21.7M-parameter ViT detector for robust AI-image detection, scoring 0.9362 across unseen generators, with deployment via Chrome extension and future TikTok integration.
Most AI-image detectors ace clean benchmarks and collapse on real uploads. Ours holds 0.99 AUROC across every compression, blur, crop and noise level tested, and 0.95 on a generator it has never seen.
AI-image detectors often fail after images are compressed, resized, or reposted. InvariantGuard keeps working anyway.
