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:
Online shoppers rarely describe the perfect product in one query. They explore, add constraints, and sometimes change their minds. We built Shopping Copilot to handle exactly that.
An autonomous ML research agent. It verifies its own results instead of trusting them, and beats the baseline where a greedy agent scores below it.
TikTok TechJam「Autonomous ML Research Agent for Recommender Systems」
Hand-written Triton attention kernels, benchmarked against the baseline, with shape-aware dispatch choosing the fastest path per case with every optimization validated and explainable.
This is an AI image detection software pilot project.
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.
AI-image detectors often fail after images are compressed, resized, or reposted. InvariantGuard keeps working anyway.
Hardware-aware Transformer kernel optimization that automatically matches each workload to the right GPU optimization strategy.
Shopping Butler finds your dream product in ≤10 chat turns using BM25 phrase-scoring and a gated local LLM, proving smart retrieval beats brute-force LLM use.
A conversational shopping copilot that understands vague requests, remembers evolving preferences and delivers accurate recommendations quickly—without paid APIs.
How AI Helps Content Teams Scale Blog Production
What's your idea? This will be a short tagline for the project
WIP
A student-built platform where people and AI agents can navigate, learn, build, and explore together through WebMCP.
An autonomous AI security agent that continuously audits Google Cloud, proves questionnaire compliance with live cryptographic proof, and executes governed fixes.
x
Real-time HTTP security header analysis with scoring, redirect inspection, SSRF protection, and actionable security recommendations.
claude driven image detection model development. blatantly token-maxxed.
claude driven gpu kernel optimization. blatantly tokenmaxxed.
Complex goals. Fragmented institutions. Gemini reasoning, connected through one governed AI bridge.
A zero-model, zero-token shopping agent that turns every customer reply into a hard filter — hitting the target product 99.9% of the time within ~2 turns, using nothing but standard-library Python.
UAS Technical Task
Each turn runs `observe → route → retrieve → rerank → answer + clarify`.
An action-adventure 3D game set in ancient Egypt where players solve puzzles, explore historic tombs, and battle mythological creatures to uncover hidden secrets.
