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:
MoodMirror — Your emotions, reflected through AI. Analyzes your voice and facial expressions to understand your mood and deliver an intelligent score with personalized results.
Raiding the fakes real-world edits couldn't hide.
A closed-loop AI agent on Google Cloud that investigates data incidents, generates schema repairs, validates them in a sandbox, and prevents downstream ML system failures.
An enterprise agent harness powered by causal memory and self-organizing playbooks to execute complex, autonomous operations with total explainability across zero-trust boundaries..
Perry is an accuracy-gated GPU Transformer that delivers 11.8x speedup across 13 official workloads and makes a 100K-token case run within 32 GiB on an RTX 5090.
Elevator pitch CI for the knowledge your AI depends on — detect trusted knowledge changes, trace affected AI outputs, selectively replay them, and propose safe actions.
Compression and reposting change an image's pixels but not its origin. We fine-tune a vision encoder so its features ignore that damage, and detection accuracy holds where it usually drops.
A human-decision gate for Strands agents: capability is not authority
An autonomous ML research agent for recommender systems. It forms hypotheses, patches its own code, executes iterative optimization loops, and verifies results via bootstrap on sealed splits.
Real-time observability and audit layer for enterprise AI agents built on Claude, catches unverified actions before they execute, explains the failure, and applies a correction.
tiktoktechjam - shopping copilot
We built a hybrid detector (CLIP + frequency analysis) that catches AI-generated images even after blur, compression, resizing, or noise -- the stuff real images actually go through.
An autonomous agent that does ML research: hypothesise, code, run, measure, repeat. It beat the official KuaiRand recommender baseline in 30 self-directed iterations with zero human intervention.
AI-powered assistant for Gadaa Eco Builder, teaching the UNESCO-recognised Gadaa system while supporting real-world reforestation using WebMCP.
SafeGraph AI combines Knowledge Graphs and Agentic AI to deliver explainable disaster preparedness guidance, helping communities learn, understand risks, and respond to emergencies.
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.
An offline-first conversational shopping agent that turns changing preferences into fast, explainable, catalog-valid recommendations—without network calls or model tokens.
The control plane that runs a company of AI agents — not a chat window, a payroll.
One interactive, inspectable AI teacher across 9 school subjects and 20 languages.
An AI agent that analyzes consumer complaints, researches relevant information, prioritizes cases, drafts responses, and coordinates resolution actions with human oversight.
An autonomous Gemini agent that reads emails, summarizes key points, and automatically saves tasks and draft replies to Google Cloud Firestore.
Software that heals itself
MailPidge
AI-Powered Career Mentorship & Strategic Roadmap Agent