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:
Agents finish tasks. IsoPact makes sure the business actually settles, preventing conflicting actions across enterprise agent fleets and verifying the outcome.
We built a conversational shopping copilot that understands changing intent and constraints, achieving 100% Hit Rate@10 and a 0.965 technical score, about 9x the baseline.
n offline conversational shopping agent that tracks changing intent, asks useful clarifying questions, and quickly ranks the right products from a 50,000-item catalog.
An Autonomous Taskmaster Agent Powered by Gemini 3.7 Flash That Red-Teams, Fortifies, and Deploys Secure LLMs.
An AI tutor that answers only from your course notes, cites the exact page, and checks its math with SymPy. Powered by NVIDIA Nemotron 3 Nano, Super and Ultra on Nebius Token Factory.
An autonomous multi-agent AI research team that invents, writes, tests, and self-heals recommendation system models directly in PyTorch code.
Harness buddy automates all the ML research for you. It writes training code, reads its own crashes, and critiques itself when stuck. Beat the FM baseline on hidden test. Zero human interventions.
ShopMate — the shopping agent that knows when to ask and when to answer.
Conversational search that learns what matters and finds the right product faster
Detects AI-generated images and holds accuracy after real-world compression, blur, crop & rescale using a hybrid CLIP + FFT-forensics model. 0.996 AUC clean, 0.984 across 15 transforms.
An evidence-grounded Gemini agent for scientific reviewers: navigate complex climate documents, analyze passages, trace context, and draft human-reviewed comments without automatic submission.
Cleri is a shopping assistant you actually talk to, not a search bar with dropdowns. Say what you want in plain words. Change your mind halfway through. Skip questions you don't care about.
WARDEN is a security firewall for AI-agent capabilities, using Gemini to detect malicious tools, Ed25519 to seal trusted ones, and runtime policy enforcement to keep agent fleets safe.
Give AI agents real power without giving them the final word. Release Sentinel lets agents act through WebMCP while a deterministic Gatekeeper retains release authority.
When source evidence changes, Veritas autonomously traces and repairs every registered consequence across Google Workspace- preserving human edits and proving the result.
An advanced, offline-first Autonomous AI Code Writer and Multi-Agent Operating System powered entirely by local models
To better understand the behaviour of our AIGC detector, we reviewed representative failure cases across authentic and AI-generated images.
BibleOmnix is an AI Faith Creator that identifies unbelief, targets it with biblical truth, remembers each person's teaching state, and progressively plants Scripture and builds faith.
Professional Agents. Multi-agent analyser: upload paper+marks, map chapters, track a student all year. Teacher/student/parent views; ping teacher only if missing data or a judgment call.
The copilot that tunes itself to any machine and pins the right product at #1.
An e-commerce copilot that turns conversation into ranked products, with a self-iterating prompt lab that evaluates and refines intent understanding without fine-tuning.
Tiktok TechJam Track 4, running an AI shopping agent
Autonomous Machine Learning Research Agent for Recommender Systems
An agent with 4 characters that improves Machine Learning models on its own. It works out what is actually wrong, writes the code to fix it, then checks whether the fix really did what it promised.