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 autonomous agent that runs the full ML research loop, train, evaluate, recover from crashes, repeat, on TikTok's KuaiRand recommender challenge, beating baseline with zero human tuning.
Multi-agent customer support system using all Gemini Enterprise Agent Platform pillars. It covers shopping, orders, billing, refunds, memory, escalation, MCP tracking, eval-gated and CI/CD shipping.
Learning-guided search synthesizes, benchmarks, and deploys shape-specialized Transformer programs on RTX 4080, achieving 14.49x geometric-mean speedup over the PyTorch baseline on Shapes 1-13.
Offline-first conversational search that finds the right catalog product even when shopping intent is vague, evolving, or replaced.
Four Gemini 3.5 ADK agents compress 4-hour ICH E6(R2) protocol-deviation paperwork into a 60-second Part 11-signed cold-chain rescue for ultra-low-temperature biopharma shipments.
Your inbox, on autopilot — Gemini classifies, routes, and acts on every email.
Stop guessing, Start growing: Taking the guesswork out of aquaculture.
Automated QC tells you a delivery failed. This agent tells you which preset version did it, who changed it, and under what ticket - then proves it by re-running the stage and measuring.
An autonomous agent for early-stage startups that reads product feedback in French and English, clusters it, and opens real GitHub tickets for the problems that matter, on its own.
AI agents execute. ProofOS proves. It turns agent completion claims into fail-closed VERIFIED or ABSTAIN verdicts using independently authorized evidence and deterministic verification.
Nobody asked it to do anything. GharOS reads your household's inbox, works out what each message implies, catches conflicts, does the safe parts and runs the house, leaving you the real calls.
A 4-Agent Advisory Pipeline using Strands SDK and AWS Bedrock for prompt optimization and safety auditing.
An autonomous agent that plans, writes, and schedules a week of social media content on its own — no daily prompting, just results.
AI fixes ARM64 build fails on Android phone - Nebius+NVIDIA
Physics-based forensic features + Clip, combined by an interpretable random forest: A robust, calibrated AI-image detector that can say WHY an image looks fake, and stay fast when it must.
A smart middleware that converts product scans into structured inbound inventory for ERP/POS systems, automating invoice reconciliation and expiration date tracking.
Spot the synthetic. Protect the authentic.
AI image detection that stays accurate even when images get compressed, blurred, or resized.
The ultimate data analyst for film studios. Combine Gemini's reasoning with ClickHouse MCP's speed to make instant, data-driven marketing decisions.
An autonomous product team that detects issues, talks to users, finds root causes, ships fixes, and verifies impact, continuously turning product signals into improvements
A conversational shopping copilot that understands vague requests, remembers evolving preferences and delivers accurate recommendations quickly—without paid APIs.
An answerability-aware, evidence-grounded shopping agent that knows what to ask, how to rank, and when to commit.
A Gemini agent fleet that runs a company: it writes executable models of the business, tests them against reality, and acts. CEO-Bench is our benchmark. Write your own adapter, point it at yours, run.
Find better models. Build an even better ensemble.