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 churn recovery agent that negotiates personalized retention offers like discounts, pauses, and plan changes to save subscriptions and process outcomes through PayPal.
LLM-powered software advisor that probes vague queries, ranks catalogue products on grounded evidence, and explains every recommendation with source-row citations.
Milestone billing where "invoice paid" is a real dependency: AI drafts the plan, you approve each PayPal invoice, and the schedule moves itself when PayPal confirms a payment.
A chatbot for individual entrepreneurs that tracks regulatory changes and prepares mandatory reports, ensuring no deadlines are missed.
Turn what your community already loves (shows, games, podcasts) into a library shelf: cited shelf-talkers, a ranked buy list and programme ideas, grounded in Qloo's taste graph.
Sovereign claim-to-evidence auditing with Apertus.
Cultural intelligence agent grounded in Qloo's 250M+ graph, formally verified in SPARK Gold, Latin semantic interlingua, and accessible 3D sign avatar.
Find the breaking change. Prove the fix
AI agents design for the audience they imagine. Moûsa, a plugin for Claude Code, Codex and Kiro, seals that guess, measures the audience with Qloo and makes the design use what the guess missed.
On periodic semiconductor arrays, identical structures can fool template matching. DriftSense Pilot uses OpenCV 5 to read edge roughness, estimate confidence, and trigger re-imaging or human review.
Xvimo receives suspicious messages on WhatsApp and web as an open-source AI agent, checks before Nigerians send money, with a verdict, reasons and evidence in English, Pidgin, Yoruba, Hausa or Igbo.
Papers make claims. Nullius measures them: an AI agent rebuilds an ML paper's experiment in a sandbox, and an independent checker tests whether the reported number holds.
AquaLinks scores freshwater pollution risk from Sentinel-2 satellite images with fixed math. Five AI agents explain the score and never change it.
Everyone tells Huddle privately what they can take on. Huddle proposes a fair plan, without saying who set which limit.
The autonomous trust and monetization layer for agentic commerce on PayPal rails.
Conversational weather intelligence for every Indian — verified, multilingual, actionable
Conversational weather intelligence for every Indian — verified, multilingual, actionable.
AI-powered construction inspection grounded in real-world evidence.
Give your agent a reason to look again. AutoVision uses OpenCV 5 and AWS to measure scenes, choose deeper inspections, and turn returned evidence into next steps through REST and MCP.
Agentic video triage in seconds: OpenCV 5 picks frames worth inspecting, an agent verifies events against policy and escalates uncertainty to a human. AWS deploy, observability, measured eval.
Adaptive learning, truly personalized. Your cognitive learning twin.
An intelligent legal assistant for Indian advocates, defense counsels, and prosecutors. Analyze FIRs, map statutory IPC/CrPC sections, retrieve verified judgments from Indian Kanoon
Next Experiment is an AI agent that investigates failed LLM fine-tunes and tests fixes against a control before you spend on retraining.
A gamified wellness app empowering students to track moods, build mindful habits, and level up their mental health — one bloom at a time
