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:
Programmable escrow for AI agents on Base: lock USDC, verify work deterministically, release on pass or slash on fail. Agent LLM runs on NVIDIA Nemotron via Nebius Token Factory.
AI copilot for short-video creators: ad scripts in Darija, French and English, translation, hashtags and a weekly plan from a channel own stats - NVIDIA Nemotron on Nebius, budget-capped.
A private Personal AI that remembers your context, plans tasks, uses the right tools, and takes approved actions to get work done.
A privacy-first AI agent that combines memory, tasks, files, skills, and tool use into one extensible personal AI assistant.
An AI cloud-operations agent that cannot act until a named human approves — now running on Nebius Token Factory with NVIDIA Nemotron.
Review AI filing suggestions, approve exact moves, and undo with a recorded trail.
An expressive virtual robot that guides older adults through a voice-based geriatric assessment and prepares a traceable draft for clinician review.
Governed ICFR remediation briefs for the office of the CFO — NVIDIA Nemotron on Nebius Token Factory
Refuse-first hunt agent: local GO/PARK gates, optional Tavily grounding, NVIDIA Nemotron on Nebius Token Factory only for named hypotheses.
A support-ticket copilot that routes each ticket through the cheapest Nemotron model that can handle it — and saves the big one for the reply that actually needs to be right.
Evidence-gated coding agent runtime where Nemotron proposes and independent verification decides.
Grasshopper drives a real browser through multi-step tasks using Nebius Token Factory's Nemotron models — and after the first run, repeats the same job with zero LLM calls.
Node.js prototype: verified NVIDIA Nemotron stream on Nebius Token Factory, tool validation, credential checks and 29 tests.
Single-Pass Drone Video to Accurate 3D Model Generation System AI-Enabled Georeferenced 3D Reconstruction from a Single UAV flight
An AI assistant that remembers your goals, detects conflicts, and helps you keep your commitments.
Two patches pass the smoke test. Patch Jury finds boundary counterexamples and turns them into executable evidence for a maintainer's decision.
Circuit Mind AI is an AI-powered circuit design copilot that converts natural-language hardware ideas into circuit architectures, component lists, validation insights, and export-ready KiCad files
An owner-controlled visitor journal with a synthetic AI-assisted review demo.
Source-linked incident dossiers with contradictions, explicit uncertainty and proposed remediation.
Robot teleoperation telemetry + deterministic trajectory evaluation for embodied AI, with an NVIDIA Nemotron model on Nebius Token Factory narrating PASS/FAIL verdicts it cannot overturn.
Verify payment claims with deterministic rules. Nemotron explains the verdict, Tavily adds public context, but neither can change it. Demo uses test transactions.
Reopen checks whether a closed civic complaint was really fixed. It then builds a dated escalation plan with drafts and sources.
AI incident remediation platform powered by NVIDIA Nemotron on Nebius Token Factory. Combines verifiable log evidence, sandboxed patch validation, and human sign-off.
Kiro: Your Code, Your Agent.
