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 maps and pulls scientific literature daily for what a research field has actually studied, and alerts you only when a verified gap gets filled based on your parameters.
A website made to effectively and efficiently manage customer wait times through a virtual queue.
4 autonomous AI agents run a virtual software studio — they perceive, remember, decide, and act every 15 seconds. Powered by Gemini 3.5 Flash. No human intervention required.
A listing studio for print-on-demand sellers where the agent presses the same buttons you do, in the same grid, with every action visible and overridable.
Life, without the paperwork maze.
Turn months of satellite imagery into field priorities in minutes, not days. 1415 Agri uses Gemini's reasoning to show farmers where to inspect first and make better field decisions.
A WebMCP-powered food-rescue workspace where AI agents create explainable meal-allocation plans and people approve every real-world commitment.
An immersive cinematic 3D journey through mysterious worlds, ancient memories, and dimensional portals — built to make the impossible feel explorable
Safety-first autonomous control for Positive Energy Districts combining Gemini 3.5 Flash contextual reasoning with deterministic life-safety guardrails.
A Turkish-speaking agent that owns a car service appointment for days: books it, calls to remind, retries, falls back to SMS, reschedules, and issues the signed work order. Nobody drives the middle.
HIOP gives AI agents a deterministic authority boundary before they cause real-world effects—allowing, denying, or holding actions for approval while producing tamper-evident evidence receipts.
“An AI-powered workflow assistant that helps virtual assistants organize tasks, streamline client operations, and turn repetitive work into efficient, repeatable workflows.”
Type any place on Earth and get a live Habitat Health score, built in real time from actual air quality, a 14-day climate trend, and real species records pulled straight from public data.
A shared, visible observing route for people and their AI agents.
Chronos is a governed incident-remediation control plane using multi-agent debate to fix pipeline failures, while making destructive production mutation structurally impossible by code.
A raise can leave you poorer from benefit cliffs. CliffCheck maps that cliff across 16 US states, and now exposes WebMCP tools so an in-browser agent can answer "should I take this promotion?"
A high-performance 3D spatial website merging physics-driven particle canvases, dynamic 3D memory spheres, scroll-driven robotics telemetry, and rich micro-interactions.
Phloem is an AI-native engineering team that plans, codes, tests, reviews, deploys, and manages budgets across multiple LLM agents from one transparent workspace.
ScamLab helps students practice spotting scams through realistic simulations, clues, feedback, and adaptive training—before they encounter scams in real life.
You and an AI agent operate the same board, not a chat window beside it. Graph curves, wire circuits, bond atoms, drop a ball, and it explains how each change, yours or its own, shaped the result.
Kanverse Human API turns phone-only services into goal-driven workflows, using CALL-E to call targets, evaluate outcomes, and continue automatically until the goal is achieved.
An autonomous exception closer that blocks unsupported waste custody claims, requests exact corrective evidence, resumes safely, and releases an evidence-linked packet.
Eleven native WebMCP tools turn a 12-step reflection into a safe human-agent workflow: the agent clarifies and navigates, the browser scores, and the person confirms every choice.
Spotigo lets you describe a civic problem out loud — a pothole, a downed power line — and an agent turns that into a filed report, but it can never hit submit without your explicit yes.
