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:
A trainer asks ChatGPT to add a missing exchange to the video lesson already open. OpenScene waits for the learner before releasing the recorded answer.
Paste a YouTube link, get 3 upload-ready Shorts — auto vertical crop with face-tracking, burned-in captions, and AI-generated titles/descriptions. No editing software needed.
A web page where a person and an AI agent source verified food imports together - the agent operates the same screen the buyer is looking at, and cannot send anything without the buyer's approval.
A completion gate for coding agents. When candidate patches disagree, approval is withheld and the disagreement becomes a question; the answer becomes a versioned acceptance test.
Document your tennis serve, track your progress and improve your game.**
Video editing is a hundred precise operations, not one prompt. Klipvia exposes those operations as WebMCP tools so a person and an agent can collaborate on the same timeline.
Before you buy the couch, find out whether it can get up the stairs. Your staircase answers, and it can answer the furniture shop too.
Nowadays everyone can build & ship. But how fast is your distribution? DemoDominator turns any URL into studio-grade product walkthroughs w/ synchronized voiceovers & rich Video SEO schema in 25 sec
The doctor gives the plan once. Sanad carries it until reality matches.
Welcome to modern team vibecoding: everyone's LLM is writing their slice of code right now. We're your new safe and effective editing layer, delivering one clean repo instead of a sea of conflicts.
Your autonomous AI team for creating YouTube Shorts.
CurrentCut keeps your social feed alive: an autonomous agent researches your company and what’s current, proposes cited reel concepts, and turns approved ideas into platform-ready videos.
We stopped optimizing how the agent ranks and started optimizing when it knows enough to rank. 2.75 turns to converge, 0 LLM tokens, $0 per session, and +60 rank-1 hits on 800 unseen sessions.
An ML research agent that owns the whole loop — it forms the hypothesis, writes the code, trains, and grades itself. 23 experiments, zero human code, and it caught its own data leak before we did.
Your agent says the run completed. The trace says which step actually failed. Glass Box middleware: a span waterfall per Agent Run, plus a policy gate that denies secret exfiltration.
A Pokédex for the dogs and cats you meet in real life. Point your phone at any pet and Boop names the breed on-device, cuts them into a die-cut sticker, and pins them to the map where you met.
A multi-agent creative studio built on WebMCP—where humans and AI agents collaborate to create videos in a shared workspace
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 AI multi-agent studio that turns a creative brief into a complete cinematic production.
Auteur gives AI filmmakers a persistent Film Bible, grounded by Parallel research, that keeps every generated shot coherent with Gemini Vision drift detection and automatic correction.
RenderOps Director doesn't stop at detecting a broken shot. It diagnoses the failure thru Grafana, executes a human-approved fix in Google Cloud and proves the recovered frames are ready for editorial
Turn good intentions into neighborhood action. Patchwork lets people and AI agents discover projects, build plans while keeping them human-approved. Use any AI browser to query it, like ChatGpt.
An LLM agent that diagnoses, changes, retrains and measures a recommendation model in a loop: 0.6016 → 0.6056 on KuaiRand-Pure, no human intervention, and a harness built to check its work.
SNIPR uses WebMCP to let AI agents safely query renovation assignments, inspect spatial room context, and propose actions while keeping SNIPR the source of truth.
