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:
AI agents investigate incidents. Humans authorize. Deterministic code recovers.
The agent can analyze and route authority risk. It cannot approve or apply production changes on its own. Probabilistic capability operates under deterministic authority.
An OpenCV 5 privacy agent that catches faces, QR codes, and text regions before a screenshot becomes a public incident.
A governed coastal-operations agent that turns field evidence into auditable decisions and dispatches work only when deterministic runtime controls authorise action.
Physical AI that sees infrastructure, reasons over visual and sensor evidence, takes safe action, and verifies the real-world outcome.
An ambient AI agent that coordinates your home, handles routine access and deliveries, and only interrupts you when human judgment truly matters.
Autonomous developer workstation powered by AWS Strands SDK and Bedrock, featuring closed-loop AST compiler verification, local shell execution, and multi-language crash triage and self-healing.
Freelance billing by conversation. Strands agents draft invoices, chase overdue, and estimate tax — you still approve every email.
Red-team the assessment, not the student — stress-test whether AI can bypass the intended learning.
BillShield is an AI agent that continuously discovers recurring expenses, detects suspicious or unnecessary charges, decides what action should be taken.
Healthcare goes quiet after the prescription. NaniAI carries the whole episode labs, waiting, results and only nudges you when something changes.
Turn hospitality referrals into prioritized, explainable, owner-approved follow-up—without auto-sending outreach.
Handle the routine quietly. Mobilize the technician instantly.
Sovereign multi-agent platform that turns water, energy, food, environment, and health data into actionable decisions for Algeria
CashflowGuardian is the autonomous AI agent for freelancers that stops scope creep and chases unpaid invoices. It flags contract violations and drafts escalations for you to approve with one click.
A shopping copilot that uncovers hidden needs from conversation, adapts when preferences change, and explains every recommendation.
From computational papers to reproducible evidence, without the busywork.
ShopPal is a lightweight shopping copilot that understands messy human intent, combines lexical and semantic search, and finds the right product fast, with zero inference-time API calls.
Everyday Agents. Family Loop: finish wellbeing setup once, then agents run check-ins, app/site asks, and a Sunday red/needs-you/green digest. Parents only step in when something new, missed unapproved
A shopping copilot that is stress-tested against real language (not just catalog terms), learns which questions to ask to narrow the search fastest, and diversifies recommendations for fairer coverage
Professional Agents. Multi-agent analyser: upload paper+marks, map chapters, track a student all year. Teacher/student/parent views; ping teacher only if missing data or a judgment call.
**FieldBridge** — a governed Strands agent that turns a thin field-service ticket into the safest next human decision before a truck rolls.
Enhancing your shopping experience
A conversational shopping copilot that understands vague requests, remembers evolving preferences and delivers accurate recommendations quickly—without paid APIs.
