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
Institutional Risk Agent Fleet uses Gemini agents to investigate financial risk while deterministic controls verify evidence, enforce permissions, audit actions, and escalate decisions to humans.
An AI career co-pilot that guides aspiring professionals into cybersecurity with personalized study plans, resume gap analysis, and mock interviews, remembering your progress every step of the way.
An asynchronous background agent that autonomously cleans corrupt datasets and renders visualization dashboards without human intervention.
A voice-first memory companion for a person living with dementia. Ten agents keep her day; the warmth is a prompt, the safety is a mechanism — medication answers never touch a model.
Six agents on Vertex AI Agent Engine treat every supplier invoice as an attack: Model Armor fails closed, policy is code, one identity may pay, exactly once — plus a billing kill switch.
Practice your hardest conversations against a live, interruptible AI counterpart. Every score line cites a published source. Built on ADK 2.8's live evaluation stack.
An evidence-based multi-agent system that evaluates job opportunities, maps qualifications to requirements, identifies gaps, and turns the assessment into actionable career intelligence.
Crucible attacks its own AI agents every night with a deterministic tripwire — not an LLM's opinion — then writes the fix and proves it holds before dawn.
Serverless AI agents triggered by user actions and external events autonomously execute multi-step workflows, producing UI artifacts and live data for connected platforms.
An adaptive AI room-reset partner that compares photos, prioritizes what to fix, and learns your household’s preferences from every correction.
Multi-agent DAG orchestrator powered by Gemini multimodal models, Live voice, and Antigravity. Decomposes goals into autonomous specialist workflows in real time.
Two AI models propose your ERP scope, independently. Python - never an LLM - decides what actually gets built, with a citation for every call.
An autonomous dual-agent AI system protecting users from digital exhaustion and online phishing scams.
Learn, visualize, and generate social media content for slope-intercept form (Y=MX+B) with dynamic line animations, geometric cartoon strips, financial applications, and historical evolution.
Autonomous crypto incident response that identifies the likely theft, traces stolen funds across chains and wallets, and keeps monitoring until the trail moves again.
Most AI answers your questions. This one asks you: it interviews a retiring expert to dig out judgment they can't write down, then stays behind as their alter so juniors keep working with it.
RegOps is a secure multi-agent system that turns regulatory changes into evidence-backed findings, approved actions, deterministic revalidation, and complete audit trails on Google Cloud.
RetryPermit — policy-governed recovery for failed events
An autonomous morning market briefing that finds agreement, disagreement, and thin evidence across financial news and video.
Job boards show you what exists. Jobs NightWatch shows you what changed and scores against your profile.
The plan breaks. The operation recovers.
Autonomous AI sales agent for service businesses that qualifies incoming leads, determines the next action, updates CRM data, schedules follow-ups, and notifies the manager
I run 4 iterations of credit request form without success. An agent should have deployed to handle this long running task.
A persistent software robot that turns goals into safe, auditable multi-step actions using Gemini 3.5 Flash with memory, permissions, recovery, and Core-controlled tool execution.
937 – 960 of 1841
