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:
Elevator pitch CI for the knowledge your AI depends on — detect trusted knowledge changes, trace affected AI outputs, selectively replay them, and propose safe actions.
Per-Agent token budgets for the Agent Launchpad: enforced in the control plane before a run starts, with a ledger of every allow, charge, deny, and reset decision.
Problem: Teams waste hours manually triaging bug reports. Solution: An autonomous agent using Gemini 3.5 for instant analysis and patches. Tech: Deployed via Google Cloud Run.
An offline-first conversational shopping agent that turns changing preferences into fast, explainable, catalog-valid recommendations—without network calls or model tokens.
The control plane that runs a company of AI agents — not a chat window, a payroll.
...but what if we could put a leash on our agents?
One interactive, inspectable AI teacher across 9 school subjects and 20 languages.
Zillow can't tell you which way the front door faces. VastuNest reads floor plans and satellite images with Gemini, scores homes against the criteria that actually rule them out, and works overnight.
Software that heals itself
AI-Powered Career Mentorship & Strategic Roadmap Agent
AI that writes your docs, sheets and decks in your own voice, researches with cited sources, and keeps every number consistent when one changes.
Adds scoped, revocable access control to Agent Launchpad. Every request to an Agent is checked server-side against granted permissions, denied outside scope, and logged with actor, action, decision.
Sentinel governs AI agent actions in real time—allowing safe work, holding risky commands for human approval, and blocking threats to protect your data and systems.
Your second brain rots: notes keep recommending tools you retired. vault-patrol audits your vault on every push and opens one subtraction-only PR, each finding code-verified against verbatim quotes.
AI coach for Pokémon VGC: Gemini 3.5 Flash + Google ADK + Cloud Run, grounded in a damage calculator & Firestore metagame data — not guesses. Cuts tactical errors up to 80x vs. ungrounded LLMs.
An autonomous AI SRE that diagnoses and fixes production incidents in minutes, with a human approving every fix. Six agents, multimodal Gemini, live on Google Cloud.
An evidence-driven AI planner that turns ambiguous goals into five verifiable actions, each with explicit evidence and risk notes.
TalentAgent is the agent your career never had: it works while you sleep, backs every resume claim with real work, and learns which employers actually hire people like you.
Describe your startup idea and get 3 live landing pages, real competitor research, domain availability, and market sizing — powered by Gemini + SerpApi + name.com. Live in production today.
An agentic accessibility app that turns live ASL signs into captions and speech, asks for confirmation when uncertain, and learns each signer's correction while keeping camera frames on device.
AgriSentinel.OS: The Autonomous Multi-Agent Shield for Smallholder Farmers
Native Cloud AI operator running on Google Cloud Run that seamlessly executes 11 Google Workspace services directly inside Google Chat using Antigravity Engine & Model Context Protocol (MCP).
Stops stale queued rollout authority before it can change Cloud Run traffic.
Trust infrastructure for economic AI agents: preserve human intent, verify evidence, bound authority, and prove outcomes before and after an action.
