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 interactive AI debate partner that helps you practice arguments, counter-attacks, and speech delivery in real time.
For the things you were never taught to name
AI agents that deliver code through pull requests — Claude Code + Codex with worktree isolation, a command allowlist, and secret scanning. Never automatically merged.
Praxa turns theatre research into human–agent collaboration: WebMCP tools search trusted sources, compare productions, and return page-level citations.
Study smarter...
Your AI uses WebMCP to access government knowledge, while you can inspect the sources, provenance and limits behind every result.
Accessible campus navigation that adapts routes to mobility needs and live disruptions, helping users avoid stairs, steep slopes and unavailable elevators.
Proofloop turns proven management frameworks and knowledge into Google ADK agents that help solopreneurs find root causes, choose the next action, and measure results.
BOOKSCOPE turns web-scraped book data into actionable intelligence with interactive analytics, smart recommendations, price insights, ratings, availability tracking, and value scoring.
A Strands-compatible security layer that scans AI-built repos and blocks unsafe tool calls triggered by untrusted GitHub or MCP content before execution.
Turn particle-physics questions into shared, replayable visual investigations.
Municipal waste rules that AI agents can understand and act on—without guessing, while humans retain control of final decisions.
An agent-native incident response command center where AI agents investigate outages through WebMCP, simulate safe fixes, and execute production-changing actions only after explicit human approval.
Your bill never got you to set the aircon to 25°C. Your own glowing flat will. WattLah names the drain, shows the score, and turns one habit into a block-wide leaderboard.
An autonomous Gemini agent that recovers interrupted work, takes one bounded action, and reconciles reality before retrying.
Finding opportunities means wasting hours on expired listings and complex requirements. Taskmaster uses a multi-agent Gemini pipeline to research, filter, and rank student tech path options.
Outlast helps NUS students give broken personal items one safe, peer-supported repair attempt before replacing them.
An autonomous agent that ingests security alerts, classifies them using Gemini, auto-remediates clear low-risk cases, and escalates ambiguous.
Prove you're old enough without revealing your birthdate to a server. ProofPass swaps a rental app's date-of-birth field for a Midnight zero-knowledge proof; only pass/fail ever touches the chain.
Most shopping assistants ask what you want. Ours works out what it doesn't know and asks that instead.
Human or AI, every incident PR must prove itself
Narrow is an offline shopping agent that asks the smartest question each turn, narrowing 50,000 products to your exact match in about 2 turns, no LLM, no API cost with an 100% product hit rate.
The canvas a human and an AI agent build together — safely — and export to real, running code.
Autonomous enterprise IP governance platform linking Gemini agents to Solana Token-2022 Soulbound contracts for secure, compliant asset-backed royalty distributions.
