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:
Agents write most of the diff now, and nobody reviews at agent speed. Tenet turns architectural intent into structured constraints it feeds to your coding agent — then blocks the PR when they break.
You and an AI agent operate the same board, not a chat window beside it. Graph curves, wire circuits, bond atoms, drop a ball, and it explains how each change, yours or its own, shaped the result.
Git caught code collisions. Humans caught design collisions through communication. AI agents have neither. Shepherd detects when individually correct agents build a collectively broken system.
A triple-layered security middleware for AI coding agents — smarter prompt-injection detection, a confirm-before-write gate, and one-click rollback.
From raw message to actionable risk verdict - powered by Gemini , governed by human approval.
RunProof turns every AI Agent run into a persistent, privacy-safe receipt, helping teams explain failures, cancellations, latency and token usage without exposing sensitive content.
No Tokens? We got you!
Satellites collision coordination takes days, and third-party software forces Sat secret data into their DBs. Aegis AI servers negotiate directly in TEE in minutes without storing secret data.
Your lockfile trusts one registry. CAIRN doesn't. Independent attesters verify every package on-chain, so a tampered dependency is blocked in CI before it ever reaches your build.
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.
One request. Many sites. Capability resolution for WebMCP agents.
Run a medieval tavern one guest at a time: brew, serve, and grow a one-room bar into a heaving hall of thirsty guests.
Protect Today, Preserve Tomorrow. EcoPulse uses real time weather data to monitor, predict, and provide solutions before any issue happens to arise.
PyroWatch fuses live NASA satellite fire detections with real-time weather physics to flag wildfire risk early — giving communities and responders a critical head start before flames spread.
Protect sensitive information. Prove what stayed unchanged
PantryPilot turns simple meal goals into an optimized grocery order. Plan meals, compare prices, respect allergies, and approve every purchase with a human-in-the-loop WebMCP agent.
Plan your weekends or trips based on your needs with ease. Don't just go to the same old place, use tripster.
Nine rule-based strategies race live on Polymarket's 5-minute BTC markets. Watch which trading ideas actually survive contact with real prices.
Relay is a secure, LLM-powered shopping agent that turns natural conversation into discovery, checkout, and post-purchase help, while Visa-style identity, risk, and consent protect every transaction.
Converge turns intent into connection. Tell us what you want to do—study, build, meet or collaborate—and we surface the right people and opportunities, while keeping every choice human.
Pulse is a live-map where suburbs glow and pins pulse brighter based on the actual foot traffic of real people checking in real time, instead of a static list of pages.
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.
SDK for managing agent traffic that uses WebMCP
