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:
The fullstack framework for the Agentic Web. Every Janux app ships a WebMCP surface by default, so agents use your real UI tools instead of scraping it. Bun-native, React-ecosystem compatible.
No Tokens? We got you!
A Gemini-powered multi-agent system using parallel tool calling to analyze script-to-screen continuity and live production data.
AI agents can retry conversations, but retrying real-world actions, like bookings or payments, can accidentally create duplicates. Our agent Action Ledger makes those actions crash-safe.
Contrôle d'accès par QR Code pour les écoles : scannez en une seconde, suivez la présence en temps réel, alertez les parents automatiquement.
Your autonomous co-founder agent. Give it an idea, and a team of Gemini agents plans, collaborates, and builds a founder-ready business blueprint with you in the loop.
A privacy first mental wellness companion that helps people understand their well-being patterns and build healthier daily routines through responsible AI.
A maze game where an AI agent can inspect, solve, and actually play the game through WebMCP tools
Ctrl Alt Del turns opaque Agent execution into an auditable run so as to protected by prompt security, durable memory, Glass Box tracing, and estimated-versus-actual cost evidence.
ShieldOne is an autonomous multi-agent Cloud Security platform
" Secure Records. Clear Ownership. Zero Doubt "
Your AI agent for sourcing and negotiating the capacity that doesn't have an API.
Your agent reads the contract, flags what will cost you, and drafts the fixes as redlines you can accept or reject. It has no tool that edits the document. Not by policy. By construction.
AI-powered verification that detects scams, exposes evidence, and helps you trust opportunities safely.
A sticky-note board where the agent is a teammate, not a script. It claims notes, moves them and comments back — running in your browser session, so it never sees a credential.
SLB-ScopedRun turns "don't look there" into "it isn't there." Each Agent Run mounts only the one delegated resource, read-only, enforced server-side — not by asking the model nicely.
A read-only, evidence-aware architecture map where people and AI agents inspect the same project graph, trace verified paths, expose bypasses, and preserve uncertainty through WebMCP.
Backend-enforced authorization that lets AI agents use private data without overstepping human intent or ownership.
Turn “done” from an agent claim into a verifiable artifact.
Teaching materials meant TeX for math, Word for layout, PowerPoint for figures, and unusable AI. Sigma Studio puts it all on one page that's intuitive to edit, and AI edits it with you. Open source.
One sentence in, one signed document out. An agent chain drafts, generates and prepares contracts via Foxit PDF Services — then a REAL human signs. Signed PDF + full audit trail.
88 million Americans are served by a water system with a violation on record. This page turns that record into six WebMCP tools an AI agent can call - and never returns a zero it doesn't have.
Autonomous multi-agent Hollywood filmmaking suite orchestrating scriptwriting, Imagen 3 VFX moodboards, Gemini TTS rehearsals, and partner MCP telemetry in real time.
Volc Agent Launchpad is a three-layer middleware that lets safe AI coding work pass, contains dangerous prompts and reported runtime actions, and exports verifiable trace evidence.
