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:
A desktop cat that watches your AI coding assistant — blocks dangerous commands before they run, then roasts your bad habits in a bubble when you finish.
Local shell completion that ranks valid choices to your habits and explains each one in Korean or English.
Turning a used camera into a self hosted pet-cam to watch my dog Chloe while I am out.
DREDGE is an AI-native platform combining GPU acceleration, intelligent agents, and advanced computation to help developers build, deploy, and scale next-generation AI systems.
HarnessVM launches secure, double-isolated AI coding sandboxes with browser and terminal access, so you can run agents, tools, and local or cloud models in YOLO mode with confidence.
Real-time security gateway for AI coding agents — block secrets, catch prompt injection, audit every tool call. One config line.
An auditable local AI agent combining bounded archetype context, symbolic device state, and reflection—then testing honestly where those mechanisms help or fail.
Sandboxed is a Codex skill that lets you unleash coding agents—while keeping their work, access, and fallout safely contained.
Vexyl Guard protects AI-connected workloads with local, privacy-first policy checks and a Linux security agent that monitors before it acts.
Prove recovery before agents get destructive authority.
A reversible workflow engine that turns Codex and GPT-5.6 visual briefs into safe, modular, low-load desktop themes with verified interactions and clean restore.
AI tutors explain. Meno turns your materials into a teacher that won’t stop until you truly master them.
The fully autonomous Digital Forensics & Incident Response (DFIR) agent: GPT-5.6 chooses where to look; deterministic code controls what may run and verifies exactly what was executed and cited.
QNX-powered smart elevator: per-floor headcount via webcam, dispatched by a priority+aging algorithm so no floor waits forever, even when another floor is busier.
Autonomous Security Recon Agent - ASRA
I38 is a completely blind accessible desktop environment based on the i3 window manager.
Apprentice expands Vintage Story with playable races, professions, skill trees, hidden classes, poisons, advanced crafting, dangerous regions, and Grandmaster progression. Shape your fate.
Run Codex unattended inside a hardened container that treats the agent as untrusted - prompt injection can't escape. A shared project brain resumes work across sessions, limits, and machines.
Audit and optimize AGENTS.md and Codex Skills, detect conflicts and token waste, generate execution-ready goals, and turn user corrections into regression tests for reliable AI coding workflows.
A transparent AI routing layer that matches each task to the right model, reasoning depth, tools, and workflow—reducing wasted compute while preserving human control.
An RK3566-based onboard Linux and ROS/ROS 2 platform for real-time control, sensor integration, autonomous navigation, and rapid deployment in drones and robotic systems.
AI Infrastructure Engineer
EcoRoute cuts LLM cost and carbon with an OpenAI-compatible gateway that safely caches, routes, and optimizes AI requests across approved models and hosts.
Approval-first Virtual QCPU runtime with reproducible safety proofs
