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:
GridShift is an AI energy copilot that forecasts building peaks, coordinates batteries, EV charging and HVAC, and gives facility teams a clear plan to approve before action.
A nested multi-agent system powered by Gemini 3, using ReWOO planning for task decomposition and knowledge integration, with dynamic tooling and persistent memory to boost research efficiency.
A self-improving copilot that turns research into reach.
This is a demonstration of the future of self-improving interfaces to the real world, rapidly identifying and understanding objects in photos taken of real world environments. Self Improving memory.
Stop wasting time on dependency hell and legacy drag. Our ReviveAgent, a self-improving AI, resolves conflicts, refactors code, and eliminates technical debt, instantly unlocking 100% feature velocity
A self-improving AI social-media team that hires and fires its own agents to keep you trending on X, 24/7.
AI agents to serve manufacturers and industrial distributors
ERA is a self-improving AI that builds other AIs — generating, testing, and refining agents that evolve into reusable tools, expanding its intelligence with every iteration.
A Simple Project: Self-Adjusting CHat Agent.
Our agent learns from successful applications and gets smarter over time.
Developer-first AI coaching and best practices. Real-time guidance that prevents failures and evolves through feedback, powered by Gambit-based self-learning on Gemini 2.0 Flash, Google ADK and Weave.
SynErgi is a self-evolving grid optimizer combining multi-agent planning and GRPO reinforcement learning to cut costs, emissions, and risk—learning cheaper, cleaner energy decisions every run.
The next step in autonomous driving coordination
Problem: Knowledge cutoffs is a major problem when packages are updated in record speed. The solution: Having a self-learning agent that injects code agents with relevant and up-to-date documentation
Automating the agent engineering step of the development process while keeping QA sane.
ContentEngine is a self improving content generation agent system that learns and grows with the user through agentic memory, prompt self-optimization, and Reinforcement Learning
We help patients become informed healthcare consumers by researching their symptoms across multiple medical specialties—so they know the right questions to ask before they even book an appointment.
Ask any question. Watch fully enriched AI actors (with memory, intrinsic characteristics, problem solving methods, history etc.) play it out in a state of the art discrete-time simulation.
AutoNAS is an intelligent Neural Architecture Search system that uses AI agents and reinforcement learning to design optimal neural networks automatically.
Introducing SEA, a framework that can evolve your agents without changing the model weights.
Cross provider cookbook hub for AI. Mix models and tools to generate runnable, traceable, self improving notebooks. Reduce integration pain today and build data for tomorrow's RL.
Behavior-driven code review: run apps in a secure sandbox, verify real-browser flows, log evidence, and improve overtime with RL.
Provide any image, and it gives you the prompt for that. Fully model agnostic. Self improving.
Where cutting-edge AI infrastructure meets autonomous learning - agents that improve through experience, collaboration, and evolution.
