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
The GPT moment for robotics: pretrain on the world (video), imagine the solution to any problem, act it out, learn from the result.
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
Where cutting-edge AI infrastructure meets autonomous learning - agents that improve through experience, collaboration, and evolution.
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 RL reward design and training methods for video game environments using LLMs with Open Evolve
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.
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
A self-improving AI social-media team that hires and fires its own agents to keep you trending on X, 24/7.
AI is short-sighted and Sales are impersonal We let AI dream -- passively generates and verifies general knowledge graph allowing quick factual multi-step reasoning. We use iterative RL to respond
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.
From user meetings to measurable impact in minutes, not days.
Self-improving AI system: 5 agents validate each other's work sequentially, learns optimal models via Weave tracking, uses Tavily search. 100% success vs 80% baseline, 0% hallucinations.
Photo -> Free text (ie hard) quiz app. This app is self improving: quality, grading, exam bords updated, and even UI, all dynamically improve with combination of RL(serverless GRPO) and DSPy (GEPA).
AI tutoring agents that learn from their mistakes and tutor feedback to generate better lesson plans and interactive activities over time
Autonomous agent that builds, tests, and self-improves n8n workflows using MCP expertise—generate → validate → revise. Live webhook demo + Streamlit dashboard; results tracked in W&B.
Help SDRs send personalized emails at scale.
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.
An Oracle of Failure. A developer-first scalpel that kills the debugging nightmare in agentic AI by transforming the graveyard of logs into a living, visual map of the crime.
Coding agent that evaluate execution and result
Self-improving video-article matcher using FPO (Federated Prompt Optimization). AI learns across deployments to better describe video scenes and rate content relevance at reels.hurated.com.
Meet Hot Takes Only, your AI-powered selfie coach that roasts you to glory.
A lightweight runtime verification layer for AI agents. It wraps your agent’s tools and outputs in a policy-aware safety monitor, catching unsafe or non-compliant actions before they execute.
AI agents to serve manufacturers and industrial distributors
Behavior-driven code review: run apps in a secure sandbox, verify real-browser flows, log evidence, and improve overtime with RL.
1 – 24 of 67
