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
AI-powered risk assessment that replaces physical collateral with satellite, climate, and market data to enable collateral-free lending for smallholder farmers
Autopilot patrols a real Latin American e-commerce network (318K orders), finds the lanes quietly losing money, and queues the fix. Honest statistics, human-approved actions, live on Qwen Cloud.
A council of specialized AI agents that review code together — mapping structure, catching security and quality issues, and validating their own fixes before you see them.
Typed prospective memory that notices the right future cue and acts exactly once
Duselang is a production education platform (adaptive practice, LMS, live quizzes) with MemoryAgent tutor built for the Global AI Hackathon with Qwen Cloud, Track 1.
Your metrics dropped. Qwen finds why — or proves why it can't. An autopilot agent that refuses to lie, backed by statistical proof.
Agent memory that cites its sources. An open-source memory engine for Qwen agents where every rule cites the exact experiences that taught it. Memory you can audit is memory you can trust.
A four-store memory layer for LLM agents that resolves contradictions, decays gracefully, and retrieves under a token budget, proven against 3 baselines.
An AI agent with human-like long-term memory that learns, remembers, and evolves across conversations instead of forgetting after every chat.
A self-scoring multi-agent negotiation testbed, no LLM-as-judge. It measurably keeps each party's secrets private vs a single agent and honestly reports what did and didn't work.
Automates invoices, customer inquiries, BTW (VAT) declarations & weekly growth reports for Dutch SMEs using Qwen-VL + Qwen-Max — every decision confidence-gated by an inspectable Human Ledger.
"The zero-crew AI Showrunner: autonomously scripting, casting, rendering, and editing vertical mobile dramas with Qwen and Wan."
A multi-agent AI system for regulated organisations that creates institutional memory, improves decision consistency, and never forgets.
Six AI agents debate your business questions, remember every past decision, and converge on an auditable verdict — fully autonomous, powered by Qwen.
Qwen experts directed by a Genie that knows when NOT ▎ to be a MoE. +21.9% mean quality vs a single agent 29 wins / 6 losses over 40 double-judge pairwise Rounds.
Sees everything. Streams nothing.
Qwen Council is a fully autonomous multiagent-humanic system evaluating and commenting on the latest arXiv papers with blind-review machanism.
A Qwen-powered SRE agent society that debates real infrastructure evidence, requests human approval, and safely diagnoses physical servers.
Cybersecurity team for a a small team
A memory agent for novelists: Quill remembers your story's lore, forgets what stops mattering, and catches contradictions live, powered by four Qwen Cloud agents.
AI recruiting copilot for lean teams — source, screen, pipeline, and outreach without adding headcount. Local-first, chat-driven, built for startup hiring.
Compliance Autopilot uses Qwen Cloud agents to scan real repositories, map regulations to code evidence, generate fixes, and open human-approved GitHub pull requests.
ReVoice is an AI companion for people with aphasia that uses personalized, evidence-based cues to help them recover forgotten words instead of simply giving answers, adapting to each user's recovery.
Open-source AI system that parses messy RFQ emails, PDFs, and spreadsheets into structured, priced, human-reviewed quotes.
73 – 96 of 729
