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
BOLMEET AI is an autonomous meeting intelligence platform that attends meetings, understands conversations, reasons with organizational memory, and turns discussions into actionable outcomes.
A memory layer for Qwen agents that audits its own reliability at runtime — re-grounding stale facts and refusing to act on memory it can't verify.
An AI-powered smart home assistant using Whisper and Qwen LLM to turn natural speech into real-time MQTT hardware control via ESP32.
An AI agent that automates business workflows from start to finish.
Qwen Cloud Autopilot that searches jobs in your Chrome, scores fit against CV + GitHub, and drafts a suggested CV only after human approval.
Device-local memory for AI agents: keep every decision in the browser, send Qwen only the capped, hash-cited proof it needs, and forget on schedule.
1-shot Text to Video, Now 1-shot Text to Interactive Video as well. Fully composable, use Alibaba Cloud models for QWEN, Happy Horse and WAN. Use SoTA public adapters for other parts of the pipeline.
FounderOS: an AI board for operators of existing businesses. Eight AI agents debate your toughest call, including a dedicated Skeptic, and return a board ready memo with a clear recommendation.
Solving reviewer sycophancy with adversarial convergence in multi-agent AI systems — review agents challenge each other to catch what others miss.
A privacy-first screenless wearable reads your body at the edge; Qwen on Alibaba Cloud flags signals as steady, watch or elevated, with wellbeing advice and recommendations in a smartphone app.
A privacy-first multimodal AI agent that understands daily routines, detects missed tasks and household risks, and proactively alerts older adults and their families.
An autonomous multi-agent companion that ends the copy-paste trap by reading your live browser context, remembering you across sessions, and explaining every decision instantly using Qwen Cloud.
Engram gives agents a mind, not a database: beliefs that revise when contradicted, sleep that turns failures into lessons, and a live memory graph you can watch think.
A memory engine for AI agents that forgets on purpose: memories fade unless used, beliefs are superseded instead of overwritten, and recall stays under a fixed token budget. Built on Qwen.
Graub AI: The AI Team Your Business Always Needed!
"Give Qwen models a memory. Across sessions. Across conversations. Forever."
A Qwen Cloud agent that turns ambiguous opportunities into verified execution plans with human approval gates.
An AI communication runtime that reads, classifies, and autonomously negotiates over ordinary email - policy-gated, round-capped, audit-logged.
An agentic surveillance camera that turns natural-language instructions into verifiable, privacy-first alerts.
AI Driven Inquiry pipeline, with self regulated approach
A source-grounded memory layer for Qwen that learns across sessions, recalls critical evidence within tight context windows, and updates outdated memories without slowing the foreground agent.
12 specialized AI kernels running in production since Feb 2026 on a bare-metal mesh. Built with Qwen Cloud. IQ 185. Zero failures. Not a demo — a production cognitive society.
A training-free memory sidecar that lets a Qwen agent forget stale facts and skip the per-write LLM token tax.
241 – 264 of 729
