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
A local-first, open-source control plane for governed GPT-5.6 agent workflows.
An evidence engine for code that is only allowed to speak with proof.
An educational, self-hostable version of Little Linked Librarian that teaches AI workflows, agent tools, distributed nodes, and modern software architecture through a working neighborhood library.
Turn workplace knowledge into reviewable, interactive SCORM training with GPT-5.6.
We ship a solid fraud detection AI, autogenerate its entire EU AI Act paperwork straight from the live pipeline, and anchor every decision onchain so an auditor can prove nothing was tampered with.
forMika turns scattered group chats into one shared plan for guests, food, dietary needs and costs with Mika suggesting the next best action. Less organizing. More being together.
Codex asks before it force-pushes, deletes, or pays. A human decides, and every yes, no, and timeout becomes a signed receipt anyone can verify offline.
Tamalife turns your subscriptions into living creatures. If you ignore renewals, price hikes, or wasteful spending, your garden withers making subscription management impossible to ignore.
FieldPact turns a skilled-trades project brief into a complete Crew Pack, equips staffing teams with trade-adaptive evidence tools, and gives workers transparent offers with worker-controlled Proof.
Robust memory for science research agents, and a rough first step towards a scientist AI according to Yoshua Bengio: a hypothesis synthesizer & evaluator.
Intent: your desktop remembers so you don't have to.
A safe, read-only desktop tool that turns local project metadata into clear recovery plans and bounded next steps for Codex.
Giving overlooked sports the context, analysis, and stories they deserve.
Students think they are bad at math when they hit prerequisite gaps. Margin diagnoses exactly what's missing, teaches the shortest path back to your query, and confirms mastery with solving problems.
Evaluates AI-generated summaries and analyzes whether they missed important details about marginalized communities and other historically underrepresented voices.
Qonvergence Trials lets distinct AI agents advocate, challenge, and arbitrate scientific hypotheses against public evidence-preserving every disagreement and citation.
Science/Retrace turns GPT 5.6 into a guided research workspace for learning, reviewing, researching, experimenting, and writing with retraceable evidence and reproducible loops and folders.
GPT-5.6 investigates, Codex repairs, a human approves and an unchanged deterministic verifier decides PASS.
Governed AI execution that humans can safely interrupt, correct, and resume—with a complete provenance trail showing what changed and why.
Language barriers in ERs delay critical care when seconds count. I built Triage Medical to translate patient symptoms, score urgency levels, and pinpoint pain zones so doctors can treat faster.
TopoDrawer turns network ideas into working labs: design and organize topologies with intuitive engineer-first tools, animate traffic, let AI build, configure, and validate, then export to EVE-NG.
AI that teaches you to build—not AI that builds instead of you.
One ranked attention queue for AI-agent reliability, human approvals, and presentation readiness.
Turn AlphaFold 3 results into a local-first, evidence-linked workspace for structures, confidence, PAE, and grounded GPT-5.6 analysis.
865 – 888 of 8014
