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:
Verified agent actions, safer by middleware.
We often "approve" AI agents without seeing what they’ll really do. AirLock changes that by isolating every run, blocking dangerous changes, and promoting only what it truly reviewed.
An autonomous AI housing agent that understands your needs, finds and ranks the best properties, and continuously monitors the market for new matches.
Charter turns a plain description of a business into a sealed, ready to sign formation packet. It does everything around the government filing, then hands it to the owners to sign themselves.
Git caught code collisions. Humans caught design collisions through communication. AI agents have neither. Shepherd detects when individually correct agents build a collectively broken system.
Your own agent prepares expense reports inside your existing login—no embedded model, no new standing credential, and a human still signs.
Production-grade guardrails for AI agents: auditability, real-time safety, and self-healing recovery without changing how you build.
One script line turns any site's existing frontend into WebMCP tools you can speak to and point at — voice and hand gestures, no LLM in the loop.
LastTube gives every discontinued-shade candidate a system or human disposition, then unlocks an observed offer only when exact-variant and visual proof are complete.
Give every retired battery its next chapter, reuse it or responsibly recycle it.
it is build to answer questions, and use to solve real world problems
Clanker-in-the-middle: Middleware that watches, gates, and logs every move your AI coding agent makes.
Giral asks Gemini the questions your buyers ask, tracks if your brand gets cited over competitors, diagnoses why it doesn't, and turns that into a prioritized fix-it list — for AI-search visibility.
A private, offline-first shopping agent that understands evolving needs, adapts when shoppers change their minds, and finds the right product faster.
State-bound release control for autonomous agents: certify candidates by diffing real effects, then gate promotion with an audited, tamper-evident ledger.
Find what customers deducted. Prove what they were entitled to deduct. Recover the difference.
Users inspect a synthetic factory, optimize an isolated scenario, compare it to the committed baseline, and request human approval.
Agent middleware that runs a plan's tool calls before the model has finished writing the plan, and refuses the ones it cannot prove safe. 2.19x faster end to end
AI Clinical Copilot connecting MRI scans, blood reports, consultations, prescriptions, and surgery with intelligent analysis, voice assistance, and real-time clinical decision support.
Amalthea interviews your household first, then plans the week and rebuilds the grocery list as plan minus pantry.
Handoff Gate: Trust every handoff, not every agent. It blocks unsupported claims, guides agents to correct them, and keeps unreliable research out of the final report.
Counterstep safely reverses an AI agent’s overreach and proves exactly what it repaired.
We stopped optimizing how the agent ranks and started optimizing when it knows enough to rank. 2.75 turns to converge, 0 LLM tokens, $0 per session, and +60 rank-1 hits on 800 unseen sessions.
Your agent says the run completed. The trace says which step actually failed. Glass Box middleware: a span waterfall per Agent Run, plus a policy gate that denies secret exfiltration.
