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:
Stop risky AI agent actions before they execute by tracking context, data sensitivity, and multi-step tool behavior in real time.
Estes turns local waste — eucalyptus, coffee husk, rice husk — into sensors, filters, and scientific evidence. Open source platform for environmental citizenship.
Giving AegisForge visual perception to understand scenes, make decisions, and verify outcomes.
Move a rain slider and see which Cuajimalpa neighborhoods to prioritize for floods and landslides.
Hyperlocal Urban Heat & Civic Climate Resilience platform mapping Gainesville heat islands and mutual-aid infrastructure with NASA GLOBE and Google Gemini AI.
Autonomous quantitative trading engine with VIX macro gating, Tri-Agent consensus, and Alpaca atomic bracket routing to insulate momentum portfolios.
Snap a photo of confusing paperwork — get plain words, real deadlines, and a plan.
CarbonShift: Run compute when energy is greener.
See. Investigate. Decide. Approve. Act. Verify. — AI-powered visual incident response with OpenCV 5 and human-approved remediation.
Think before you spend — an AI-powered decision engine that turns your real finances into a BUY, WAIT, or SKIP verdict.
An AI-powered dependency upgrade agent that automatically detects breaking changes, repairs Python code, runs tests, and verifies fixes with anti-cheating safeguards.
You approve the boundary — not every action. The server enforces it while the AI works for days. Safety does not depend on the model behaving safely.
CIRCA uses AI and parallel traffic simulations to test emergency responses before safely applying the best one then learns from the real outcome.
Fact-based security evaluation for AI agents.
WildGuard AI turns scattered wildlife news into real-time intelligence using AI, multilingual NLP, risk scoring, and geospatial analysis to detect threats, hotspots, wildlife crime patterns.
Mimi gives open-source maintainers an evidence dossier for npm vulnerability reports: package grounding, public advisory context, bounded tests, deterministic oracle results, and explicit coverage.
Read the square before you trust it. QuishLens decodes QR codes, links, payments and documents, detects phishing signals, and explains the risk before you click or pay.
ScamLens AI scores suspicious messages, links, emails and screenshots from 0 to 100. It explains every red flag, combining a transparent security rule engine with AI you can't sweet-talk.
An AI-powered digital security copilot that detects threats, explains how attacks work, protects sensitive data, and teaches users how to defend themselves — with or without AI.
Agent Safety Gate is a safety layer between any AI agent and its tools. Our MCP-compatible proxy intercepts every tool call and decides: allow, block, or pause for human approval.
Investigate npm audit warnings with experiments you can rerun. Reproduce a supported vulnerability, catch repairs that break the app, and flag saved evidence when its inputs change.
Eleven AI agents find the bed. Code checks every move. A human signs the big ones.
Stops autonomous AI agents from leaking confidential data by enforcing deterministic trajectory invariants across multi-step tool execution with sub-millisecond latency.
