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:
The ultimate agentic cinema clearance engine
Support tickets triage themselves: ML classifies urgency and category, Gemini drafts the reply, and the agent decides — resolve or escalate — with no human in the loop.
Making emergency search and rescue more efficient through artificial intelligence and image-processing pipelines, so rescue teams know where to look first.
When a public agency opens bids, Track Record wakes up on its own, reads every bidder's contract history, and delivers a one-page award memo showing what each low bid has historically become.
A document firewall for AI agents. Verso scans a PDF before your agent reads it, catches text hidden in the file but invisible to a person, and refuses to release it, with a signed receipt.
WildNest is the first end-to-end AI platform for animal rescue — from intake to adoption, every meal, scan, and story travels with the animal so no rescued life is ever lost in the system.
ProofID lets users prove eligibility for age, student status, and income without revealing raw personal data, while an AI Policy Engine turns natural-language rules into verifiable requirements.
Combine small specialized expert models to robustly detect AI Images
Zero-trust escrow & reputation rail for autonomous AI—locks funds, verifies delivery, audits A2A commerce on GCP.
Gemini agents autonomously triage shipment fraud & compliance risk, act only within a published delegation boundary, and fail closed to a human review queue that always shows the source document.
A zero-trust scope attenuation firewall, dynamic blast-radius evaluator, and cryptographic HMAC provenance control plane for autonomous multi-agent systems.
A fast, reliable consent‑verification tool that instantly checks user input and returns a clear badge for secure, seamless validation.
Don’t trust the tool response. Verify the state. Runtime Truth detects when a WebMCP action reports success but the authoritative application state says otherwise.
to avoid your procrastination
Image Scanner using CNN and EfficientNetB0
Krishi Mithra is an AI-powered farming assistant that detects crop diseases, provides treatment advice, weather alerts, and multilingual support through voice and images.
Our project fine-tunes a pre-trained ResNet18 model to detect AI Images from real images.
We are homeless software/computing students
Helping people unified! Trade skills, not money!
Prove that you meet job requirements without exposing your résumé or personal information.
An agentic system that separates Arabic text matches from historically valid authorial attestations using Gemini, Google ADK, and deterministic evidence verification.
AI-powered wildlife monitoring that detects threats, prevents human-wildlife conflicts, and alerts authorities before lives are lost.
A unified developer hub for building reusable agent skills, orchestrating MCP tool integrations, and deploying context-aware AI directly into the Freshworks ecosystem.
A pre-production agent that checks screenplay facts, catches continuity breaks, and returns a cited revision brief.
