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
Protecting Privacy in Real Time, One Frame at a Time
A two-stage pipeline consisting of a Nomic embedder and a modified Mamba-based decoder.
An Agentic, AI Red Team Approach for Proactive Geo-Compliance Risk Detection
Your real-time privacy coach - flagging sensitive comments, encrypting every step, and building safer habits powered by fully homomorphic encryption and on-device AI.
Lightning fast safety and quality evaluations for online reviews
Where privacy becomes invisible, and security feels effortless.
AI-Powered Tool that filters Google reviews for valid, spam, ads, irrelevant, or “not visited” using Hugging-Face models Gemma and Qwen for smarter insights.
"Filter the Noise, Find the Truth" An AI-powered moderation agent that flags low-quality Google reviews using rules, heuristics, and LLMs to improve trust on location-based platforms.
Post without panic: VeilVault spots sensitive stuff (faces, plates, emails, location cues) and lets you blur or unblur each with one tap—in photos and videos—so you stay in control.
Automating Compliance, Amplifying Confidence.
Unfortunately my HF is not working as of now
Noisy location reviews warp choices. Our project learns trust from patterns—not hand labels. Two complementary prototypes cross-check every call. Clear, auditable signals that you can act on.
From Natural Language to Lynx Components.
Testing for the Age of Agents.
Transforming regulatory compliance checking from a manual challenge into an automated, auditable solution with power of LLM.
AI flags policy-violating reviews with 90%+ accuracy using BERT. ReactJS and FastAPI enable real-time moderation for platforms like Google Maps.
PonyTune combines rule-based heuristics with HuggingFace embeddings to deliver a fast, interpretable, and high-performing NLP classification pipeline.
FairTik leverages multi-modal AI and human-aligned reinforcement learning to ensure creators get rewarded fairly and transparently—redefining how digital content’s true worth is measured
I built an automated system to detect policy violating Google reviews. Using machine learning and NLP, it analyzes review text and metadata to flag issues like spam or irrelevant content
Apotheosis, your Knit dependency visualisation tool. Has a CLI, a web UI and a processor! And you can integrate it in your Gradle workflow!
Privacy-first AI chat: Secure, anonymized, and encrypted conversations powered by cutting-edge technology.
Weaving through code, at your fingertips.
Tired of fake reviews ruining your plans? ReviewSentry spots bad reviews like that friend who always knows which places to trust. Real reviews from real people.
We transform regulatory risk from a reactive cost center into a predictable, automated step in your development lifecycle, ensuring faster and safer global expansion.
1 – 24 of 307
