Hero Banner

Top Builders

Explore the top contributors showcasing the highest number of app submissions within our community.

Vercel

Vercel is a platform designed for developers, providing speed, reliability, and scalability to create and deploy web applications. With built-in CI/CD, zero configuration, and deep integrations with popular Git providers such as GitHub, GitLab, and Bitbucket, Vercel streamlines the development process, making it easy for teams to collaborate and iterate on their projects.

General
Release date2015
AuthorVercel
TypeDeployment and hosting platform

Tutorials

Great tutorials on how to build with Vercel

Vercel - Helpful Resources

Check it out to become a Vercel Master!

Edit on GitHub

Vercel AI technology page Hackathon projects

Discover innovative solutions crafted with Vercel AI technology page, developed by our community members during our engaging hackathons.

CasePilot Real-Time AI Financial Forensics

CasePilot Real-Time AI Financial Forensics

CasePilot is an event-driven financial forensics platform built for modern fintech environments where fraud unfolds in seconds. Traditional rule engines generate alert noise but fail to expose coordinated patterns across accounts, devices, and locations. CasePilot turns raw transaction streams into structured investigations by combining real-time ingestion, graph analysis, and AI-assisted case generation. The system ingests live transactions and risk signals, aggregates related alerts into single investigative units, and assigns dynamic risk scores. A graph network module maps relationships between users, wallets, devices, and IP addresses to expose mule rings and shared infrastructure. A geospatial velocity engine calculates distance and implied travel speed between events to detect impossible travel and account takeover scenarios. An integrated AI copilot operates in context of the active case. It synthesizes transaction logs, entity links, and historical outcomes retrieved through vector search to generate structured investigative reports and Suspicious Activity Reports. When analysts resolve cases, their decisions are embedded back into the system as structured memory, allowing future investigations to benefit from prior outcomes and reducing false positives over time. CasePilot is designed as a full-stack, real-time investigative workspace: a command center dashboard for monitoring, an interactive graph for tracing fraud networks, geospatial visualization for anomaly detection, and an AI layer that converts evidence into actionable enforcement. The result is a system that shortens investigation cycles, improves detection of coordinated fraud, and creates a continuously learning audit trail.

TradeWise AI

TradeWise AI

Traders face information overload and emotional bias when making market decisions. TradeWise AI addresses this by combining automated technical market intelligence with behavioral insights and social content generation. The platform computes indicators (SMA, RSI, ATR, momentum), identifies patterns, and produces clear, human-readable explanations. It analyzes trader behavior—win rate, holding time, trade frequency—and provides psychology-driven recommendations and trade recovery probabilities. TradeWise AI also includes a RAG-backed search, on-demand content creation for social platforms, real-time alerts, and demo/offline modes for safe exploration. Built as an MVP, it’s aimed at retail traders, trading coaches, and small teams who want actionable analytics, better discipline, and shareable market narratives—while emphasizing education and sound risk management rather than guaranteed predictions.

Product Experience - AI Agent

Product Experience - AI Agent

It is interesting to see how UX and UI directly influence conversions. We decided to uncover real pain points faced by users trying to use the Deriv website. The target users were Gen Z and millennials who are not financially savvy yet but are curious about getting into trading. Through observing behavior, friction points, and confusion moments, we focused on where users hesitate, drop off, or lose trust. For Deriv, this approach serves two clear goals. First, it helps attract new users by reducing cognitive overload. Second, it improves conversion by guiding users with clarity, confidence, and simpler decision paths. What would change if these frictions were left unresolved?

Secure-AI

Secure-AI

LLMs have recently adopted persistent memory to provide models with better user knowledge and personalisation. However, this introduces a new vector for adversarial manipulation. This report investigates Memory Injection, a threat model where adversaries exploit indirect prompt injection within web content to poison an agent's long-term memory. Employing user manipulation scenarios, we show that memory attacks, should they succeed, are effective at changing model behaviour towards the user, often more so than a direct system prompt. Hence, this highlights the need for more robust evaluations of memory updates in agentic memory systems.

AlertIQ

AlertIQ

AlertIQ is a next-generation financial crime intelligence platform designed to address the core failures of traditional AML systems. Instead of relying on static rules and fragmented monitoring, AlertIQ continuously analyzes transactions in real time, learning customer behavior, tracking temporal patterns, and mapping complex account networks to uncover hidden risk. The platform fuses behavioral models, time-based intelligence, and relationship graphs into a unified risk engine that detects money laundering, fraud, and compliance breaches before they escalate. Every alert is supported by Model Insights, clearly explaining why it was triggered, what patterns were detected, and how risk evolved over time—ensuring full transparency and auditability. AlertIQ actively measures and reduces false positives using confidence-weighted scoring, analyst feedback loops, and fairness-aware modeling. This minimizes alert fatigue while preserving detection accuracy, allowing compliance teams to focus on genuinely high-risk cases. To streamline regulatory workflows, AlertIQ includes a built-in Compliance Copilot that transforms complex alerts into regulator-ready summaries, supports SAR preparation, and simplifies audits—without removing human oversight. The system is fully aligned with global AML standards, including FATF risk-based principles and regional regulatory frameworks. Built with responsible and sustainable AI, AlertIQ uses lightweight models for detection and applies large language models only for explanations and reporting. The result is an efficient, explainable, and future-ready AML solution that restores trust, reduces operational risk, and transforms how institutions fight financial crime.

Abyss

Abyss

Our project is an AI Web Application Firewall (AI WAF) designed to protect AI agents and LLM-powered applications from prompt injection, jailbreaking attempts, and malicious user inputs while preserving legitimate user interactions. As AI systems become more integrated into real-world decision-making and financial workflows, traditional security models are no longer sufficient. Our platform introduces a multi-layered AI-native security approach that validates inputs, monitors model behaviour, and verifies outputs before execution. The system is built using a Next.js frontend with serverless backend security pipelines, integrated with advanced AI models such as Gemini and machine learning-based risk scoring engines. Our agent is designed to be financially intelligent, meaning it understands context around financial data, sensitive operations, and high-risk actions, allowing it to prevent exploitation attempts that target financial logic or transaction workflows. Unlike traditional rule-based filters, our platform uses semantic embedding analysis, behavioural anomaly detection, and adaptive threat intelligence to identify evolving jailbreak techniques. The platform assigns real-time risk scores to prompts and agent actions, allowing safe prompts to pass while blocking or rewriting malicious ones. This ensures security without degrading user experience. The solution is deployed using cloud-native architecture for low-latency, real-time protection, making it suitable for enterprise AI deployments, fintech AI agents, customer-facing AI systems, and autonomous decision-making platforms. Our long-term vision is to build the foundational security layer that allows organizations to safely deploy AI agents on the public internet at scale.