AWS

Top Builders

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

AWS

Amazon Web Services (AWS) is the world's most comprehensive and broadly adopted cloud platform, offering over 200 fully featured services from data centers globally. Since its launch in 2006, AWS has provided a highly reliable, scalable, low-cost infrastructure platform in the cloud that powers hundreds of thousands of businesses in 190 countries worldwide. AWS is a leader in cloud computing, offering services that span compute, storage, databases, networking, analytics, machine learning, artificial intelligence, Internet of Things (IoT), security, and enterprise applications.

General
Company	Amazon Web Services, Inc.
Founded	2006
Website	https://aws.amazon.com/
Documentation	https://docs.aws.amazon.com/
Technology Type	Cloud Provider

Start Building with AWS Products

AWS provides a vast array of services that enable developers and businesses to build sophisticated, scalable applications in the cloud. From foundational services like compute and storage to advanced machine learning and AI capabilities, AWS offers the tools needed to innovate and grow.

AWS SageMaker

AWS SageMaker is a fully managed machine learning service that enables developers to quickly and easily build, train, and deploy machine learning models at scale. You can find more information on our AWS SageMaker tech page.

AWS Kiro

Kiro is an AWS-powered agentic coding service that uses "spec-driven development" to turn prompts into code and tests. You can find more information on our AWS Kiro tech page.

Edit on GitHub

AWS AI Technologies Hackathon projects

Discover innovative solutions crafted with AWS AI Technologies, developed by our community members during our engaging hackathons.

FairPrice: AI Agents for Africa's Informal Economy

Africa’s informal sellers; students, market traders, side-hustlers can't get buyers to pay upfront, because there's no shared trust layer between strangers. Nearly every transaction defaults to cash on delivery, and a single refused delivery erases days of margin for a seller who can least absorb it. FairPrice fixes this without asking sellers to leave the tools they already use. A seller generates a payment QR or link from a dashboard or directly inside WhatsApp. The customer pays, funds are held in escrow, and they release the moment delivery is confirmed, no trust required on either side. Behind this sits ZEMA 360, our autonomous commerce agent layer, orchestrated on UiPath Maestro and powered by Qwen and Gemini, with AMD GPU inference running live through Fireworks AI. It handles order fulfillment, price verification, and human-in-the-loop approval for high-value payouts over WhatsApp, without a human operator watching every transaction. This isn't infrastructure built for a hackathon demo; it's running in production right now, processing real payments for real Nigerian sellers. We're live since May 2026, before any paid acquisition: 12 active sellers, dozens of orders processed, and real GMV moving through escrow, with a working AI agent stack on AMD infrastructure actually doing the work of fulfillment and pricing, not just decorating a README.

Sentinel Band

Most "agent fixes your cloud" demos hand one LLM both the findings and the keys. One prompt injection in a bucket tag and it's deleting your audit logs. Sentinel Band is built so that no single agent holds both read and write AWS access, and no agent trusts another agent's prose. Only validated JSON schemas cross agent boundaries. Four independent gates have to agree before anything is written to AWS: Independent verification — a second agent, in its own process, re-queries AWS itself to confirm a finding. It never inherits the first agent's claims. Deterministic policy gate — pure Python (no LLM) re-derives the risk tier and checks a hardcoded allowlist + exact parameters before any boto3 write. Wired executor — even a call that passes the gate cannot run unless its concrete boto3 executor is explicitly mapped in code. Rollback requirement — Remediation refuses to run anything without a registered inverse. rollback_possible is an enforced invariant; a human can undo any auto-fix with one message. If any gate disagrees, the write does not happen. Everything fails closed.

MeetWise

MeetWise is an AI-powered meeting intelligence and organizational memory platform that helps teams capture, understand, and act on the knowledge generated in every conversation. Unlike traditional note-taking tools, MeetWise goes beyond transcription by extracting decisions, action items, risks, blockers, requirements, and key insights from meetings in real time. The platform creates a persistent memory across meetings, projects, and teams, ensuring that important information is never lost. By connecting discussions with historical context, MeetWise allows users to instantly retrieve decisions, commitments, and insights from previous meetings. During live meetings, it continuously analyzes conversations and provides contextual assistance, helping participants access relevant information without searching through recordings, documents, or chat histories. MeetWise also identifies contradictions and inconsistencies across meetings by comparing new discussions with previously captured knowledge. This helps teams maintain alignment, avoid misunderstandings, and make more informed decisions. Action items generated during meetings are automatically converted into trackable tasks and integrated into existing workflows, ensuring accountability and follow-through. By integrating with workplace tools, project documentation, communication platforms, and development environments, MeetWise creates a unified intelligence layer for the organization. It transforms meetings from isolated conversations into a continuously evolving knowledge base that supports collaboration, decision-making, and execution. MeetWise helps organizations remember every conversation, connect every decision, and turn discussions into measurable outcomes.

CloudGuardAI

In today's fast-paced cloud environments, manual Incident Response (IR) is too slow to mitigate active threats. CloudGuard AI is an automated Security Operations Center (SOC) pipeline powered by an intelligent multi-agent system. We engineered three specialized AI agents using the CrewAI framework: ThreatHunter: Ingests raw security logs (e.g., AWS WAF logs) and extracts critical forensic data into structured JSON formats. PolicyChecker: Evaluates the forensic data against strict compliance rules to intelligently determine if action is required. CloudOpsRunner: Instantly generates precise Infrastructure as Code (Terraform) scripts to remediate the vulnerability and block the threat. The workflow is triggered via our custom web dashboard. As the agents process the threat utilizing the ultra-fast Groq LLM, they push real-time status updates and remediation scripts directly to a team chat via the Band API. CloudGuard AI drastically reduces the Mean Time to Respond (MTTR) from hours to mere seconds, enabling autonomous and secure cloud infrastructure management.

MAITS/BANDA

The platform is written in Python and operates in a multi-threaded architecture managed by a centralized Orchestrator. It simulates multi-agent algorithmic trading (Paper Trading mode) while enforcing strict operational constraints through specialized modules: Multi-Threaded Orchestrator: Manages individual, isolated Trading Units (bots), ensuring concurrency and stability. Security Sentinel: Processes and validates all trade intents before execution to prevent out-of-bounds order sizes or unauthorized operations. Data Optimizer: Calculates real-time financial metrics, risk exposure, and tracks critical analytics such as Max Drawdown for every active bot. BandConnector: Integrates directly with Band Protocol oracles to fetch decentralized price feeds. These feeds are used as a ground-truth reference to audit local exchange data, detect price anomalies, and prevent execution based on manipulated or stale data. Logging and Auditing (Логування та аудит) The system separates operational concerns into distinct file structures to maintain clean state tracking: Bot Logs: Isolated runtime logs for individual bots are written to /home/ubuntu/kucoin_prod/bots/logs/n_bot.log (where n is the bot ID). Analytical Ledger: Trade history and portfolio metrics are committed to JSON Lines format at state/trades_history.lsonl for each bot container. System Auditor: A standalone tool (auditor.py) evaluates historical logs and real-time state to compile performance reports.

FreshMart: A Multi-Agent Grocery Experience

FreshMart is a full-stack grocery ordering platform built on a multi-agent architecture using the Band SDK. Three specialized AI agents work together behind the scenes: a Manager agent that routes requests, a Query agent (LangGraph) that answers questions about products and orders, and an Action agent (CrewAI) that handles order mutations like cancellations and updates. On the frontend, customers get a polished Next.js portal where they can browse 30+ products with a shopping cart, place orders, and track them through the full lifecycle pending, processing, shipped, delivered. A built-in AI chat assistant (powered by Claude) lets customers view their orders, change quantities, or cancel — all in plain conversation. Key technical highlights: - Band SDK multi-agent orchestration across three frameworks (Anthropic SDK, LangGraph, CrewAI) - Supabase for auth, database, and real-time data - Background job that automatically advances order statuses over time - Cookie-based auth with scoped data access so each customer only sees their own orders - Full cart persistence, stock management, and server-side checkout validation