Kiro

Top Builders

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

Kiro

Kiro is an AWS-powered agentic coding service designed to revolutionize software development through "spec-driven development." It leverages artificial intelligence to interpret natural language prompts and automatically generate code and tests, significantly accelerating the development lifecycle. Kiro aims to reduce manual coding efforts and improve code quality by ensuring that applications adhere closely to their specifications.

General
Author	AWS
Release Date	2025
Website	https://aws.amazon.com/
Documentation	https://aws.amazon.com/documentation-overview/kiro/
Technology Type	Agentic IDE

Key Features

Spec-Driven Development: Translates high-level natural language specifications into functional code and comprehensive tests.
AI-Powered Code Generation: Utilizes advanced AI models to write code automatically, reducing development time.
Automated Test Creation: Generates relevant test cases alongside code, ensuring immediate validation and higher quality.
AWS Integration: Seamlessly integrates with the broader AWS ecosystem, leveraging cloud infrastructure for scalable development.
Agentic Workflow: Employs AI agents to manage and execute development tasks, from planning to implementation.

Start Building with Kiro

Kiro offers an innovative approach to software development, allowing teams to rapidly build and test applications by focusing on specifications rather than intricate coding details. As an AWS-powered service, it provides the scalability and reliability expected from a leading cloud provider. Developers interested in leveraging AI for accelerated and more reliable coding should explore Kiro's capabilities.

👉 Kiro Documentation on AWS 👉 Explore AWS AI/ML Services

Edit on GitHub

AWS kiro AI technology Hackathon projects

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

Nexus — Engineering Trust Layer

AI coding assistants can generate software quickly, but responsibility still belongs to human engineers. Nexus was built to make AI-assisted software verification transparent, reproducible, and trustworthy. Nexus is an Engineering Trust Layer that separates every software decision into three stages: executable evidence, AI reviewer analysis, and human approval. Instead of asking developers to trust an AI, Nexus requires every decision to be backed by evidence that can be inspected and replayed. The demonstration begins with an AI-generated code submission. Nexus freezes the change, executes automated verification using pytest and Hypothesis property-based testing, and records reproducible evidence, including generated counterexamples when verification fails. A Fireworks AI reviewer analyzes the evidence and provides an independent opinion, but the AI never makes the final decision. Human reviewers remain responsible for approving or rejecting changes. Every decision is stored in an append-only audit trail through the Decision Workspace API backed by SQLite. Replay Mode demonstrates a contract-validated verification session, while Live Mode performs real backend reads and writes. If any dependency is unavailable, Nexus follows a Fail Honest policy by reporting the failure instead of fabricating results. For the AMD Developer Hackathon, we implemented an AMD execution adapter for AMD Developer Cloud. Cloud activation was requested during the hackathon but was still pending when this submission was prepared. Rather than simulate AMD execution, we honestly disclose this limitation. The adapter is implemented and ready, but we make no unsupported claims about MI300X execution. Nexus includes a demonstration console, evidence pipeline, live Fireworks reviewer integration, append-only audit storage, comprehensive documentation, and a fully passing automated test suite, providing a trustworthy foundation for AI-assisted software engineering.

CaptionForge AI

CaptionForge AI is a production-ready video captioning platform built for the AMD Developer Hackathon Track 2. It processes videos through a modular Extract-Reason-Style multi-stage AI pipeline: Extract - Uses imageio-ffmpeg to extract audio and Pillow/imageio to sample 6 keyframes from videos Reason - Transcribes audio using Whisper-v3 and analyzes visual content using Kimi-k2p6 (both via Fireworks AI on AMD MI300X GPUs) Style - Transforms factual captions into four distinct styles using DeepSeek-v4-pro: Formal - Objective, professional documentation Sarcastic - Dry, theatrical irony Humorous-Tech - Programming metaphors Humorous-Non-Tech - Everyday observational comedy Evaluate - Local CaptionCritic validates for hallucinations and style adherence Key Innovations: Decoupled architecture enables flexibility and maintainability Cloud AMD MI300X GPU acceleration via Fireworks AI enables serverless deployment Multi-model fallback chain (DeepSeek → Kimi → GPT-OSS) for reliability Automated reasoning cleanup removes leaked chain-of-thought from model outputs Style-specific evaluation ensures quality across all four required styles Technology Stack: Backend: FastAPI + SQLAlchemy + SQLite Frontend: React + TypeScript + Vite + Tailwind CSS AI/ML: Whisper-v3, Kimi-k2p6, DeepSeek-v4-pro (all via Fireworks AI) Deployment: Vercel (serverless) + Docker

ExecOS AI – Multi-Agent Executive Operating System

ExecOS AI is an AI-powered Executive Operating System designed to help founders, startups, and small businesses make faster, data-driven decisions without hiring an expensive executive team. Instead of simply answering questions, ExecOS AI acts like an AI boardroom where specialized business experts collaborate to analyze business performance and generate actionable insights. Users can upload business documents such as financial reports, sales data, operational records, marketing performance, customer feedback, and internal reports. These documents are automatically processed using Retrieval-Augmented Generation (RAG), allowing the platform to understand the company's current business context before answering questions or generating reports. ExecOS AI uses a workflow-based orchestration system that coordinates multiple AI specialists, including Finance, Marketing, Business Analysis, Customer Success, and Executive Strategy. Their combined knowledge is synthesized into a single executive response, giving business owners practical recommendations instead of isolated answers. The platform supports natural language business conversations where users can ask questions such as "Why has our profit margin decreased?", "What is our revenue trend?", or "How can we reduce operating expenses?" The AI analyzes uploaded business knowledge and produces contextual recommendations, risk assessments, and improvement strategies tailored to the business. One of the platform's key features is AI-generated Executive Reports. With a single click, ExecOS AI produces a structured executive report containing financial analysis, marketing insights, operational risks, customer experience analysis, business health scoring, confidence metrics, priority actions, and a 30-day strategic action plan. Our goal is to make executive-level business intelligence accessible to every startup and small business by providing instant, AI-driven strategic guidance through a modern and intuitive platform

Haven

Haven is an AI-powered mental wellness platform built to make emotional support accessible and stigma-free — for the majority who never reach a therapist due to cost, distance, or hesitation. At its core is an empathetic AI companion, powered by open-source LLMs (Qwen3p7-plus via Fireworks AI), holding warm conversations that remember a user's mood, goals, and journal entries across sessions — a companion that grows familiar over time, not a generic chatbot. Haven layers real-time emotion detection(Llama-v3p2-11b-vision-instruct via Fireworks AI) into every interaction, understanding how a user feels and letting the AI adapt its tone — more grounding during distress, more encouraging during progress. Journaling is a first-class feature: users write freely, and the AI offers gentle reflective insights and mood trend summaries, helping users notice their own patterns without judgment. Voice therapy sessions add a human, embodied feel — users speak naturally and hear warm, multilingual spoken responses, powered by self-hosted, open-source speech models (Whisper for STT, XTTS-v2 for TTS) on AMD GPU infrastructure, keeping conversations off third-party APIs. Guided breathing exercises and a calming soundscape corner give an immediate tool for regulating anxiety, independent of the AI chat. Clinically grounded assessments — including PHQ-9 and GAD-7 — give users an objective baseline to track change over time, bridging casual self-care and clinical insight, while directing users toward licensed professionals, not replacing them. A crisis detection layer (sentinet/suicidality Hugging Face Classifier) runs continuously in the background, so even indirect expressions of distress are caught, not just explicit crisis language — routing users to verified, government-approved helpline numbers. Multiple visual themes and multilingual support built to feel less like software, more like a companion that's actually paying attention.

smart token efficient agent

Our submission for the AMD Developer Hackathon is a highly optimized, hybrid AI agent designed to maximize token efficiency while maintaining rigorous accuracy standards across complex evaluation tasks. To achieve this, we engineered a local-first cascade system. The agent runs entirely within the strict grading constraints (CPU-only, 4GB RAM) by bundling a highly quantized `gemma:2b` model running locally via an embedded Ollama server. This local instance acts as our zero-cost primary solver, immediately handling simpler queries in categories like factual Q&A and sentiment analysis without consuming any external API tokens. When the local model detects low confidence or encounters complex reasoning, math, or coding tasks, the agent dynamically escalates the prompt to the cloud-based Fireworks AI API. We strictly constrain this fallback tier to utilize only the allowed Gemma 4 models (such as `gemma-4-31b-it`). By intelligently routing queries—using local compute for the easy tasks and reserving the cloud API solely for the difficult ones—our agent achieves an exceptional balance of high accuracy (easily passing the 84.2% gate) and minimal token expenditure. The entire system is packaged in a lean, self-contained Docker image well under the 10GB limit.

Team AIAutomation Submission

The solution is a hackathon onboarding ecosystem that helps participants move from registration to a working team setup with minimal friction by using a hackathon-specific onboarding page as the main source of truth for setup checklists, team assignment or team-creation instructions, submission rules, teammates, and mentor information, while an AI assistant only steps in when the page is unclear or when users need troubleshooting for issues like missing credits, promo codes, team confusion, or mentor lookup; the flow starts by identifying the participant’s hackathon and routing them to the correct page, then guides them through creating an AMD Developer Cloud account, claiming cloud credits, creating a Fireworks.ai account, redeeming promo credits, generating an API key, connecting that key to the AI builder, and linking GitHub so teams can access a boilerplate repository and collaborate quickly; at the team layer, it helps users find their team, team leader, teammates, Discord handles, GitHub usernames, team channels, repository links, and mentor details when available, and if data is missing or inconsistent it explains the limitation and points users back to the onboarding page or organizer instructions; the architecture should be model agnostic, token efficient, secure, observable, rate-limited, and evaluated for faithfulness, relevance, coherence, groundedness, and toxicity so the system remains reliable throughout the hackathon.