Top Builders

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

Generative Agents

Generative Agents are computer programs designed to replicate human actions and responses within interactive software. To create believable individual and group behavior, they utilize memory, reflection, and planning in combination. These agents have the ability to recall past experiences, make inferences about themselves and others, and devise strategies based on their surroundings. They have a wide range of applications, including creating immersive environments, rehearsing interpersonal communication, and prototyping. In a simulated world resembling The Sims, automated agents can interact, build relationships, and collaborate on group tasks while users watch and intervene as necessary.

General
Relese dateApril 7, 2023
TypeAutonomous Agent Simulation

Start building with Generative Agents

We have collected the best Generative Agents libraries and resources to help you get started to build with Generative Agents today. To see what others are building with Generative Agents, check out the community built Generative Agents Use Cases and Applications.

Generative Agents Tutorials

Generative Agents resources

Kickstart your development with Generative Agents.

Edit on GitHub

Generative Agents AI technology page Hackathon projects

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

OmniClaims Adjuster

OmniClaims Adjuster

OmniClaims Adjuster: El Futuro de la Liquidación de Siniestros En la actualidad, el procesamiento de reclamos de seguros es un proceso manual, lento y propenso a errores. OmniClaims Adjuster revoluciona el sector Insurtech mediante una arquitectura multi-agente totalmente autónoma construida sobre la familia de modelos Gemini 3.1 de Google. Diseñado para la AI Agent Olympics Hackathon, este sistema actúa como un ajustador de seguros experto. En lugar de depender de un solo modelo monolítico, el flujo de trabajo orquesta múltiples agentes especializados trabajando en paralelo y en tiempo real: 1. Agente de Extracción: Transforma las narrativas no estructuradas del cliente en datos estructurados estandarizados bajo esquemas estrictos de Pydantic. 2. Agente de Pólizas: Analiza los términos contractuales (PDFs) verificando límites, deducibles, exclusiones y coberturas con precisión milimétrica. 3. Agente de Visión (Daños): Aprovecha la multimodalidad nativa de Gemini 3.1 Pro para examinar fotografías de evidencias, evaluando la severidad y la congruencia del daño reportado. 4. Agente Antifraude: Detecta anomalías cruzando variables (ej. inconsistencias entre la historia del cliente y la evidencia visual) para emitir una puntuación de riesgo. 5. Agente Orquestador: Consolida todos los análisis en una decisión final holística (Aprobado, Rechazado o Revisión Manual). A nivel técnico, la plataforma cuenta con un backend en FastAPI y una interfaz Gradio con diseño premium glassmorphism. Priorizando la explicabilidad (AI Transparency), el sistema expone en la UI todo el Chain of Thought (Razonamiento) de los agentes. OmniClaims Adjuster no reemplaza al ajustador humano; lo empodera resolviendo automáticamente el 80% de los casos claros y entregando un dossier procesado de alta inteligencia para los reclamos complejos.

Storyteller: Autonomous Multi-Agent

Storyteller: Autonomous Multi-Agent

Storyteller is an autonomous multi-agent AI system designed for publishing houses and EdTech platforms to generate safe, high-quality children's literature at scale. Unlike traditional single-prompt LLM systems, Storyteller uses a structured narrative execution engine powered by multiple specialized agents. The Planner constructs a story DAG, the Generator creates content, the Extractor updates narrative state, and the Verifier enforces strict constraints such as reading level, safety, and tone. The system includes an intelligent repair loop, automatically correcting content that violates safety or quality constraints. This ensures reliable, brand-safe storytelling suitable for young audiences. Storyteller also features a modern React-based dashboard for managing stories, reviewing outputs, and controlling generation parameters. By combining multi-agent orchestration, stateful reasoning, and model routing, Storyteller reduces content creation time by up to 90% while maintaining high quality and safety standards. This project demonstrates how agentic AI systems can move beyond simple text generation to deliver structured, production-ready workflows.

Rehaby

Rehaby

Rehaby is an AI-powered rehabilitation intelligence platform designed to bridge the gap between hospital-based physiotherapy and home recovery. Many patients receive proper monitoring and rehabilitation support while admitted in hospitals, but after discharge, rehabilitation often becomes unsupervised. Patients may perform exercises incorrectly, lose motivation, misunderstand instructions, or skip therapy sessions completely. This problem is especially common among elderly, post-surgical, orthopedic, neurological, and cardiovascular rehabilitation patients who may also face difficulties traveling long distances for short clinical follow-ups. Improper rehabilitation can increase recovery time, risk of re-injury, and workload on healthcare professionals. Rehaby addresses this challenge through an intelligent AI-driven rehabilitation ecosystem that enables patients to safely continue physiotherapy exercises from home while remaining connected with clinicians. The platform combines computer vision, real-time posture tracking, and adaptive rehabilitation intelligence to analyze patient movements and provide immediate corrective feedback. Using technologies such as MediaPipe Pose, OpenCV, TensorFlow Lite, and FastAPI, Rehaby performs live joint angle analysis, posture correction, repetition counting, and movement scoring directly through a web-based interface. The patient-side application offers real-time camera posture tracking, skeleton overlays, AI voice guidance, visual corrective feedback, and session summaries to improve exercise accuracy and adherence. On the clinician side, a mobile dashboard allows healthcare professionals to monitor patient progress remotely through analytics, form score trends, session histories, and recovery performance insights. The system also supports Urdu voice interaction and low-bandwidth accessibility to improve usability for diverse patient populations.

NEXUS — Multi-Agent Enterprise Intelligence System

NEXUS — Multi-Agent Enterprise Intelligence System

**NEXUS** is a collaborative multi-agent system that listens to enterprise meetings in real-time, retrieves relevant knowledge, routes decisions to specialized domain agents, and autonomously executes follow-up actions — all without human relay. **NEXUS** listens to enterprise meetings, retrieves relevant knowledge, routes decisions to specialized domain agents, and autonomously executes follow-up actions — closing the full loop from voice → context → reasoning → action. Enterprise managers lose **40% of their day** to fragmented information. Meetings produce decisions — but those decisions get buried in transcripts, never reach the right expert, and never trigger automated action. **NEXUS closes the gap.** Voice → brain → action, fully autonomous.

nuncio

nuncio

nuncio is an autonomous agentic pipeline built to solve one of the biggest friction points in enterprise sales and recruiting: generic outreach. While personalized video can increase reply rates by 3–5x, it has traditionally been impossible to scale. nuncio changes that by turning any public social profile into a hyper-personalized 1:1 video pitch in under 90 seconds. The platform operates as a linear, autonomous workflow. TinyFish first enriches and cleans public profiles from LinkedIn, X, and other sources to extract relevant context and achievements. An AI coaching agent then identifies strong personalization angles and helps tailor the message toward goals like sales, recruiting, or investor outreach. Claude 3.5/Qwen3 synthesizes the profile data, selected angles, and sender brief into a coherent script that references the target’s real work. The Melius MCP creative agent assembles visuals and thumbnails on a persistent canvas, while HeyGen’s Video Agent renders a structured three-scene video using the sender’s cloned voice and avatar. Finally, the video is delivered through a branded landing page with auto-generated captions and one-click translation into 8+ languages. Built for the intelligent enterprise, nuncio goes beyond static templates by enabling sales and HR teams to deliver outreach that feels deeply researched and genuinely human. With built-in credit protection, rate limiting, and an open production architecture powered by Turso and Vultr, nuncio is designed as a scalable foundation for automated yet truly personal enterprise communication.