Hero Banner

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.

Unlimited Experts

Unlimited Experts

Investing is inherently an emotional game, often leading to reactive decisions and "FOMO." For the average trader, it is nearly impossible to keep up with the 24/7 global news cycle, and professional financial advice is frequently either too expensive or biased toward specific institutions. Unlimited Experts addresses these hurdles by deploying a network of specialized AI agents, each a dedicated expert in a specific asset class—such as Gold, EUR/USD, or Bitcoin. Our platform moves beyond simple chatbots by implementing a multi-agent "debate" architecture. These agents manage complex probabilities, synthesize global news, and track social trading trends in real-time. Instead of working in silos, the agents communicate with each other to refine their predictions and cross-reference market impacts (e.g., how a shift in Gold might affect EUR/USD). Users can subscribe to their preferred asset expert and interact in plain English, receiving 24/7 up-to-the-second updates. By removing the emotional friction and providing institutional-grade analysis through a scalable AI network, Unlimited Experts democratizes high-level financial intelligence.

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?

PartnerPulse - AI powered Partner churn prediction

PartnerPulse - AI powered Partner churn prediction

Stage 1a: Batch Churn Prediction PartnerPulse begins by analyzing the full partner portfolio (~5,000 partners), engineering 60+ behavioral, financial, and sentiment-based features from the last 6 months. These include commission trends, referral activity, login behavior, support tickets, sentiment signals, and competitor exposure. A bulk ML model (HistGradientBoostingRegressor) predicts churn risk, assigns LOW/MEDIUM/HIGH risk classes, and computes SHAP explanations for the top 50 highest-risk partners—making each prediction transparent and actionable. Stage 1b: Competitive Intelligence (Parallel) In parallel, the system assesses external market pressure by measuring multi-homing rates, share of voice, and sentiment gaps. It also scrapes key competitors (PocketOptions and OlympTrade) to capture both product positioning and affiliate program structures (commissions, CPA rates, tiers). This produces a structured, portfolio-wide competitive landscape. Stage 2: Churn Diagnosis Predictions and competitive insights are combined to diagnose why each partner is at risk. SHAP drivers are mapped to five root causes: Revenue Decline, Engagement Drop, Competitor Pressure, Support Dissatisfaction, and Platform Mismatch. Each partner receives a primary and secondary root cause with weighted attribution. Stage 3: Cohort Grouping & Action Partners are grouped into cohorts by root cause, partner type, and platform. Each cohort is assigned tailored retention strategies - ranging from commission restructuring and re-engagement campaigns to competitive counter-offers or support escalation which is refined by cohort size and risk severity. Stage 4: Internal Communication Insights are operationalized through automated executive briefings, real-time Slack alerts via OpenClaw, and a consolidated CEO-level summary-ensuring churn risk translates into timely, targeted action.

AI-Powered Multi-Agent Enterprise Platform

AI-Powered Multi-Agent Enterprise Platform

Deriv Agent is a comprehensive AI-powered agent management platform that transforms enterprise operations through intelligent automation and multi-agent collaboration. Built with Agno and OpenRouter, the platform addresses three core business challenges that require sophisticated AI capabilities. **HR Operations Automation**: The platform provides a self-service HR system that automates contract generation, answers policy questions through conversational AI, and tracks compliance proactively. Specialized agents handle document generation, policy Q&A, benefits administration, and compliance monitoring. Multi-agent teams collaborate to process complex HR workflows, from onboarding documentation to visa compliance tracking, dramatically reducing manual work and improving employee experience. **Financial Crime Detection**: The system employs advanced AI agents for transaction monitoring, anomaly detection, and network analysis to identify money laundering, fraud, and suspicious trading patterns in real-time. The platform uses behavioral anomaly detection, graph-based network analysis, and automated evidence collection to reduce false positives from thousands of alerts to high-confidence cases. Agents automatically generate suspicious activity reports (SARs) with full investigation packs ready for compliance review. **Trading Intelligence**: The platform provides comprehensive market analysis, behavioral coaching, and social content generation for traders. Specialized agents analyze market trends, explain price movements, detect emotional trading patterns, and generate engaging social media content. The system combines market intelligence with behavioral insights to help traders understand markets, recognize their own patterns, and stay informed through AI-generated content. The platform features a flexible architecture with multiple interfaces including a Telegram bot with live streaming of agent actions, a web UI, and a full REST API.

Traca

Traca

Overview traca is a split-view web platform combining live market dashboards with a conversational AI analyst. It delivers instant market intelligence through plain-language explanations of price movements and technical patterns, behavioral coaching that detects emotional trading signals like FOMO and revenge trading, and social automation via AI personas that generate platform-optimized content for LinkedIn and X. ✨ Core Features (MVP) Real-time Market Insights: Direct integration with Deriv API across Forex, Crypto, and Stock markets provides live pricing and historical data. Conversational AI: A unified chat interface handles market analysis queries, delivers behavioral feedback, and creates social media content in one seamless flow. Split-View Dashboard: Side-by-side layout presents live price charts, sentiment indicators, and AI analyst chat for efficient decision-making. Behavioral Pattern Detection: Advanced algorithms identify win/loss streaks, risk escalation patterns, and impulsive behavior, delivering timely nudges and habit-building reinforcement. Social Content Drafting: Platform-aware content generation produces professional LinkedIn posts and concise X updates tailored to each network's format. 🏗️ Architecture traca employs a Modular Monolith architecture optimized for real-time data streaming and AI inference: Frontend: React (Vite), TailwindCSS, shadcn/ui, and Zustand for state management. Backend: FastAPI (Python) with Uvicorn and WebSocket support for real-time communication. AI Engine: Mistral API cloud LLM for natural language understanding, market analysis, and content generation. Data Source: Deriv API integration for live market pricing, historical trade data, and account activity. Persistence: SQLite database stores trade history, session-based chat memory, and content drafts. This architecture ensures low-latency market data delivery, responsive AI interactions, and scalable performance.