A curated archive of 313 AI prompts for ChatGPT, Claude, Gemini, and anywhere else you need them. Search, filter by category, and copy with one click.
License notices for bundled JS libraries including React, decimal.js-light, and lucide-react.
/*! decimal.js-light v2.5.1 https://github.com/MikeMcl/decimal.js-light/LICENCE */ /** * @license React * react-dom-client.production.js * * Copyright (c) Meta Platforms, Inc. and affiliates. * * This source code is licensed under the MIT license found in the * LICENSE file in the root directory of this source tree. */ /** * @license React * react-dom.production.js * * Copyright (c)
Defines a multi-agent AI architecture for coordinated travel planning covering flights, hotels, dining, budgets, and itineraries.
TripCraft AI uses a sophisticated multi-agent system powered by Agno to create personalized travel experiences. This document explains the different agents and their roles in the system. ## Team Structure The system is orchestrated by the "TripCraft AI Team", which coordinates multiple specialized agents to create comprehensive travel plans. The team operates in a coordinated mode, ensuring all
Defines an XML template for an agent action option with evaluate, memory, thought, action name, input, and route fields.
```xml
<Option>
<Evaluate>{evaluate}</Evaluate>
<Memory>{memory}</Memory>
<Thought>{thought}</Thought>
<Action-Name>{action_name}</Action-Name>
<Action-Input>{action_input}</Action-Input>
<Route>Action</Route>
</Option>
```
Structured observation template for an AI agent tracking desktop state, UI elements, and execution steps.
```xml
<Observation>
Execution Step: ({steps}/{max_steps})
Action Response: {observation}
[Start of Desktop State]
Cursor Location: {cursor_location}
Foreground Application: {active_app}
Opened Applications:
{apps}
List of Interactive Elements:
{interactive_elements}
List of Scrollable Elements:
{scrollable_elements}
List of Informative Elements:
{informative_elements}
[End of Desktop Sta
AI agent for automating Windows GUI and CLI tasks with structured planning and tool use.
You are "Windows-Use," a highly proficient AI assistant specializing in Windows desktop automation. Your purpose is to understand user requests, intelligently plan sequences of actions, interact with the GUI and CLI, and solve problems much like an expert human Windows user would. You are meticulous, adaptive, and resourceful. Your primary directive is to successfully and accurately complete the u
XML template for structuring an agent response with evaluate, memory, thought, and final answer fields.
```xml
<Option>
<Evaluate>{evaluate}</Evaluate>
<Memory>{memory}</Memory>
<Thought>{thought}</Thought>
<Final-Answer>{final_answer}</Final-Answer>
<Route>Answer</Route>
</Option>
```
A requirements.txt listing specific versions of agno, streamlit, qdrant-client, and ollama packages.
agno>=2.2.10 streamlit==1.40.2 qdrant-client==1.12.1 ollama==0.4.4
Boilerplate README for a Next.js app with Prisma database setup, dev server instructions, and Vercel deployment guide.
This is a [Next.js](https://nextjs.org) project bootstrapped with [`create-next-app`](https://nextjs.org/docs/app/api-reference/cli/create-next-app). ## Setup 1. **Install dependencies:** ```bash pnpm install ``` 2. **Configure environment:** ```bash cp .env.example .env.local ``` Update `.env.local` with your database credentials if needed. 3. **Setup database:** `
A robots.txt file allowing all user agents full access with no disallowed paths.
User-agent: * Disallow:
A robots.txt file allowing all user agents full access with no disallowed paths.
User-agent: * Disallow:
Multi-agent Streamlit app using specialized AI educators to create personalized learning plans via Google Docs.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-ai-teaching-agent-team) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** A Streamlit application that brings together a team of specialized AI teaching agents who collaborate like a professional teaching
A list of Python package dependencies for a Streamlit AI application with OpenAI and search integrations.
streamlit==1.41.1 openai==1.58.1 duckduckgo-search==6.4.1 typing-extensions>=4.5.0 agno>=2.2.10 composio-phidata==0.6.9 composio_core composio==0.1.1 google-search-results==2.4.2
Simulates a full digital agency with five specialized AI agents covering strategy, tech, product, dev, and marketing.
An AI application that simulates a full-service digital agency using multiple AI agents to analyze and plan software projects. Each agent represents a different role in the project lifecycle, from strategic planning to technical implementation. ## Demo: https://github.com/user-attachments/assets/a0befa3a-f4c3-400d-9790-4b9e37254405 ## Features ### Five specialized AI agents - **CEO Agent**:
A requirements file listing Python package dependencies including dotenv, agency-swarm, and streamlit.
python-dotenv==1.1.1 agency-swarm==1.7.0 streamlit
Multi-agent pipeline using Google ADK and Gemini to generate competitive sales battle cards with SWOT, objections, and visuals.
A multi-agent AI pipeline that generates competitive sales battle cards in real-time, built with [Google ADK](https://google.github.io/adk-docs/) and Gemini 3. **Give it a competitor + your product** → Get a complete battle card with positioning strategies, objection handling scripts, and visual comparisons. ## Features - 🔍 **Live Research** - Real-time web search for competitor intelligence -
Minimal requirements file specifying google-adk and google-genai package dependencies.
google-adk>=1.0.0 google-genai>=1.0.0
Autonomous multi-agent SEO audit tool using Google ADK, Firecrawl MCP, and Gemini to crawl, analyze, and report.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-ai-seo-audit-team-with-gemini) and learn how to build this AI SEO Audit Team from scratch with detailed code walkthroughs, explanations, and best practices.** The **AI SEO Audit Team** is an autonomous, multi-agent workflow built with Google ADK. It takes a webpag
Defines Python project dependencies including google-adk and pydantic v2.7.0+.
google-adk pydantic>=2.7.0
Multi-agent Streamlit app simulating a legal team with researcher, analyst, strategist, and coordinator roles.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-ai-legal-team-run-by-ai-agents) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** A Streamlit application that simulates a full-service legal team using multiple AI agents to analyze legal documents and p
A requirements file listing Python dependencies including agno, streamlit, qdrant-client, openai, pypdf, and duckduckgo-search.
agno>=2.2.10 streamlit qdrant-client openai pypdf duckduckgo-search
Multi-agent GPT-4o system combining web search and YFinance for comprehensive financial analysis in Python.
## 💲 AI Finance Agent Team with Web Access
This script demonstrates how to build a team of AI agents that work together as a financial analyst using GPT-4o in just 20 lines of Python code. The system combines web search capabilities with financial data analysis tools to provide comprehensive financial insights.
### Features
- Multi-agent system with specialized roles:
- Web Agent for general
A list of Python package dependencies including OpenAI, Agno, DuckDuckGo search, yfinance, and SQLAlchemy.
openai agno>=2.2.10 duckduckgo-search yfinance sqlalchemy
Streamlit multi-agent research app with routing, fallback, verification, and synthesis built on AG2.
A Streamlit app that blends agent teamwork with agent-enabled routing and fallback, built entirely on AG2. ## What This Shows - **Agent teamwork**: explicit roles and sequential handoffs - **Agent-enabled routing**: a clear decision step with local-doc vs web fallback - **AG2-first implementation**: no Microsoft AutoGen dependency; installs via `ag2[openai]` ## Features - Local document upload
Specifies minimum version dependencies for ag2 OpenAI, Streamlit, and pypdf packages.
ag2[openai]>=0.11.0 streamlit>=1.33.0 pypdf>=4.2.0
Multi-agent system using Google ADK and Gemini to analyze landing pages, provide UI/UX feedback, and generate improvements.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-ai-ui-ux-feedback-agent-team-with-nano-banana) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** A sophisticated multi-agent system built with Google ADK that analyzes landing page designs, provides exper
Lists core Python dependencies: google-adk, python-dotenv, and pydantic.
google-adk python-dotenv pydantic
Multi-agent system using Firecrawl and Exa AI to crawl competitor websites and generate strategic analysis reports.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-ai-competitor-intelligence-agent-team) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.** The AI Competitor Intelligence Agent Team is a powerful competitor analysis tool powered by Firecrawl and Agno's A
Lists specific Python package dependencies with version constraints for a project.
firecrawl-py==1.9.0 duckduckgo-search==7.2.1 agno>=2.2.10 streamlit==1.41.1
Multi-agent platform for property search, market analysis, and valuations using Firecrawl and AI.
### 🎓 FREE Step-by-Step Tutorial **👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-an-ai-real-estate-agent-team) and learn how to build this AI SEO Audit Team from scratch with detailed code walkthroughs, explanations, and best practices.** The **AI Real Estate Agent Team** is a sophisticated property search and analysis platform powered by special
Lists Python dependencies with version constraints for a Streamlit-based AI application.
streamlit>=1.28.0 agno>=2.2.10 openai>=1.0.0 firecrawl-py>=1.9.0 pydantic>=2.7.0 python-dotenv>=1.0.0 requests>=2.31.0 googlesearch-python>=1.2.3