원본과 구현 방법 살펴보기.
에이전트 정의서·예제 코드·워크플로·교육 과정과 개발 도구를 모았습니다. 자료별로 연결된 학습용 에이전트도 확인할 수 있습니다.
performance-monitor
Use when you need to analyze existing metric, log, and output files to spot performance patterns and anomalies, then write a grounded, evidence-cited observability plan (what to measure, thresholds, dashboards) as Markdown.
원본 환경 확인 필요
task-distributor
Use when you need to design and document a task-distribution strategy across multiple agents or workers — how to split work, order queues, respect priorities and deadlines, and balance load — written as a clear Markdown plan.
원본 환경 확인 필요
workflow-orchestrator
Use when you need to design workflow and state-machine definitions — states, transitions, error handling, and compensation/rollback logic — and write them as specs or config that other agents or a runtime can execute.
원본 환경 확인 필요
ab-test-analysis
Use when the user wants to analyze A/B test results, interpret p-values, determine statistical significance, or make a ship/no-ship decision. Triggers on: 'analyze A/B test', 'p-value', 'statistical significance', 'confidence interval', 'ship or no ship', 'test results', 'did it work'.
원본 환경 확인 필요
cohort-analysis
Use when the user wants to analyze retention, cohort behavior, engagement trends, or understand how different user groups perform over time. Triggers on: 'cohort analysis', 'retention analysis', 'user retention', 'cohort retention', 'week 1 retention', 'retention curve'.
원본 환경 확인 필요
competitive-analyst
Use when you need to analyze direct and indirect competitors, benchmark against market leaders, or develop strategies to strengthen competitive positioning and market advantage.
원본 환경 확인 필요
data-researcher
Use this agent when you need to discover, collect, and validate data from multiple sources to fuel analysis and decision-making. Invoke this agent for identifying data sources, gathering raw datasets, performing quality checks, and preparing data for downstream analysis or modeling.
원본 환경 확인 필요
first-principles-thinking
Use when the user wants to challenge assumptions, break down a complex problem from scratch, or approach something with first principles reasoning. Triggers on: 'first principles', 'challenge assumptions', 'why do we do it this way', 'rethink', 'from scratch', 'fundamental truths'.
원본 환경 확인 필요
market-researcher
Use this agent when you need to analyze markets, understand consumer behavior, assess competitive landscapes, and size opportunities to inform business strategy and market entry decisions.
원본 환경 확인 필요
project-idea-validator
Use this agent when you need an idea pressure-tested with brutal honesty, competitor teardown, market validation, and clear go/no-go guidance before building.
원본 환경 확인 필요
research-analyst
Use this agent when you need comprehensive research across multiple sources with synthesis of findings into actionable insights, trend identification, and detailed reporting.
원본 환경 확인 필요
scientific-literature-researcher
Use when you need to search scientific literature and retrieve structured experimental data from published studies. Invoke this agent when the task requires evidence-grounded answers from full-text research papers, including methods, results, sample sizes, and quality scores.
원본 환경 확인 필요
search-specialist
Use when you need to find specific information across multiple sources using advanced search strategies, query optimization, and targeted information retrieval. Invoke this agent when the priority is locating precise, relevant results efficiently rather than analyzing or synthesizing content.
원본 환경 확인 필요
trend-analyst
Use when analyzing emerging patterns, predicting industry shifts, or developing future scenarios to inform strategic planning and competitive positioning.
원본 환경 확인 필요
agentic_rag_embedding_gemma
This Streamlit app demonstrates an agentic Retrieval-Augmented Generation (RAG) Agent using Google's EmbeddingGemma for embeddings and Llama 3.2 as the language model, all running locally via Ollama.
원본 환경 확인 필요
🧠 Agentic RAG with GPT-5
An agentic RAG application built with the Agno framework, featuring GPT-5 and LanceDB for efficient knowledge retrieval and question answering.
원본 환경 확인 필요
🧠 Math Tutor Agent – Agentic RAG with Feedback Loop
This project implements an **Agentic-RAG architecture** to simulate a math professor that solves **JEE-level math questions** with step-by-step explanations. The system smartly routes queries between a vector database and web search, applies input/output guardrails, and incorporates human feedback for continuous learning.
원본 환경 확인 필요
🧐 Agentic RAG with Reasoning
A sophisticated RAG system that demonstrates an AI agent's step-by-step reasoning process using Agno, Gemini and OpenAI. This implementation allows users to add web sources, ask questions, and observe the agent's thought process in real-time with reasoning capabilities.
원본 환경 확인 필요
Typed Agentic RAG with Pydantic AI
This Streamlit app answers questions from uploaded PDFs or a documentation URL. Every response is a validated `Answer` object with exact source quotes, chunk IDs, a confidence score, and an `answered` decision. If retrieval is too weak, the app refuses before calling the language model.
원본 환경 확인 필요
Agentic RAG with LangGraph: AI Blog Search
2. **Run the Application**: ```bash streamlit run app.py ```
원본 환경 확인 필요
🤖 AutoRAG: Autonomous RAG with GPT-4o and Vector Database
**👉 [Click here to follow our complete step-by-step tutorial](https://www.theunwindai.com/p/build-autonomous-rag-app-using-gpt-4o-and-vector-database) and learn how to build this from scratch with detailed code walkthroughs, explanations, and best practices.**
원본 환경 확인 필요
Contextual AI RAG Agent
A Streamlit app that integrates Contextual AI's managed RAG platform. Create a datastore, ingest documents, spin up an agent, and chat grounded on your data.
원본 환경 확인 필요
🔄 Corrective RAG Agent
- **Smart Document Retrieval**: Uses Qdrant vector store for efficient document retrieval - **Document Relevance Grading**: Employs Claude 4.5 sonnet to assess document relevance - **Query Transformation**: Improves search results by optimizing queries when needed - **Web Search Fallback**: Uses Tavily API for web search when local documents aren't sufficient - **Multi-Model Approach**: Combines OpenAI embeddings and Claude 4.5 sonnet for different tasks - **Interactive UI**: Built with Streamlit for easy document upload and querying
원본 환경 확인 필요
🐋 Deepseek Local RAG Reasoning Agent
A powerful reasoning agent that combines local Deepseek models with RAG capabilities. Built using Deepseek (via Ollama), Snowflake for embeddings, Qdrant for vector storage, and Agno for agent orchestration, this application offers both simple local chat and advanced RAG-enhanced interactions with comprehensive document processing and web search capabilities.
원본 환경 확인 필요
🤔 Agentic RAG with Gemini Flash Thinking
A RAG Agentic system built with the new Gemini 2.0 Flash Thinking model and gemini-exp-1206, Qdrant for vector storage, and Agno (phidata prev) for agent orchestration. This application features intelligent query rewriting, document processing, and web search fallback capabilities to provide comprehensive AI-powered responses.
원본 환경 확인 필요
👀 RAG App with Hybrid Search
A powerful document Q&A application that leverages Hybrid Search (RAG) and Claude's advanced language capabilities to provide comprehensive answers. Built with RAGLite for robust document processing and retrieval, and Streamlit for an intuitive chat interface, this system seamlessly combines document-specific knowledge with Claude's general intelligence to deliver accurate and contextual responses.
원본 환경 확인 필요
🔍 Knowledge Graph RAG with Verifiable Citations
A Streamlit application demonstrating how **Knowledge Graph-based Retrieval-Augmented Generation (RAG)** provides multi-hop reasoning with fully verifiable source attribution.
원본 환경 확인 필요
llama3.1_local_rag
- The app loads the webpage data using WebBaseLoader and splits it into chunks using RecursiveCharacterTextSplitter. - It creates Ollama embeddings and a vector store using Chroma. - The app sets up a RAG (Retrieval-Augmented Generation) chain, which retrieves relevant documents based on the user's question. - The Llama-3.1 model is called to generate an answer using the retrieved context. - The app displays the answer to the user's question.
원본 환경 확인 필요
🖥️ Local RAG App with Hybrid Search
A powerful document Q&A application that leverages Hybrid Search (RAG) and local LLMs for comprehensive answers. Built with RAGLite for robust document processing and retrieval, and Streamlit for an intuitive chat interface, this system combines document-specific knowledge with local LLM capabilities to deliver accurate and contextual responses.
원본 환경 확인 필요
local_rag_agent
This application implements a Retrieval-Augmented Generation (RAG) system using Llama 3.2 via Ollama, with Qdrant as the vector database. Built with Agno v2.0.
원본 환경 확인 필요