```
├── .github/
├── workflows/
├── jekyll-gh-pages.yml (300 tokens)
├── CONTRIBUTION.md (1500 tokens)
├── LICENSE (omitted)
├── README.md (14.8k tokens)
├── crewai_mcp_course/
├── README.md (700 tokens)
├── images/
├── AIAgentUseCase.jpg
├── Awesome AI Agent UseCases Industry Include _ Healthcare, Finance, Education, Customer Service, Retail, Transportation, Manufacturing, RealEstate, Agriculture, Energy, Entertainment, Legal, Human Resource, Hosp (1).jpg
├── Awesome AI Agent UseCases Industry Include _ Healthcare, Finance, Education, Customer Service, Retail, Transportation, Manufacturing, RealEstate, Agriculture, Energy, Entertainment, Legal, Human Resource, Hospital.jpg
├── industry_usecase.png
├── industry_usecase1.png
```
## /.github/workflows/jekyll-gh-pages.yml
```yml path="/.github/workflows/jekyll-gh-pages.yml"
# Sample workflow for building and deploying a Jekyll site to GitHub Pages
name: Deploy Jekyll with GitHub Pages dependencies preinstalled
on:
# Runs on pushes targeting the default branch
push:
branches: ["main"]
# Allows you to run this workflow manually from the Actions tab
workflow_dispatch:
# Sets permissions of the GITHUB_TOKEN to allow deployment to GitHub Pages
permissions:
contents: read
pages: write
id-token: write
# Allow only one concurrent deployment, skipping runs queued between the run in-progress and latest queued.
# However, do NOT cancel in-progress runs as we want to allow these production deployments to complete.
concurrency:
group: "pages"
cancel-in-progress: false
jobs:
# Build job
build:
runs-on: ubuntu-latest
steps:
- name: Checkout
uses: actions/checkout@v4
- name: Setup Pages
uses: actions/configure-pages@v5
- name: Build with Jekyll
uses: actions/jekyll-build-pages@v1
with:
source: ./
destination: ./_site
- name: Upload artifact
uses: actions/upload-pages-artifact@v3
# Deployment job
deploy:
environment:
name: github-pages
url: ${{ steps.deployment.outputs.page_url }}
runs-on: ubuntu-latest
needs: build
steps:
- name: Deploy to GitHub Pages
id: deployment
uses: actions/deploy-pages@v4
```
## /CONTRIBUTION.md
# Contributing to 500-AI-Agents-Projects
Welcome — this repository collects 500 AI agent projects, templates, demos, and integrations. Thank you for helping grow a practical, reproducible, and responsible catalog of agent work. This document is tuned to the AI-agent focus of the project: reproducibility, model/data hygiene, evaluation, and safety.
Quick summary
- Add small, runnable, well-documented agent examples and templates.
- Prefer reproducible demos and small checkpoints or external download scripts.
- Follow the folder schema and metadata so projects are discoverable and automatable.
- Pay attention to license, data provenance, and ethical/safety notes.
---
## What to contribute
- New agent projects (single- or multi-agent; code, notebooks, or demos).
- Templates/boilerplates for agent types (reactive, planning-based, learning agents, RL, LLM-based, etc.).
- Integrations (environments, simulators, observability / logging tools).
- Shared tooling (evaluation harnesses, metrics, benchmark suites, dataset loaders).
- Docs, reproducible experiments, visualization utilities, or lightweight datasets (or links to them).
If your contribution is large (new category, many projects, major refactor) please open an issue first to coordinate placement and naming.
---
## Project folder requirements (must-have)
Each agent project added must include the following at the top level of its folder:
- README.md — concise description, intended use-case, quick start with exact commands, expected output, and runtime (CPU/GPU/time).
- LICENSE or a note referencing repository root LICENSE (see root LICENSE).
- requirements.txt, pyproject.toml, or environment.yml (pin critical dependency versions).
- One or more runnable examples (script or notebook) that reproduce the core behavior.
- Provide minimal example(s) that run in <10 minutes on a modest machine where possible.
- tests/ or a smoke-test script with instructions to run them.
- metadata.yaml or metadata.json (see example below).
- small models / datasets should be included only if tiny. Prefer external hosting (Hugging Face, S3, Google Drive) with a download script.
Example metadata schema (recommended)
```yaml
title: quick-chatbot-agent
author: Your Name <you@example.com>
language: python
tags:
- llm
- agent
- rl
license: MIT
datasets:
- name: example-dialogs
url: https://...
entrypoint: run_demo.py
requirements: requirements.txt
```
---
## Naming & layout conventions
- Folder names: lowercase, hyphen-separated (e.g., multi-agent-pursuit).
- Place one logical project per folder.
- Keep demos and notebooks near the code: demo.ipynb and run_demo.py in the project root.
- Avoid committing large binaries. Use .gitattributes or .gitignore to keep repository clean.
---
## Reproducibility & experiments
- Include seed values, environment variables, and exact dependency versions.
- Provide a minimal run command and expected output sample.
- For stochastic experiments, include evaluation scripts and deterministic seeds or checkpoints.
- If results require large compute or private data, include a small reproducible “toy” example that demonstrates the same pipeline on tiny inputs.
---
## Models, datasets & large files policy
- Don’t add large datasets or model checkpoints directly. Instead:
- Provide a download script (download.sh / download.py) that fetches artifacts from a stable host (Hugging Face, S3, Zenodo).
- Document the expected location/path after download.
- Clearly state dataset licenses, attribution, and any usage restrictions.
- When linking to external model weights provide their license and any fine-tuning provenance.
---
## Code style, documentation & tests
- Python: follow PEP 8, add a linter config (.flake8, pyproject.toml with [tool.black] or similar).
- JS/TS: provide ESLint/Prettier configs where relevant.
- Document complex algorithms with short docstrings and references.
- Add unit or integration tests when possible. Include a lightweight smoke test that CI can run quickly.
---
## Evaluation & metrics
- Include an evaluation script that produces metrics (accuracy, reward, latency).
- State measurement conditions (hardware, seeds).
- Where applicable, include latency and memory cost alongside performance metrics.
---
## CI / GitHub Actions recommendations
- If adding workflows, put them under .github/workflows and ensure expensive jobs are optional or use small inputs.
- Recommended checks: lint, unit tests, smoke demos. Heavy training jobs should be omitted or gated/opt-in.
---
## PR process and checklist
Before opening a PR:
- [ ] Fork and create a branch: feat/<short-desc> or fix/<short-desc>
- [ ] Update README and metadata
- [ ] Include tests or a smoke-test demonstration
- [ ] Ensure no secrets or private data are included
- [ ] Confirm license compatibility for added assets
PR description should include:
- What changed and why
- How to run the example(s) and tests
- Links to related issues or external artifacts (datasets, model hosts)
Suggested minimal PR template (add to .github/PULL_REQUEST_TEMPLATE.md if helpful):
```markdown
## Summary
Short description of change
## How to run
1. pip install -r requirements.txt
2. python run_demo.py
## Checklist
- [ ] README updated
- [ ] metadata.yaml added/updated
- [ ] smoke test included
```
---
## Security, secrets & responsible disclosure
- Never commit secrets, private keys, or API tokens.
- If you discover a security vulnerability, do not open a public issue. Contact maintainers privately (see repository contact info) or use GitHub's private security advisory.
---
## Ethics, fairness & safety
AI agents can amplify harms. When contributing:
- Include an explicit "Ethical considerations" or "Safety notes" section in the README if the agent interacts with people, makes decisions, or processes personal data.
- State potential biases, failure modes, and appropriate usage guidance.
- Avoid shipping models trained on clearly disallowed data (private or scraped personal content without consent).
- Prefer human-in-the-loop defaults for high-risk demos and clearly mark such demos as not production-ready.
---
## Licensing and attribution
- Respect upstream licenses for models, code, and datasets. Include attribution and license text where required.
- If the project uses third-party models/datasets, list their license and link to the source.
---
## Communication & review
- Maintainers will review PRs and may request changes. Please reply to review comments and push updates.
- For large or disruptive changes, maintainers may ask for staged PRs to ease review.
---
## Contributor support & contact
If you need early feedback:
- Open an issue describing your planned contribution with the following: summary, folder name, and minimal example of what you plan to add.
- For urgent or private matters, use the contact method listed in the repository (owner profile / repo settings).
---
## Code of Conduct
By contributing, you agree to the project's Code of Conduct. Be respectful, constructive, and collaborative.
---
<<<<<<< HEAD
Thank you for contributing to 500-AI-Agents-Projects — your examples, templates, and tools make the agent community stronger and more reproducible.
=======
Thank you for contributing to 500-AI-Agents-Projects — your examples, templates, and tools make the agent community stronger and more reproducible.
>>>>>>> f5a092190b226a6723718d7680aa689f1d2b64bc
## /README.md
# 🌟 500+ AI Agent Projects / UseCases
[](https://github.com/ashishpatel26/500-AI-Agents-Projects)
A curated collection of AI agent use cases across industries, showcasing practical applications and linking to open-source projects for implementation. Explore how AI agents are transforming industries like healthcare, finance, education, and more! 🤖✨
---
## 📋 Table of Contents
- [Introduction](#introduction)
- [Industry Usecase](#-industry-usecase-mindmap)
- [Use Case Table](#use-case-table)
- [Framework Wise UseCase](#framework-wise-usecases)
- [CrewAI UseCase](#framework-name-crewai)
- [AutoGen UseCase](#framework-name-autogen)
- [Agno UseCase](#framework-name-agno)
- [Langgraph UseCase](#framework-name-langgraph)
- [Contributing](#contributing)
- [License](#license)
---
## 🧠 Introduction
Artificial Intelligence (AI) agents are revolutionizing the way industries operate. From personalized learning to financial trading bots, AI agents bring efficiency, innovation, and scalability. This repository provides:
- A categorized list of industries where AI agents are making an impact.
- Detailed use cases with links to open-source projects for implementation.
Whether you're a developer, researcher, or business enthusiast, this repository is your go-to resource for AI agent inspiration and learning.
---
## 🏭 Industry UseCase MindMap
---
## 🧩 Use Case Table
| Use Case | Industry | Description | Code Github |
| ------------------------------------------- | ---------------- | -------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| **HIA (Health Insights Agent)** | Healthcare | analyses medical reports and provide health insights. | [](https://github.com/harshhh28/hia.git) |
| **AI Health Assistant** | Healthcare | Diagnoses and monitors diseases using patient data. | [](https://github.com/ahmadvh/AI-Agents-for-Medical-Diagnostics.git) |
| **Automated Trading Bot** | Finance | Automates stock trading with real-time market analysis. | [](https://github.com/MingyuJ666/Stockagent.git) |
| **Virtual AI Tutor** | Education | Provides personalized education tailored to users. | [](https://github.com/hqanhh/EduGPT.git) |
| **24/7 AI Chatbot** | Customer Service | Handles customer queries around the clock. | [](https://github.com/NirDiamant/GenAI_Agents/blob/main/all_agents_tutorials/customer_support_agent_langgraph.ipynb) |
| **Product Recommendation Agent** | Retail | Suggests products based on user preferences and history. | [](https://github.com/microsoft/RecAI) |
| **Self-Driving Delivery Agent** | Transportation | Optimizes routes and autonomously delivers packages. | [](https://github.com/sled-group/driVLMe) |
| **Factory Process Monitoring Agent** | Manufacturing | Monitors production lines and ensures quality control. | [](https://github.com/yuchenxia/llm4ias) |
| **Property Pricing Agent** | Real Estate | Analyzes market trends to determine property prices. | [](https://github.com/AleksNeStu/ai-real-estate-assistant) |
| **Smart Farming Assistant** | Agriculture | Provides insights on crop health and yield predictions. | [](https://github.com/mohammed97ashraf/LLM_Agri_Bot) |
| **Energy Demand Forecasting Agent** | Energy | Predicts energy usage to optimize grid management. | [](https://github.com/yecchen/MIRAI) |
| **Content Personalization Agent** | Entertainment | Recommends personalized media based on preferences. | [](https://github.com/crosleythomas/MirrorGPT) |
| **Legal Document Review Assistant** | Legal | Automates document review and highlights key clauses. | [](https://github.com/firica/legalai) |
| **Recruitment Recommendation Agent** | Human Resources | Suggests best-fit candidates for job openings. | [](https://github.com/sentient-engineering/jobber) |
| **Virtual Travel Assistant** | Hospitality | Plans travel itineraries based on preferences. | [](https://github.com/nirbar1985/ai-travel-agent) |
| **AI Game Companion Agent** | Gaming | Enhances player experience with real-time assistance. | [](https://github.com/onjas-buidl/LLM-agent-game) |
| **Real-Time Threat Detection Agent** | Cybersecurity | Identifies potential threats and mitigates attacks. | [](https://github.com/NVISOsecurity/cyber-security-llm-agents) |
| **E-commerce Personal Shopper Agent** | E-commerce | Helps customers find products they’ll love. | [](https://github.com/Hoanganhvu123/ShoppingGPT) |
| **Logistics Optimization Agent** | Supply Chain | Plans efficient delivery routes and manages inventory. | [](https://github.com/microsoft/OptiGuide) |
| **Vibe Hacking Agent** | Cybersecurity | Autonomous Multi-Agent Based Red Team Testing Service. | [](https://github.com/PurpleAILAB/Decepticon) |
| **MediSuite-Ai-Agent** | Health insurance | A medical ai agent that helps automating the process of hospitals / insurance claiming workflow. | [](https://github.com/MahmoudRabea13/MediSuite-Ai-Agent) |
| **Lina-Egyptian-Medical-Chatbot** | Health insurance | A medical ai agent that helps automating the process of hospitals / insurance claiming workflow. | [](https://github.com/MahmoudRabea13/MediSuite-Ai-Agent) |
## Framework wise Usecases
---
### **Framework Name**: **CrewAI**
| Use Case | Industry | Description | GitHub |
| -------------------------------- | ----------------------- | -------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------- |
| 📧 Email Auto Responder Flow | 🗣️ Communication | Automates email responses based on predefined criteria to enhance communication efficiency. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/flows/email_auto_responder_flow) |
| 📝 Meeting Assistant Flow | 🛠️ Productivity | Assists in organizing and managing meetings, including scheduling and agenda preparation. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/flows/meeting_assistant_flow) |
| 🔄 Self Evaluation Loop Flow | 👥 Human Resources | Facilitates self-assessment processes within an organization, aiding in performance reviews. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/flows/self_evaluation_loop_flow) |
| 📈 Lead Score Flow | 💼 Sales | Evaluates and scores potential leads to prioritize outreach in sales strategies. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/flows/lead-score-flow) |
| 📊 Marketing Strategy Generator | 📢 Marketing | Develops marketing strategies by analyzing market trends and audience data. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/marketing_strategy) |
| 📝 Job Posting Generator | 🧑💼 Recruitment | Creates job postings by analyzing job requirements, aiding in recruitment processes. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/job-posting) |
| 🔄 Recruitment Workflow | 🧑💼 Recruitment | Streamlines the recruitment process by automating various tasks involved in hiring. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/recruitment) |
| 🔍 Match Profile to Positions | 🧑💼 Recruitment | Matches candidate profiles to suitable job positions to enhance recruitment efficiency. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/match_profile_to_positions) |
| 📸 Instagram Post Generator | 📱 Social Media | Generates and schedules Instagram posts automatically, streamlining social media management. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/instagram_post) |
| 🌐 Landing Page Generator | 💻 Web Development | Automates the creation of landing pages for websites, facilitating web development tasks. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/landing_page_generator) |
| 🎮 Game Builder Crew | 🎮 Game Development | Assists in the development of games by automating certain aspects of game creation. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/game-builder-crew) |
| 💹 Stock Analysis Tool | 💰 Finance | Provides tools for analyzing stock market data to assist in financial decision-making. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/stock_analysis) |
| 🗺️ Trip Planner | ✈️ Travel | Assists in planning trips by organizing itineraries and managing travel details. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/trip_planner) |
| 🎁 Surprise Trip Planner | ✈️ Travel | Plans surprise trips by selecting destinations and activities based on user preferences. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/surprise_trip) |
| 📚 Write a Book with Flows | ✍️ Creative Writing | Assists authors in writing books by providing structured workflows and writing assistance. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/flows/write_a_book_with_flows) |
| 🎬 Screenplay Writer | ✍️ Creative Writing | Aids in writing screenplays by offering templates and guidance for script development. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/screenplay_writer) |
| ✅ Markdown Validator | 📄 Documentation | Validates Markdown files to ensure proper formatting and adherence to standards. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/markdown_validator) |
| 🧠 Meta Quest Knowledge | 📚 Knowledge Management | Manages and organizes knowledge related to Meta Quest, facilitating information retrieval. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/meta_quest_knowledge) |
| 🤖 NVIDIA Models Integration | 🤖 AI Integration | Integrates NVIDIA AI models into workflows to enhance computational capabilities. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/integrations/nvidia_models) |
| 🗂️ Prep for a Meeting | 🛠️ Productivity | Assists in preparing for meetings by organizing materials and setting agendas. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/prep-for-a-meeting) |
| 🛠️Starter Template | 🛠️ Development | Provides a starter template for new projects to streamline the setup process. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/crews/starter_template) |
| 🔗CrewAI + LangGraph Integration | 🤖 AI Integration | Demonstrates integration between CrewAI and LangGraph for enhanced workflow automation. | [](https://github.com/crewAIInc/crewAI-examples/tree/main/integrations/CrewAI-LangGraph) |
### **Framework Name**: **Autogen**
> **Code Generation, Execution, and Debugging**
| Use Case | Industry | Description | Notebook |
| --------------------------------------------------------------------------------------- | ----------------------- | --------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🤖 Automated Task Solving with Code Generation, Execution & Debugging | 💻 Software Development | Demonstrates automated task-solving by generating, executing, and debugging code. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_auto_feedback_from_code_execution) |
| 🧑💻 Automated Code Generation and Question Answering with Retrieval Augmented Agents | 💻 Software Development | Generates code and answers questions using retrieval-augmented methods. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_RetrieveChat) |
| 🧠 Automated Code Generation and Question Answering with Qdrant-based Retrieval | 💻 Software Development | Utilizes Qdrant for enhanced retrieval-augmented agent performance. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_RetrieveChat_qdrant) |
> **Multi-Agent Collaboration (>3 Agents)**
| Use Case | Industry | Description | Notebook |
| :----------------------------------------------------------------------- | :-------------------------- | :------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| 🤝 Automated Task Solving by Group Chat (3 members, 1 manager) | 🤝 Collaboration | Demonstrates group task-solving via multi-agent collaboration. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_groupchat) |
| 📊 Automated Data Visualization by Group Chat (3 members, 1 manager) | 📊 Data Analysis | Uses multi-agent collaboration to create data visualizations. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_groupchat_vis) |
| 🧩 Automated Complex Task Solving by Group Chat (6 members, 1 manager) | 🤝 Collaboration | Solves complex tasks collaboratively with a larger group of agents. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_groupchat_research) |
| 🧑💻 Automated Task Solving with Coding & Planning Agents | 🛠️ Planning & Development | Combines coding and planning agents for solving tasks effectively. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_planning.ipynb) |
| 📐 Automated Task Solving with Transition Paths Specified in a Graph | 🤝 Collaboration | Uses predefined transition paths in a graph for solving tasks. | [](https://microsoft.github.io/autogen/docs/notebooks/agentchat_groupchat_finite_state_machine) |
| 🧠 Running a Group Chat as an Inner-Monologue via the SocietyOfMindAgent | 🧠 Cognitive Sciences | Simulates inner-monologue for problem-solving using group chats. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_society_of_mind) |
| 🔧 Running a Group Chat with Custom Speaker Selection Function | 🤝 Collaboration | Implements a custom function for speaker selection in group chats. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_groupchat_customized) |
> **Sequential Multi-Agent Chats**
| Use Case | Industry | Description | Notebook |
| :--------------------------------------------------------------------------------- | :--------------------- | :------------------------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🔄 Solving Multiple Tasks in a Sequence of Chats Initiated by a Single Agent | 🔄 Workflow Automation | Automates sequential task-solving with a single initiating agent. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_multi_task_chats) |
| ⏳ Async-solving Multiple Tasks in a Sequence of Chats Initiated by a Single Agent | 🔄 Workflow Automation | Handles asynchronous task-solving in a sequence of chats initiated by one agent. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_multi_task_async_chats) |
| 🤝 Solving Multiple Tasks in a Sequence of Chats Initiated by Different Agents | 🔄 Workflow Automation | Facilitates sequential task-solving with different agents initiating each chat. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchats_sequential_chats) |
> **Nested Chats**
| Use Case | Industry | Description | Notebook |
| :----------------------------------------------------------------------------- | :--------------------------- | :------------------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🧠 Solving Complex Tasks with Nested Chats | 🧠 Problem Solving | Uses nested chats to solve hierarchical and complex problems. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_nestedchat) |
| 🔄 Solving Complex Tasks with A Sequence of Nested Chats | 🧠 Problem Solving | Demonstrates sequential task-solving using nested chats. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_nested_sequential_chats) |
| 🏭 OptiGuide for Solving a Supply Chain Optimization Problem with Nested Chats | 🏭 Supply Chain Optimization | Showcases how to solve supply chain optimization problems using nested chats, a coding agent, and a safeguard agent. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_nestedchat_optiguide) |
| ♟️ Conversational Chess with Nested Chats and Tool Use | 🎮 Gaming | Explores the use of nested chats for playing conversational chess with integrated tools. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_nested_chats_chess) |
> **Application**
| Use Case | Industry | Description | Notebook |
| :------------------------------------------------------------------------------------------------- | :--------------------------- | :------------------------------------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| 🔄 Automated Continual Learning from New Data | 📊 Machine Learning | Continuously learns from new data inputs for adaptive AI. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_stream.ipynb) |
| 🏭 OptiGuide - Coding, Tool Using, Safeguarding & Question Answering for Supply Chain Optimization | 🏭 Supply Chain Optimization | Highlights a solution combining coding, tool use, and safeguarding for supply chain optimization. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_nestedchat_optiguide) |
| 🤖 AutoAnny - A Discord bot built using AutoGen | 💬 Communication Tools | Showcases the development of a Discord bot using AutoGen for enhanced interaction. | [](https://github.com/microsoft/autogen/tree/main/samples/apps/auto-anny) |
> **Tools**
| Use Case | Industry | Description | Notebook |
| :--------------------------------------------------------------------- | :----------------------------- | :------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🌐 Web Search: Solve Tasks Requiring Web Info | 🔍 Information Retrieval | Searches the web to gather information required for completing tasks. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_web_info.ipynb) |
| 🔧 Use Provided Tools as Functions | 🛠️ Tool Integration | Demonstrates how to use pre-provided tools as callable functions in AutoGen. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_function_call_currency_calculator) |
| 🔗 Use Tools via Sync and Async Function Calling | 🛠️ Tool Integration | Illustrates synchronous and asynchronous tool usage within AutoGen workflows. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_function_call_async) |
| 🧩 Task Solving with Langchain Provided Tools as Functions | 🔍 Language Processing | Leverages Langchain tools for task-solving within AutoGen. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_langchain.ipynb) |
| 📚 RAG: Group Chat with Retrieval Augmented Generation | 🤝 Collaboration | Enables group chat with Retrieval Augmented Generation (RAG) to support information sharing. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_groupchat_RAG) |
| ⚙️ Function Inception: Update/Remove Functions During Conversations | 🔧 Development Tools | Allows AutoGen agents to modify their functions dynamically during conversations. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_inception_function.ipynb) |
| 🔊 Agent Chat with Whisper | 🎙️ Audio Processing | Demonstrates AI agent capabilities for transcription and translation using Whisper. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_video_transcript_translate_with_whisper) |
| 📏 Constrained Responses via Guidance | 💡 Natural Language Processing | Shows how to use guidance to constrain responses generated by agents. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_guidance.ipynb) |
| 🌍 Browse the Web with Agents | 🌐 Information Retrieval | Explains how to configure agents to browse and retrieve information from the web. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_surfer.ipynb) |
| 📊 SQL: Natural Language Text to SQL Query Using Spider Benchmark | 💾 Database Management | Converts natural language inputs into SQL queries using the Spider benchmark. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_sql_spider.ipynb) |
| 🕸️ Web Scraping with Apify | 🌐 Data Gathering | Illustrates web scraping techniques with Apify using AutoGen. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_webscraping_with_apify) |
| 🕷️ Web Crawling: Crawl Entire Domain with Spider API | 🌐 Data Gathering | Explains how to crawl entire domains using the Spider API. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_webcrawling_with_spider) |
| 💻 Write a Software App Task by Task with Specially Designed Functions | 💻 Software Development | Builds a software application step-by-step using designed functions. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_function_call_code_writing.ipynb) |
> **Human Development**
| Use Case | Industry | Description | Notebook |
| :--------------------------------------------------------------- | :---------------------- | :------------------------------------------------------------------------------------------------ | :------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| 💬 Simple Example in ChatGPT Style | 🧠 Conversational AI | Demonstrates a simple conversational example in the style of ChatGPT. | [](https://github.com/microsoft/autogen/blob/0.2/samples/simple_chat.py) |
| 🤖 Auto Code Generation, Execution, Debugging and Human Feedback | 💻 Software Development | Showcases code generation, execution, debugging with human feedback integrated into the workflow. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_human_feedback.ipynb) |
| 👥 Automated Task Solving with GPT-4 + Multiple Human Users | 🤝 Collaboration | Enables task solving with multiple human users collaborating with GPT-4. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_two_users.ipynb) |
| 🔄 Agent Chat with Async Human Inputs | 🧠 Conversational AI | Supports asynchronous human input during agent conversations. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/Async_human_input.ipynb) |
> **Agent Teaching and Learning**
| Use Case | Industry | Description | Notebook |
| :------------------------------------------------------------------- | :-------------------------- | :--------------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 📘 Teach Agents New Skills & Reuse via Automated Chat | 🎓 Education & Training | Demonstrates teaching new skills to agents and enabling their reuse in automated chats. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_teaching) |
| 🧠 Teach Agents New Facts, User Preferences and Skills Beyond Coding | 🎓 Education & Training | Shows how to teach agents new facts, user preferences, and non-coding skills. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_teachability) |
| 🤖 Teach OpenAI Assistants Through GPTAssistantAgent | 💻 AI Assistant Development | Illustrates how to enhance OpenAI assistants' capabilities using GPTAssistantAgent. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_teachable_oai_assistants.ipynb) |
| 🔄 Agent Optimizer: Train Agents in an Agentic Way | 🛠️ Optimization | Explains how to train agents effectively in an agentic manner using the Agent Optimizer. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_agentoptimizer.ipynb) |
> **Multi-Agent Chat with OpenAI Assistants in the loop**
| Use Case | Industry | Description | Notebook |
| :-------------------------------------------------------- | :----------------------- | :---------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🌟 Hello-World Chat with OpenAI Assistant in AutoGen | 🤖 Conversational AI | A basic example of chatting with OpenAI Assistant using AutoGen. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_oai_assistant_twoagents_basic.ipynb) |
| 🔧 Chat with OpenAI Assistant using Function Call | 🔧 Development Tools | Illustrates how to use function calls with OpenAI Assistant in chats. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_oai_assistant_function_call.ipynb) |
| 🧠 Chat with OpenAI Assistant with Code Interpreter | 💻 Software Development | Demonstrates the use of OpenAI Assistant as a code interpreter in chats. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_oai_code_interpreter.ipynb) |
| 🔍 Chat with OpenAI Assistant with Retrieval Augmentation | 📚 Information Retrieval | Enables retrieval-augmented conversations with OpenAI Assistant. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_oai_assistant_retrieval.ipynb) |
| 🤝 OpenAI Assistant in a Group Chat | 🤝 Collaboration | Shows how OpenAI Assistant can collaborate with other agents in a group chat. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_oai_assistant_groupchat.ipynb) |
| 🛠️ GPTAssistantAgent based Multi-Agent Tool Use | 🔧 Development Tools | Explains how to use GPTAssistantAgent for multi-agent tool usage. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/gpt_assistant_agent_function_call.ipynb) |
> **Non-OpenAI Models**
| Use Case | Industry | Description | Notebook |
| :------------------------------------------------ | :-------- | :---------------------------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| ♟️ Conversational Chess using Non-OpenAI Models | 🎮 Gaming | Explores conversational chess implemented with non-OpenAI models. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_nested_chats_chess_altmodels) |
> **Multimodal Agent**
| Use Case | Industry | Description | Notebook |
| :--------------------------------------------- | :------------------ | :-------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🎨 Multimodal Agent Chat with DALLE and GPT-4V | 🖼️ Multimedia AI | Combines DALLE and GPT-4V for multimodal agent communication. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_dalle_and_gpt4v.ipynb) |
| 🖌️ Multimodal Agent Chat with Llava | 📷 Image Processing | Uses Llava for enabling multimodal agent conversations with image processing. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_lmm_llava.ipynb) |
| 🖼️ Multimodal Agent Chat with GPT-4V | 🖼️ Multimedia AI | Leverages GPT-4V for visual and conversational interactions in multimodal agents. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_lmm_gpt-4v.ipynb) |
> **Long Context Handling**
| Use Case | Industry | Description | Notebook |
| :--------------------------------------- | :--------------- | :--------------------------------------------------------------------------------- | :---------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 📜 Long Context Handling as A Capability | 🧠 AI Capability | Demonstrates techniques for handling long context effectively within AI workflows. | [](https://microsoft.github.io/autogen/0.2/docs/notebooks/agentchat_transform_messages) |
> **Evaluation and Assessment**
| Use Case | Industry | Description | Notebook |
| :----------------------------------------------------------------------------------- | :------------------------ | :------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------- |
| 📊 AgentEval: A Multi-Agent System for Assessing Utility of LLM-Powered Applications | 📈 Performance Evaluation | Introduces AgentEval for evaluating and assessing the performance of LLM-based applications. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agenteval_cq_math.ipynb) |
> **Automatic Agent Building**
| Use Case | Industry | Description | Notebook |
| :------------------------------------------------------------ | :---------------- | :------------------------------------------------------------------------------------ | :----------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🏗️ Automatically Build Multi-agent System with AgentBuilder | 🤖 AI Development | Explains how to automatically build multi-agent systems using the AgentBuilder tool. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/autobuild_basic.ipynb) |
| 📚 Automatically Build Multi-agent System from Agent Library | 🤖 AI Development | Shows how to construct multi-agent systems by leveraging a pre-defined agent library. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/autobuild_agent_library.ipynb) |
> **Observability**
| Use Case | Industry | Description | Notebook |
| :---------------------------------------------------------------- | :------------------------ | :----------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------ |
| 📊 Track LLM Calls, Tool Usage, Actions and Errors using AgentOps | 📈 Monitoring & Analytics | Demonstrates how to monitor LLM interactions, tool usage, and errors using AgentOps. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_agentops.ipynb) |
> **Enhanced Inferences**
| Use Case | Industry | Description | Notebook |
| :--------------------------------------------------------------------- | :----------------- | :----------------------------------------------------------------------------------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🔗 API Unification | 🔧 API Management | Explains how to unify API usage with documentation and code examples. | [](https://microsoft.github.io/autogen/docs/Use-Cases/enhanced_inference/#api-unification) |
| ⚙️ Utility Functions to Help Managing API Configurations Effectively | 🔧 API Management | Demonstrates utility functions to manage API configurations more effectively. | [](https://microsoft.github.io/autogen/0.2/docs/topics/llm_configuration) |
| 💰 Cost Calculation | 📈 Cost Management | Introduces methods for tracking token usage and estimating costs for LLM interactions. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/agentchat_cost_token_tracking.ipynb) |
| ⚡ Optimize for Code Generation | 📊 Optimization | Highlights cost-effective optimization techniques for improving code generation with LLMs. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/oai_completion.ipynb) |
| 📐 Optimize for Math | 📊 Optimization | Explains techniques to optimize LLM performance for solving mathematical problems. | [](https://github.com/microsoft/autogen/blob/0.2/notebook/oai_chatgpt_gpt4.ipynb) |
### **Framework Name**: **Agno**
> **UseCase**
| Use Case | Industry | Description | Notebook |
| :--------------------------------- | :----------------------------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| 🤖 Support Agent | 💻 Software Development / AI / Framework Support | The Agno Support Agent helps developers with the Agno framework by providing real-time answers, explanations, and code examples. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/agno_support_agent.py) |
| 🎥 YouTube Agent | 📺 Media & Content | An intelligent agent that analyzes YouTube videos by generating detailed summaries, timestamps, themes, and content breakdowns using AI tools. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/youtube_agent.py) |
| 📊 Finance Agent | 💼 Finance | An advanced AI-powered market analyst that delivers real-time stock market insights, analyst recommendations, financial deep-dives, and sector-specific trends. Supports prompts for detailed analysis of companies like AAPL, TSLA, NVDA, etc. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/thinking_finance_agent.py) |
| 📚 Study Partner | 🎓 Education | Assists users in learning by finding resources, answering questions, and creating study plans. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/study_partner.py) |
| 🛍️ Shopping Partner Agent | 🏬 E-commerce | A product recommender agent that helps users find matching products based on preferences from trusted platforms like Amazon, Flipkart, etc. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/shopping_partner.py) |
| 🎓 Research Scholar Agent | 🧠 Education / Research | An AI-powered academic assistant that performs advanced academic searches, analyzes recent publications, synthesizes findings across disciplines, and writes well-structured academic reports with proper citations. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/research_agent_exa.py) |
| 🧠 Research Agent | 🗞️ Media & Journalism | A research agent that combines web search and professional journalistic writing. It performs deep investigations and produces NYT-style reports. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/research_agent.py) |
| 🍳 Recipe Creator | 🍽️ Food & Culinary | An AI-powered recipe recommendation agent that provides personalized recipes based on ingredients, preferences, and time constraints. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/recipe_creator.py) |
| 🗞️ Finance Agent | 💼 Finance | A powerful financial analyst agent combining real-time stock data, analyst insights, company fundamentals, and market news. Ideal for analyzing companies like Apple, Tesla, NVIDIA, and sectors like semiconductors or automotive. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/finance_agent.py) |
| 🧠 Financial Reasoning Agent | 📈 Finance | Uses a Claude-3.5 Sonnet-based agent to analyze stocks like NVDA using tools for reasoning and Yahoo Finance data. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/reasoning_finance_agent.py) |
| 🤖 Readme Generator Agent | 💻 Software Dev | Agent generates high-quality READMEs for GitHub repositories using repo metadata. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/readme_generator.py) |
| 🎬 Movie Recommendation Agent | 🎥 Entertainment | An intelligent agent that gives personalized movie recommendations using Exa and GPT-4o, analyzing genres, themes, and latest ratings. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/movie_recommedation.py) |
| 🔍 Media Trend Analysis Agent | 📰 Media & News | Analyzes emerging trends, patterns, and influencers from digital platforms using AI-powered agents and scraping. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/media_trend_analysis_agent.py) |
| ⚖️ Legal Document Analysis Agent | 🏛️ Legal Tech | An AI agent that analyzes legal documents from PDF URLs and provides legal insights based on a knowledge base using vector embeddings and GPT-4o. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/legal_consultant.py) |
| 🤔 DeepKnowledge | 🧠 Research | This agent performs iterative searches through its knowledge base, breaking down complex queries into sub-questions and synthesizing comprehensive answers. It uses Agno docs for demonstration and is designed for deep reasoning and exploration. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/deep_knowledge.py) |
| 📚 Book Recommendation Agent | 🧠 Publishing & Media | An intelligent agent that provides personalized book suggestions using literary data, reader preferences, reviews, and release info. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/book_recommendation.py) |
| 🏠 MCP Airbnb Agent | 🛎️ Hospitality | Create an AI Agent using MCP and Llama 4 to search Airbnb listings with filters like workspace & transport proximity. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/airbnb_mcp.py) |
| 🤖 Assist Agent | 🧠 AI Framework | An AI agent using GPT-4o to answer questions about the Agno framework with hybrid search and embedded knowledge. | [](https://github.com/agno-agi/agno/blob/main/cookbook/examples/agents/agno_assist.py) |
### **Framework Name**: **Langgraph**
> **UseCase**
| Use Case | Industry | Description | Notebook |
| :------------------------------------ | :---------------------------- | :----------------------------------------------------------- | :----------------------------------------------------------- |
| 🤖 Chatbot Simulation Evaluation | 💻 💬 AI / Quality Assurance | Simulate user interactions to evaluate chatbot performance, ensuring robustness and reliability in real-world scenarios. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/chatbot-simulation-evaluation/agent-simulation-evaluation.ipynb) |
| 🧠 Information Gathering via Prompting | 🧠 AI / Research & Development | This tutorial demonstrates how to design a LangGraph workflow that utilizes prompting techniques to gather information effectively. It showcases how to structure prompts and manage the flow of information to build intelligent agents. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/chatbots/information-gather-prompting.ipynb) |
| 🧠 Code Assistant with LangGraph | 💻 Software Development | This tutorial demonstrates how to build a resilient code assistant using LangGraph. It guides you through creating a graph-based agent that can handle code generation, error checking, and iterative refinement, ensuring robust and accurate coding assistance. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/code_assistant/langgraph_code_assistant.ipynb) |
| 🧑💼 Customer Support Agent | 🧑💼 Customer Support Agent | This tutorial demonstrates how to build a customer support agent using LangGraph. It guides you through creating a graph-based agent that can handle customer inquiries, providing automated support and enhancing user experience. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/customer-support/customer-support.ipynb) |
| 🔁 Extraction with Retries | 🧠 AI / Data Extraction | This tutorial demonstrates how to implement retry mechanisms in LangGraph workflows, ensuring robust data extraction processes that can handle transient errors and improve reliability. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/extraction/retries.ipynb) |
| 🧠 Multi-Agent Workflow | 🧠 AI / Workflow Orchestration | This tutorial demonstrates how to build a multi-agent system using LangGraph's agent supervisor. It guides you through creating a supervisor agent that orchestrates multiple specialized agents, managing task delegation and communication flow. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/multi_agent/agent_supervisor.ipynb) |
| 🧠 Hierarchical Agent Teams | 🧠 AI / Workflow Orchestration | This tutorial demonstrates how to build a hierarchical agent system using LangGraph. It guides you through creating a top-level supervisor agent that delegates tasks to specialized sub-agents, enabling complex workflows with clear task delegation and communication. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/multi_agent/hierarchical_agent_teams.ipynb) |
| 🤝 Multi-Agent Collaboration | 🧠 AI / Workflow Orchestration | This tutorial demonstrates how to implement multi-agent collaboration using LangGraph. It guides you through creating multiple specialized agents that work together to accomplish a complex task, showcasing the power of agent collaboration in AI workflows. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/multi_agent/multi-agent-collaboration.ipynb) |
| 🧠 Plan-and-Execute Agent | 🧠 AI / Workflow Orchestration | This tutorial demonstrates how to build a "Plan-and-Execute" style agent using LangGraph. It guides you through creating an agent that first generates a multi-step plan and then executes each step sequentially, revisiting and modifying the plan as necessary. This approach is inspired by the Plan-and-Solve paper and the Baby-AGI project, aiming to enhance long-term planning and task execution in AI workflows. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/plan-and-execute/plan-and-execute.ipynb) |
| 🧠 SQL Agent | 🧠 AI / Database Interaction | This tutorial demonstrates how to build an agent that can answer questions about a SQL database. The agent fetches available tables, determines relevance to the question, retrieves schemas, generates a query, checks for errors, executes it, and formulates a response. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/sql-agent.ipynb) |
| 🧠 Reflection Agent | 🧠 AI / Workflow Orchestration | This tutorial demonstrates how to build a reflection agent using LangGraph. It guides you through creating an agent that can critique and revise its own outputs, enhancing the quality and reliability of generated content. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/reflection/reflection.ipynb)|
| 🧠 Reflexion Agent | 🧠 AI / Workflow Orchestration | This tutorial demonstrates how to build a reflexion agent using LangGraph. It guides you through creating an agent that can reflect on its actions and outcomes, enabling iterative improvement and more accurate decision-making in complex workflows. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/reflexion/reflexion.ipynb)|
| **LangGraph Agentic RAG** | | | |
| 🧠 **Adaptive RAG** | 🧠 AI / Information Retrieval | This tutorial demonstrates how to build an Adaptive RAG system using LangGraph. It guides you through creating a dynamic retrieval process that adjusts based on query complexity, enhancing the efficiency and accuracy of information retrieval. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/rag/langgraph_adaptive_rag.ipynb) |
| 🧠 **Adaptive RAG (Local)** | 🧠 AI / Information Retrieval | This tutorial focuses on implementing Adaptive RAG with local models, allowing for offline retrieval and generation, which is crucial for environments with limited internet access or privacy concerns. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/rag/langgraph_adaptive_rag_local.ipynb) |
| 🤖 **Agentic RAG** | 🤖 AI / Intelligent Agents | Learn to build an Agentic RAG system where an agent determines the best retrieval strategy before generating a response, improving the relevance and accuracy of answers. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/rag/langgraph_agentic_rag.ipynb) |
| 🤖 **Agentic RAG (Local)** | 🤖 AI / Intelligent Agents | This tutorial extends Agentic RAG to local environments, enabling the use of local models and data sources for retrieval and generation tasks. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/rag/langgraph_agentic_rag_local.ipynb) |
| 🧠 **Corrective RAG (CRAG)** | 🧠 AI / Information Retrieval | Implement a Corrective RAG system that evaluates and refines retrieved documents before passing them to the generator, ensuring higher-quality outputs. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/rag/langgraph_crag.ipynb) |
| 🧠 **Corrective RAG (Local)** | 🧠 AI / Information Retrieval | This tutorial focuses on building a Corrective RAG system using local resources, allowing for offline document evaluation and refinement processes. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/rag/langgraph_crag_local.ipynb) |
| 🧠 **Self-RAG** | 🧠 AI / Information Retrieval | Learn to implement Self-RAG, where the system reflects on its responses and retrieves additional information if necessary, enhancing the accuracy and relevance of generated content. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/rag/langgraph_self_rag.ipynb) |
| 🧠 **Self-RAG (Local)** | 🧠 AI / Information Retrieval | This tutorial demonstrates how to implement Self-RAG using local models and data sources, enabling offline reflection and retrieval processes. | [](https://github.com/langchain-ai/langgraph/blob/main/docs/docs/tutorials/rag/langgraph_self_rag_local.ipynb) |
---
## 🤝 Contributing
Contributions are welcome! 🎉 Here's how you can help:
1. Fork the repository.
2. Add a new use case or improve an existing one.
3. Submit a pull request with your changes.
Please follow our [Contributing Guidelines](CONTRIBUTING.md) for more details.
---
## 📜 License
This repository is licensed under the MIT License. See the [LICENSE](LICENSE) file for more information.
---
## 🚀 Let's Build Together!
Feel free to share this repository with your network and star ⭐ it if you find it useful. Let’s collaborate to create the ultimate resource for AI agent use cases!
## /crewai_mcp_course/README.md
# CrewAI with FastMCP Server Integration Course
This course teaches beginners how to use CrewAI with FastMCP server access through step-by-step programming examples.
## Course Overview
This course is designed for beginner developers with basic Python knowledge who want to learn how to integrate CrewAI agents with FastMCP servers. The course covers fundamental concepts, practical implementation, and advanced patterns for building intelligent agent workflows.
## Lessons
### Lesson 1: Setting up CrewAI with MCP Server Access
- Install required packages
- Set up environment variables
- Create a basic CrewAI agent
- Execute simple tasks
```mermaid
graph TD
A[Install Packages] --> B[Set Environment Variables]
B --> C[Create CrewAI Agent]
C --> D[Execute Task]
```
### Lesson 2: Integrating MCP Server with CrewAI
- Create custom tools for MCP server access
- Configure authentication and connection settings
- Use MCP server data in agent tasks
- Handle errors and exceptions
```mermaid
graph TD
A[Create FastMCP Tool] --> B[Configure Authentication]
B --> C[Create Agent with Tool]
C --> D[Execute Task with MCP Data]
D --> E[Handle Response]
```
### Lesson 3: Advanced CrewAI Patterns with MCP Server
- Implement multi-agent workflows
- Use hierarchical processes
- Share data between agents through the MCP server
- Store and retrieve research findings
- Implement quality assurance processes
```mermaid
graph TD
A[Researcher Agent] -->|Query| B(FastMCP Server)
B -->|Return Data| A
A -->|Share Findings| C[Writer Agent]
C -->|Create Report| D[Reviewer Agent]
D -->|Provide Feedback| C
C -->|Final Report| E[Output]
```
## Getting Started
### Using pip (traditional method)
1. Install the required packages:
```bash
pip install -r requirements.txt
```
2. Set up your environment variables:
```bash
export FASTMCP_URL=http://your-fastmcp-server-url:port
export FASTMCP_API_KEY=your-api-key
```
3. Run the examples:
```bash
python lesson1_setup.py
python lesson2_mcp_integration.py
python lesson3_advanced_patterns.py
```
### Using uv (recommended modern method)
[uv](https://github.com/astral-sh/uv) is a fast Python package installer and resolver. To use uv:
1. Install uv:
```bash
pip install uv
```
2. Create and activate a virtual environment:
```bash
uv venv
source .venv/Scripts/activate
```
3. Install dependencies:
```bash
uv pip install -r requirements.txt
```
4. Set up your environment variables:
```bash
export FASTMCP_URL=http://your-fastmcp-server-url:port
export FASTMCP_API_KEY=your-api-key
```
5. Run the examples:
```bash
python lesson1_setup.py
python lesson2_mcp_integration.py
python lesson3_advanced_patterns.py
```
## Requirements
- Python 3.8+
- CrewAI library
- FastMCP library
- Access to an MCP server
## Course Structure
Each lesson includes:
- A Python script with comprehensive comments
- Clear objectives and expected outcomes
- Step-by-step implementation
- Best practices for error handling and security
## Next Steps
After completing this course, you should be able to:
- Create and configure CrewAI agents
- Integrate MCP servers with agent workflows
- Build complex multi-agent systems
- Implement data sharing between agents
- Design robust error handling for production systems
## /images/AIAgentUseCase.jpg
Binary file available at https://raw.githubusercontent.com/ashishpatel26/500-AI-Agents-Projects/refs/heads/main/images/AIAgentUseCase.jpg
## /images/Awesome AI Agent UseCases Industry Include _ Healthcare, Finance, Education, Customer Service, Retail, Transportation, Manufacturing, RealEstate, Agriculture, Energy, Entertainment, Legal, Human Resource, Hosp (1).jpg
Binary file available at https://raw.githubusercontent.com/ashishpatel26/500-AI-Agents-Projects/refs/heads/main/images/Awesome AI Agent UseCases Industry Include _ Healthcare, Finance, Education, Customer Service, Retail, Transportation, Manufacturing, RealEstate, Agriculture, Energy, Entertainment, Legal, Human Resource, Hosp (1).jpg
## /images/Awesome AI Agent UseCases Industry Include _ Healthcare, Finance, Education, Customer Service, Retail, Transportation, Manufacturing, RealEstate, Agriculture, Energy, Entertainment, Legal, Human Resource, Hospital.jpg
Binary file available at https://raw.githubusercontent.com/ashishpatel26/500-AI-Agents-Projects/refs/heads/main/images/Awesome AI Agent UseCases Industry Include _ Healthcare, Finance, Education, Customer Service, Retail, Transportation, Manufacturing, RealEstate, Agriculture, Energy, Entertainment, Legal, Human Resource, Hospital.jpg
## /images/industry_usecase.png
Binary file available at https://raw.githubusercontent.com/ashishpatel26/500-AI-Agents-Projects/refs/heads/main/images/industry_usecase.png
## /images/industry_usecase1.png
Binary file available at https://raw.githubusercontent.com/ashishpatel26/500-AI-Agents-Projects/refs/heads/main/images/industry_usecase1.png
The better and more specific the context, the better the LLM can follow instructions. If the context seems verbose, the user can refine the filter using uithub. Thank you for using https://uithub.com - Perfect LLM context for any GitHub repo.