Skip to content

100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.

readme: add one-line hooks to every remaining category entry

ci21d2b796fe9a
diff --git a/README.md b/README.md
index 00240eab..7ba19ed3 100644
--- a/README.md
+++ b/README.md
@@ -135,7 +135,7 @@ streamlit run travel_agent.py
*Background agents that run on schedules or events, monitor changing context, decide what needs attention, and proactively deliver updates, artifacts, or actions.*
-* [๐Ÿ“ฐ Always-on Hacker News Briefing Agent](always_on_agents/always_on_hn_briefing_agent/)
+* [๐Ÿ“ฐ Always-on Hacker News Briefing Agent](always_on_agents/always_on_hn_briefing_agent/) - A scheduled scout that ships a ranked daily brief to Slack or email
### ๐Ÿค Multi-agent Teams
@@ -169,78 +169,78 @@ streamlit run travel_agent.py
*Agents that render interactive UI components, not just text: forms, cards, charts, editable plans.*
-* [๐Ÿ—‚๏ธ Generative UI Starter Project](generative_ui_agents/generative-ui-starter-project/)
-* [๐Ÿช™ AI Financial Coach Agent](generative_ui_agents/ai-financial-coach-agent/)
-* [๐Ÿ“Š AI Dashboard Canvas Agent](generative_ui_agents/ai-dashboard-canvas-agent/)
-* [๐Ÿ› ๏ธ AI MCP App Builder](generative_ui_agents/ai-mcp-app-builder/)
-* [โœˆ๏ธ MCP Apps Generative UI Showcase](generative_ui_agents/mcp-apps-generative-ui-showcase/)
-* [๐ŸŽ›๏ธ AI Shadcn Component Generator](generative_ui_agents/ai-shadcn-component-generator/)
-* [๐Ÿ” AI Deep Research Agent](generative_ui_agents/ai-deep-research-agent/)
+* [๐Ÿ—‚๏ธ Generative UI Starter Project](generative_ui_agents/generative-ui-starter-project/) - A chat-driven kanban board you and the agent work together
+* [๐Ÿช™ AI Financial Coach Agent](generative_ui_agents/ai-financial-coach-agent/) - Budget, savings, and debt plans rendered as interactive cards
+* [๐Ÿ“Š AI Dashboard Canvas Agent](generative_ui_agents/ai-dashboard-canvas-agent/) - Describe a dashboard in chat, charts assemble on a live canvas
+* [๐Ÿ› ๏ธ AI MCP App Builder](generative_ui_agents/ai-mcp-app-builder/) - Describe an MCP app, get a live sandboxed instance back
+* [โœˆ๏ธ MCP Apps Generative UI Showcase](generative_ui_agents/mcp-apps-generative-ui-showcase/) - MCP apps that render real interactive UI, flight search included
+* [๐ŸŽ›๏ธ AI Shadcn Component Generator](generative_ui_agents/ai-shadcn-component-generator/) - Chat your way to production-ready shadcn components
+* [๐Ÿ” AI Deep Research Agent](generative_ui_agents/ai-deep-research-agent/) - Research where every tool call renders as a live workspace card
### ๐ŸŽฎ Autonomous Game-Playing Agents
*Agents that play games end-to-end: reasoning, strategy, and action.*
-* [๐ŸŽฎ AI 3D Pygame Agent](advanced_ai_agents/autonomous_game_playing_agent_apps/ai_3dpygame_r1/)
-* [โ™œ AI Chess Agent](advanced_ai_agents/autonomous_game_playing_agent_apps/ai_chess_agent/)
-* [๐ŸŽฒ AI Tic-Tac-Toe Agent](advanced_ai_agents/autonomous_game_playing_agent_apps/ai_tic_tac_toe_agent/)
+* [๐ŸŽฎ AI 3D Pygame Agent](advanced_ai_agents/autonomous_game_playing_agent_apps/ai_3dpygame_r1/) - DeepSeek R1 writes PyGame code, browser agents run it live
+* [โ™œ AI Chess Agent](advanced_ai_agents/autonomous_game_playing_agent_apps/ai_chess_agent/) - Agent White vs Agent Black with validated moves
+* [๐ŸŽฒ AI Tic-Tac-Toe Agent](advanced_ai_agents/autonomous_game_playing_agent_apps/ai_tic_tac_toe_agent/) - Two different LLMs battle it out, move by move
### โ™พ๏ธ MCP AI Agents
*Agents that connect to external tools and data via Model Context Protocol.*
-* [โ™พ๏ธ Browser MCP Agent](mcp_ai_agents/browser_mcp_agent/)
-* [๐Ÿ™ GitHub MCP Agent](mcp_ai_agents/github_mcp_agent/)
-* [๐Ÿ“‘ Notion MCP Agent](mcp_ai_agents/notion_mcp_agent)
-* [๐ŸŒ AI Travel Planner MCP Agent](mcp_ai_agents/ai_travel_planner_mcp_agent_team)
-* [๐Ÿ”€ Multi-MCP Agent Router](mcp_ai_agents/multi_mcp_agent_router/)
+* [โ™พ๏ธ Browser MCP Agent](mcp_ai_agents/browser_mcp_agent/) - Drive a real browser with natural language over MCP
+* [๐Ÿ™ GitHub MCP Agent](mcp_ai_agents/github_mcp_agent/) - Explore and analyze any repo in plain English
+* [๐Ÿ“‘ Notion MCP Agent](mcp_ai_agents/notion_mcp_agent) - Talk to your Notion pages from the terminal
+* [๐ŸŒ AI Travel Planner MCP Agent](mcp_ai_agents/ai_travel_planner_mcp_agent_team) - Itineraries built on live Airbnb and Google Maps data
+* [๐Ÿ”€ Multi-MCP Agent Router](mcp_ai_agents/multi_mcp_agent_router/) - Specialist agents, each wired to its own MCP server
### ๐Ÿ“€ RAG (Retrieval Augmented Generation)
*Retrieval pipelines, from simple chains to agentic and multi-source.*
-* [๐Ÿ”ฅ Agentic RAG with Embedding Gemma](rag_tutorials/agentic_rag_embedding_gemma)
-* [๐Ÿง Agentic RAG with Reasoning](rag_tutorials/agentic_rag_with_reasoning/)
-* [๐Ÿ“ฐ AI Blog Search (RAG)](rag_tutorials/ai_blog_search/)
-* [๐Ÿ” Autonomous RAG](rag_tutorials/autonomous_rag/)
-* [๐Ÿ”„ Contextual AI RAG Agent](rag_tutorials/contextualai_rag_agent/)
-* [๐Ÿ”„ Corrective RAG (CRAG)](rag_tutorials/corrective_rag/)
-* [๐Ÿ‹ Deepseek Local RAG Agent](rag_tutorials/deepseek_local_rag_agent/)
-* [๐Ÿค” Gemini Agentic RAG](rag_tutorials/gemini_agentic_rag/)
-* [๐Ÿ‘€ Hybrid Search RAG (Cloud)](rag_tutorials/hybrid_search_rag/)
-* [๐Ÿ”„ Llama 3.1 Local RAG](rag_tutorials/llama3.1_local_rag/)
-* [๐Ÿ–ฅ๏ธ Local Hybrid Search RAG](rag_tutorials/local_hybrid_search_rag/)
-* [๐Ÿงฌ Multimodal Agentic RAG](rag_tutorials/multimodal_agentic_rag/)
-* [๐Ÿฆ™ Local RAG Agent](rag_tutorials/local_rag_agent/)
-* [๐Ÿงฉ RAG-as-a-Service](rag_tutorials/rag-as-a-service/)
-* [โœจ RAG Agent with Cohere](rag_tutorials/rag_agent_cohere/)
-* [โ›“๏ธ Basic RAG Chain](rag_tutorials/rag_chain/)
-* [๐Ÿ“  RAG with Database Routing](rag_tutorials/rag_database_routing/)
-* [๐Ÿ–ผ๏ธ Vision RAG](rag_tutorials/vision_rag/)
-* [๐Ÿฉบ RAG Failure Diagnostics Clinic](rag_tutorials/rag_failure_diagnostics_clinic/)
-* [๐Ÿ•ธ๏ธ Knowledge Graph RAG with Citations](rag_tutorials/knowledge_graph_rag_citations/)
+* [๐Ÿ”ฅ Agentic RAG with Embedding Gemma](rag_tutorials/agentic_rag_embedding_gemma) - Fully local agentic RAG with EmbeddingGemma and Llama 3.2
+* [๐Ÿง Agentic RAG with Reasoning](rag_tutorials/agentic_rag_with_reasoning/) - Watch the agent's step-by-step reasoning as it retrieves
+* [๐Ÿ“ฐ AI Blog Search (RAG)](rag_tutorials/ai_blog_search/) - Agentic search over blog content, built on LangGraph
+* [๐Ÿ” Autonomous RAG](rag_tutorials/autonomous_rag/) - GPT-4o answers from your PDFs, falls back to web search
+* [๐Ÿ”„ Contextual AI RAG Agent](rag_tutorials/contextualai_rag_agent/) - Managed RAG: datastore to grounded chat in minutes
+* [๐Ÿ”„ Corrective RAG (CRAG)](rag_tutorials/corrective_rag/) - Retrieval that grades itself and retries before answering
+* [๐Ÿ‹ Deepseek Local RAG Agent](rag_tutorials/deepseek_local_rag_agent/) - Local DeepSeek reasoning over your own documents
+* [๐Ÿค” Gemini Agentic RAG](rag_tutorials/gemini_agentic_rag/) - Query rewriting and web fallback with Gemini Flash Thinking
+* [๐Ÿ‘€ Hybrid Search RAG (Cloud)](rag_tutorials/hybrid_search_rag/) - Keyword plus vector search feeding Claude
+* [๐Ÿ”„ Llama 3.1 Local RAG](rag_tutorials/llama3.1_local_rag/) - Chat with any webpage, fully offline
+* [๐Ÿ–ฅ๏ธ Local Hybrid Search RAG](rag_tutorials/local_hybrid_search_rag/) - Hybrid search with everything running on your machine
+* [๐Ÿงฌ Multimodal Agentic RAG](rag_tutorials/multimodal_agentic_rag/) - Text, PDFs, images, audio, and video, answered with citations
+* [๐Ÿฆ™ Local RAG Agent](rag_tutorials/local_rag_agent/) - Llama 3.2 and Qdrant, no API keys required
+* [๐Ÿงฉ RAG-as-a-Service](rag_tutorials/rag-as-a-service/) - A production RAG service in under 50 lines
+* [โœจ RAG Agent with Cohere](rag_tutorials/rag_agent_cohere/) - Command R7B retrieval with web-search fallback
+* [โ›“๏ธ Basic RAG Chain](rag_tutorials/rag_chain/) - The minimal retrieval pipeline, applied to pharma research
+* [๐Ÿ“  RAG with Database Routing](rag_tutorials/rag_database_routing/) - Routes each question to the right database automatically
+* [๐Ÿ–ผ๏ธ Vision RAG](rag_tutorials/vision_rag/) - Ask questions about images and PDF pages with Embed-4
+* [๐Ÿฉบ RAG Failure Diagnostics Clinic](rag_tutorials/rag_failure_diagnostics_clinic/) - Find out why your RAG pipeline is wrong, systematically
+* [๐Ÿ•ธ๏ธ Knowledge Graph RAG with Citations](rag_tutorials/knowledge_graph_rag_citations/) - Multi-hop answers with verifiable source attribution
### ๐Ÿ’พ LLM Apps with Memory
*Agents and chatbots that remember conversations and user state across sessions.*
-* [๐Ÿ’พ AI ArXiv Agent with Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/ai_arxiv_agent_memory/)
-* [๐Ÿ›ฉ๏ธ AI Travel Agent with Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/ai_travel_agent_memory/)
-* [๐Ÿ’ฌ Llama3 Stateful Chat](advanced_llm_apps/llm_apps_with_memory_tutorials/llama3_stateful_chat/)
-* [๐Ÿ“ LLM App with Personalized Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/llm_app_personalized_memory/)
-* [๐Ÿ—„๏ธ Local ChatGPT Clone with Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/local_chatgpt_with_memory/)
-* [๐Ÿง  Multi-LLM Application with Shared Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/multi_llm_memory/)
+* [๐Ÿ’พ AI ArXiv Agent with Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/ai_arxiv_agent_memory/) - Paper search that remembers your research interests
+* [๐Ÿ›ฉ๏ธ AI Travel Agent with Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/ai_travel_agent_memory/) - A travel assistant that remembers your preferences
+* [๐Ÿ’ฌ Llama3 Stateful Chat](advanced_llm_apps/llm_apps_with_memory_tutorials/llama3_stateful_chat/) - Session-persistent chat with Llama 3
+* [๐Ÿ“ LLM App with Personalized Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/llm_app_personalized_memory/) - A chatbot that keeps context across conversations
+* [๐Ÿ—„๏ธ Local ChatGPT Clone with Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/local_chatgpt_with_memory/) - Fully local, with a personal memory per user
+* [๐Ÿง  Multi-LLM Application with Shared Memory](advanced_llm_apps/llm_apps_with_memory_tutorials/multi_llm_memory/) - Different models, one shared conversation memory
### ๐Ÿ’ฌ Chat with X
*Turn any data source into a chat interface.*
-* [๐Ÿ’ฌ Chat with GitHub (GPT & Llama3)](advanced_llm_apps/chat_with_X_tutorials/chat_with_github/)
-* [๐Ÿ“จ Chat with Gmail](advanced_llm_apps/chat_with_X_tutorials/chat_with_gmail/)
-* [๐Ÿ“„ Chat with PDF (GPT & Llama3)](advanced_llm_apps/chat_with_X_tutorials/chat_with_pdf/)
-* [๐Ÿ“š Chat with Research Papers (ArXiv) (GPT & Llama3)](advanced_llm_apps/chat_with_X_tutorials/chat_with_research_papers/)
-* [๐Ÿ“ Chat with Substack](advanced_llm_apps/chat_with_X_tutorials/chat_with_substack/)
-* [๐Ÿ“ฝ๏ธ Chat with YouTube Videos](advanced_llm_apps/chat_with_X_tutorials/chat_with_youtube_videos/)
+* [๐Ÿ’ฌ Chat with GitHub (GPT & Llama3)](advanced_llm_apps/chat_with_X_tutorials/chat_with_github/) - Any repo, answered in 30 lines of RAG
+* [๐Ÿ“จ Chat with Gmail](advanced_llm_apps/chat_with_X_tutorials/chat_with_gmail/) - Ask your inbox questions
+* [๐Ÿ“„ Chat with PDF (GPT & Llama3)](advanced_llm_apps/chat_with_X_tutorials/chat_with_pdf/) - The classic, in 30 lines of Python
+* [๐Ÿ“š Chat with Research Papers (ArXiv) (GPT & Llama3)](advanced_llm_apps/chat_with_X_tutorials/chat_with_research_papers/) - Explore arXiv conversationally with GPT-4o
+* [๐Ÿ“ Chat with Substack](advanced_llm_apps/chat_with_X_tutorials/chat_with_substack/) - Chat with any newsletter's archive
+* [๐Ÿ“ฝ๏ธ Chat with YouTube Videos](advanced_llm_apps/chat_with_X_tutorials/chat_with_youtube_videos/) - Ask videos questions via their transcripts
### ๐ŸŽฏ LLM Optimization Tools
@@ -253,8 +253,8 @@ streamlit run travel_agent.py
*End-to-end fine-tuning recipes for open-source models.*
-* [Gemma 3 Fine-tuning](advanced_llm_apps/llm_finetuning_tutorials/gemma3_finetuning/)
-* [Llama 3.2 Fine-tuning](advanced_llm_apps/llm_finetuning_tutorials/llama3.2_finetuning/)
+* [๐Ÿฆฅ Gemma 3 Fine-tuning](advanced_llm_apps/llm_finetuning_tutorials/gemma3_finetuning/) - 4-bit LoRA with Unsloth, small and readable
+* [๐Ÿฆ™ Llama 3.2 Fine-tuning](advanced_llm_apps/llm_finetuning_tutorials/llama3.2_finetuning/) - Fine-tune in 30 lines, free on Colab
### ๐Ÿง‘โ€๐Ÿซ AI Agent Framework Crash Courses