Shubhamsaboo/awesome-llm-apps
A free collection of 100+ ready-to-run AI agent and RAG app examples
Shubhamsaboo/awesome-llm-apps is a repository packed with over 100 open-source example projects covering AI agents and retrieval-augmented answering systems (RAG), spanning travel planning, financial analysis, medical imaging review, and game-playing agents. The examples are built to work with Claude, Gemini, GPT, DeepSeek, Llama, Qwen, and other models, and everything is released under the Apache-2.0 license, meaning anyone can clone, modify, or even sell the code. Written in Python, the projects range from single-file starter agents that need only an API key to run, up to multi-agent teams handling complex, production-style tasks.
What it does
- Organized by difficulty: starter agents runnable with just an API key, advanced agents with tools and memory, and multi-agent teams for complex workflows
- Covers real-world scenarios like travel itinerary planning, breakup recovery support, CSV data analysis, X-ray image review, fraud investigation, and personal financial coaching
- Includes multi-agent team setups (legal advisory, recruitment, real estate) and agents connected to external tools and data via the Model Context Protocol (MCP)
- Contains over 20 RAG pipeline examples that retrieve from documents, images, or audio to generate grounded answers, plus memory-based chatbots that retain conversation context and tools that cut token costs by 30-90%
- Also includes installable 'Agent Skills' that add new capabilities to coding agents like Claude Code, Codex, or Cursor in about 10 seconds
Why it matters
It lets developers skip building AI agents or RAG systems from scratch and instead study or directly reuse working code, cutting down both learning time and development cost. Comparing multiple frameworks and models side by side in one place also helps both practitioners and learners pick the right architecture for their own project.
Terms in this repo
- RAG (Retrieval Augmented Generation) · A method that retrieves relevant documents or data before generating an answer, grounding the response in that retrieved content
- Agent Skills · Installable packages of executable code that add new capabilities to a coding agent with a single command
- Model Context Protocol (MCP) · A standardized protocol that lets AI agents connect to external tools and data sources
- LoRA · A fine-tuning technique that trains only a small subset of a model's parameters on limited data, reducing tuning cost
- Apache-2.0 license · An open-source license that permits commercial use, modification, and redistribution as long as attribution is kept
Repository description (English)
100+ AI Agents, Agent Skills and RAG Apps - Free and Open Source.
Open on GitHubTrending repos
- DietrichGebert/ponytailA ruleset that teaches AI coding agents to say no to writing code
- liustack/modlensA plugin that lets text-only AI models like DeepSeek 'see' pasted images by turning them into structured text data
- marin-community/marinMarin is an open-source platform that publishes the entire process of building large language models, not just the final model
- TauricResearch/TradingAgentsA framework where multiple LLM agents split into analyst, researcher, trader and risk-management roles, debate, and decide stock trades
- asciimoo/histerA personal search engine that indexes the full text of every page and file you've seen
- anthropics/claude-plugins-officialAnthropic's official catalog for add-ons that plug new abilities into Claude Code
- vorssaint/vorssaint-utilsOne free menu bar app replaces a dozen paid Mac utilities
- MadsLorentzen/ai-job-searchAn open-source framework that runs your entire job search through Claude Code, built by someone who actually got hired using it
Latest from METAL LAB
- Anthropic funds $5M research program for AI wellbeing evaluations
- Keenable Raises $26M Seed to Build Web Search for AI Agents
- Gamma acquires Accel-backed design startup Lica
- Oura's rumored September IPO is being priced on AI, not the ring
- Alabama Launches Investigation into OpenAI Agent Breakout Incident