Verified project record

Shubhamsaboo/awesome-llm-apps

This project is an open-source repository of over 100 tested AI agent and RAG application examples across various domains. It provides developers and AI engineers with categorized starter templates and tutorials that can be cloned and run locally using standard Python or Node environments.

Project overview

It offers a large, hand-built catalog of production-style agent teams, voice agents, and RAG pipelines that pass security and evaluation CI gates, providing a broad reference library for building AI applications.

Project type: MCP · AI Agent · RAG
Use cases: Knowledge Q&A · Coding & Development · Automation
Deployment: Refer to project documentation
License: Apache-2.0

Best for

Developers and AI engineers seeking tested, open-source starter templates and tutorials for building AI agents and RAG pipelines.
Users looking to study categorized examples of generative UI agents, voice agents, or multi-agent teams.

Key capabilities

Ships a collection of installable coding agent skills containing real code that passes security and evaluation CI gates.
Ships a collection of single-file AI agents that run with just an API key.
Ships a collection of production-style agent teams equipped with tools, memory, and multi-step reasoning for complex tasks.
Ships a collection of speech-in, speech-out voice agents using real-time voice APIs.
Ships a collection of agents that render interactive UI components such as forms, cards, and editable plans.
Ships a collection of agents that play games end-to-end, encompassing reasoning, strategy, and action.
Ships a collection of agents that connect to external tools and data via the Model Context Protocol.
Ships a collection of Retrieval Augmented Generation pipelines, ranging from simple chains to agentic and multi-source setups.

Limitations and risks

Many templates require external API keys to function and do not ship with a fully self-contained runtime, meaning inference may depend on remote, paid services depending on the template selected.

Getting started

Setup is documented as taking roughly 30 seconds by cloning the repository, navigating to a specific template folder such as the starter travel agent, installing requirements using pip, and running the application via streamlit run.

Alternatives and comparisons

A framework for developing LLM applications based on instruction following, tool usage, planning, and memory, featuring function calling and RAG.
A unified multi-agent application development framework featuring Meta-Agent orchestration, hierarchical memory, and MCP Hub.
An execution layer providing coordinated agent swarms, self-learning memory, and security guardrails around coding agents.

Project comparisons

Evidence and sources

GitHub project description: 100+ AI Agent & RAG apps you can actually run — clone, customize, ship.
README: 100+ open-source AI agents, agent skills, and RAG apps. Hand-built, tested end-to-end, Apache-2.0.
README: Give your coding agent new abilities. One command to install, plain English to use. Every skill ships real code and passes a security + eval CI gate. Works with Claude Code, Codex…
README: Single-file agents that run with just an API key - a great place to start.
README: Production-style agents with tools, memory, and multi-step reasoning.

Reviewed at: 2026-07-16T12:05:49Z

Open original GitHub project