Python framework for building autonomous AI agents that research, plan, code and run tasks, with memory, RAG and 100+ LLM providers.
Shubhamsaboo/awesome-llm-apps
A large collection of open-source AI agents, agent skills, and RAG apps built on Claude, Gemini, GPT, DeepSeek, Llama, and Qwen models.
- Stars
- 142,363
- Forks
- 20,935
- Open issues
- 15
- Last commit
- 2 days ago
What is it?
Awesome LLM Apps is a collection of runnable AI projects covering single-agent apps, multi-agent teams, voice agents, MCP-connected agents, retrieval-augmented generation (RAG) pipelines, memory-enabled chatbots, and LLM fine-tuning recipes. Each template lives in its own folder with its own requirements, so you can clone the repository and run one example without setting up the rest.
The projects target a range of model providers, including Claude, Gemini, GPT, DeepSeek, Llama, and Qwen, and several use local models so they can run without API keys. Many templates are built on frameworks such as Streamlit, OpenAI Agents SDK, Google ADK, CrewAI, and LangGraph. The repository is licensed under Apache-2.0.
Beyond the code samples, the collection includes agent skills that install into coding agents such as Claude Code, Codex, and Cursor with a single command, and crash-course tutorials for major agent frameworks.
Key features
- 01Covers single-agent apps, multi-agent teams, voice agents, and MCP agents.
- 02Includes over 30 RAG templates, from basic chains to agentic and knowledge-graph variants.
- 03Supports cloud models such as GPT, Claude, and Gemini, plus local models like Llama and DeepSeek.
- 04Each template is self-contained with its own requirements and run instructions.
- 05Provides installable agent skills for coding agents such as Claude Code and Cursor.
Use cases
- Learning how to build a RAG pipeline or a tool-using agent by reading a small, working example.
- Finding a starting template for a chatbot that chats with PDFs, GitHub repos, or YouTube transcripts.
- Exploring how multi-agent teams divide work across roles such as researcher, analyst, and writer.
- Testing agent frameworks like Google ADK, OpenAI Agents SDK, or CrewAI with real project code.
Quick start
- 1
Install a agent skill with npx
npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/project-graveyard - 2
Clone the repository
git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git - 3
Enter the AI travel agent folder
cd awesome-llm-apps/starter_ai_agents/ai_travel_agent - 4
Install requirements and start the app
pip install -r requirements.txt
Things to know
- Each app has its own setup and needs its own API keys, so there is no single one-step run.
Topics
FAQ
- What is awesome-llm-apps?
- A large collection of open-source AI agents, agent skills, and RAG apps built on Claude, Gemini, GPT, DeepSeek, Llama, and Qwen models. Awesome LLM Apps is a collection of runnable AI projects covering single-agent apps, multi-agent teams, voice agents, MCP-connected agents, retrieval-augmented generation (RAG) pipelines, memory-enabled chatbots, and LLM fine-tuning recipes. Each template lives in its own folder with its own requirements, so you can clone the repository and run one example without setting up the rest.
- Is awesome-llm-apps free to use? What license does it have?
- awesome-llm-apps is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
- Is awesome-llm-apps still maintained?
- Actively maintained. The last commit to awesome-llm-apps was on Oct 18, 2026.
- What can I use awesome-llm-apps for?
- Learning how to build a RAG pipeline or a tool-using agent by reading a small, working example. Finding a starting template for a chatbot that chats with PDFs, GitHub repos, or YouTube transcripts. Exploring how multi-agent teams divide work across roles such as researcher, analyst, and writer. Testing agent frameworks like Google ADK, OpenAI Agents SDK, or CrewAI with real project code.
- How do I install awesome-llm-apps?
- Install a agent skill with npx: npx skills add https://github.com/Shubhamsaboo/awesome-llm-apps/tree/main/agent_skills/project-graveyard Clone the repository: git clone https://github.com/Shubhamsaboo/awesome-llm-apps.git Enter the AI travel agent folder: cd awesome-llm-apps/starter_ai_agents/ai_travel_agent Install requirements and start the app: pip install -r requirements.txt
- Where can I get awesome-llm-apps?
- The source code and installation instructions are on GitHub: https://github.com/Shubhamsaboo/awesome-llm-apps
Summary generated by AI from the project's README. GitHub stats refresh daily.
Related projects
A collection of 50+ runnable Jupyter notebook tutorials covering GenAI agent techniques, from simple chatbots to multi-agent systems.
A visual platform for building, testing and deploying AI agents and workflows, with built-in API and MCP server exposure.
Open-source Python framework for orchestrating role-based autonomous AI agents (Crews) and event-driven workflows (Flows).
Agent memory system that stores, recalls and reflects on memories so AI agents learn over time instead of only replaying chat history.
A minimal Python library for building AI agents that write and run their actions as Python code.