This repository is a curated list of resources for Large Language Models (LLMs), targeting developers, researchers, and enthusiasts. It aims to provide a comprehensive overview of tools, frameworks, models, and research papers related to LLM development, deployment, and application, serving as a central hub for staying updated in the rapidly evolving LLM landscape.

How It Works

The repository organizes LLM-related resources into categorized tables, covering areas such as serverless hosting, local inference, LLM serving frameworks, UI builders, fine-tuning, agentic workflows, and research papers. Each entry typically includes the tool/framework name, organization, a brief description, open-source status, and a GitHub link, facilitating quick discovery and evaluation of relevant projects.

Quick Start & Requirements

This is a curated list, not a runnable project. No installation or specific requirements are needed to browse the resources. Links to official documentation, demos, and GitHub repositories are provided for each listed item.

Highlighted Details

• Extensive coverage of LLM hosting platforms, including serverless options like Beam.Cloud, Modal, and Replicate, alongside GPU rental services.
• Detailed sections on agentic frameworks (LangChain, LlamaIndex, CrewAI, Autogen) and their core capabilities (memory, multimodality, multi-agent support).
• A comprehensive list of LLM application frameworks, RAG frameworks, and AI tools for both using and building AI applications.
• Includes a significant collection of research papers on Chain-of-Thought (CoT) prompting and their implementations.

Maintenance & Community

The list is marked as "work in progress" and was last updated on April 14th, 2025. Specific contributor or community links are not provided within the README.

Licensing & Compatibility

This repository is a collection of links and information; it does not have its own license. The licensing of individual tools and models listed varies, with many being open-source (MIT, Apache 2.0, AGPL-3.0) but some having non-commercial restrictions (e.g., XTTS-v2).

Limitations & Caveats

As a curated list, the depth of information for each resource is limited to what can be presented in a table format. The "work in progress" status indicates that the list may be incomplete or subject to change.