LLMRepos is a searchable directory of open-source AI and large language model repositories. It tracks repository metadata over time so builders can compare project popularity, recent growth, and maintenance signals.

How are projects ranked?

Directory pages rank projects by current GitHub stars. Repository detail pages show star history, recent growth, maintenance activity, and comparisons with a relevant category or subcategory. Rankings describe measurable repository signals, not an independent quality or safety audit.

What is an agent skill?

An agent skill is a reusable package of instructions, resources, or code that extends an AI agent's ability to perform a task. LLMRepos lists repositories identified as publishing, authoring, packaging, installing, managing, or reviewing agent skills.

The Model Context Protocol (MCP) is a protocol for connecting AI applications to external tools and data sources. LLMRepos lists related servers, SDKs, and developer tools in its MCP directory.

How current is the repository data?

LLMRepos refreshes its repository snapshot daily. A displayed date marks the latest available snapshot; individual metrics and GitHub metadata may change between refreshes.

Does a high ranking mean a project is recommended or secure?

No. Rankings summarize public activity signals such as stars, growth, and maintenance. They do not verify code quality, security, model performance, licensing compliance, or suitability for a particular use.

A guide to LLMRepos

LLMRepos is a directory for discovering and comparing open-source AI projects. Browse the full repository index, explore categories, or go directly to agent skills and MCP projects.

What the directory covers

The index groups public GitHub repositories for AI agents and applications, agent skills, MCP tools, retrieval-augmented generation, local model applications, inference and serving, training and research, model collections, evaluations, and learning resources. Category and tag pages provide direct, server-rendered lists that can be read without running browser JavaScript.

How to interpret the data

LLMRepos tracks GitHub stars, forks, contributors, repository metadata, and daily star snapshots. Rankings use stars; growth and maintenance signals add context. These are observable indicators, not endorsements or a substitute for checking a repository source, licence, security, and release history. The latest snapshot date appears on directory and project pages.

AI project glossary

Agent: A software system that uses a model to interpret a goal and take steps, often by calling tools.
Agent skill: Reusable instructions or resources that give an AI agent a repeatable capability.
Evaluation (eval): A test or measurement used to compare a model or AI system against tasks or criteria.
Inference: The process of running a trained model to produce outputs from inputs.
Large language model (LLM): A model trained on text or other data to understand and generate language.
MCP: Model Context Protocol, a standard for connecting AI applications with tools and data.
RAG: Retrieval-augmented generation: retrieving relevant external information to ground a model's response.
Repository: A version-controlled project, commonly hosted on GitHub, containing code, documentation, and project history.
Stars: A GitHub bookmarking signal. Stars indicate interest, not verified quality or active use.

Frequently asked questions

What is LLMRepos?: LLMRepos is a searchable directory of open-source AI and large language model repositories. It tracks repository metadata over time so builders can compare project popularity, recent growth, and maintenance signals.
How are projects ranked?: Directory pages rank projects by current GitHub stars. Repository detail pages show star history, recent growth, maintenance activity, and comparisons with a relevant category or subcategory. Rankings describe measurable repository signals, not an independent quality or safety audit.
What is an agent skill?: An agent skill is a reusable package of instructions, resources, or code that extends an AI agent's ability to perform a task. LLMRepos lists repositories identified as publishing, authoring, packaging, installing, managing, or reviewing agent skills.
What is MCP?: The Model Context Protocol (MCP) is a protocol for connecting AI applications to external tools and data sources. LLMRepos lists related servers, SDKs, and developer tools in its MCP directory.
How current is the repository data?: LLMRepos refreshes its repository snapshot daily. A displayed date marks the latest available snapshot; individual metrics and GitHub metadata may change between refreshes.
Does a high ranking mean a project is recommended or secure?: No. Rankings summarize public activity signals such as stars, growth, and maintenance. They do not verify code quality, security, model performance, licensing compliance, or suitability for a particular use.