Langroid

•
4.2k
•

Enables building LLM-powered applications through a multi-agent programming paradigm.

Langroid is an intuitive, lightweight, extensible, and principled Python framework for easily building LLM-powered applications, developed by CMU and UW-Madison researchers. It allows users to set up Agents, equip them with optional components such as LLMs, vector-stores, and tools/functions, assign them tasks, and have them collaboratively solve problems by exchanging messages. This Multi-Agent paradigm simplifies the developer experience by offering a fresh approach to LLM app-development, designed to work seamlessly with practically any LLM without relying on other major LLM frameworks.

Características Principales

01Facilitates multi-agent collaboration with message exchange.
02Offers robust RAG capabilities with DocChatAgent and various document parsers.
03Supports a wide range of LLMs, including local and remote models.
04Intuitive and extensible multi-agent framework for LLM applications.
05Includes support for function calling, structured information extraction, and tool integration.
063,392 GitHub stars

Casos de Uso

01Developing secure software applications using AI agents for vulnerability management.
02Extracting structured information from documents using local or remote LLMs.
03Building multi-agent RAG systems for specialized domains like pharmacovigilance.