Awesome GitHub RepositoriesChat Model Interfaces

LangChain is an orchestration framework designed for building, managing, and deploying applications powered by large language models. It provides a unified integration layer that normalizes disparate model provider APIs into a consistent set of primitives, enabling developers to build complex, multi-step AI workflows that manage state, memory, and tool execution. The project distinguishes itself through a durable execution runtime that maintains persistent state across long-running processes by checkpointing progress to external storage. It models agent workflows as directed graphs, allowing

Ktransformers is a comprehensive framework designed for the operation, fine-tuning, and serving of large language models. It functions as a heterogeneous inference engine and quantized execution runtime, enabling the deployment of massive models by distributing computational workloads across both CPU and GPU resources. This architecture allows users to bypass local memory constraints, making it possible to run and train models that exceed the capacity of a single device. The project distinguishes itself through specialized support for sparse architectures, particularly mixture-of-experts mode

Mistral Inference is a library for running Mistral large language models on a GPU, generating text from prompts with token streaming. It loads pretrained model weights from local disk or a remote registry into GPU memory, then produces output tokens one by one for real-time display in interactive applications. The library supports multimodal prompts that accept image URLs alongside text, enabling visual description and reasoning. It includes content safety guardrails that scan generated text against predefined policies to block or flag policy violations. For structured interactions, it provid

MiniCPM is a collection of small language models designed for local, on-device deployment in resource-constrained environments. The project focuses on running dense Transformer models on consumer hardware, including GPUs, CPUs, and Apple Silicon, without requiring custom code forks. The project distinguishes itself through heavy optimization for edge hardware, utilizing quantized weight compression in GGUF and MLX formats to reduce memory overhead. It implements advanced inference techniques such as speculative sampling and radix-tree prefix caching to accelerate generation speed and throughp

CopilotForXcode is an AI-powered coding assistant integrated directly into Xcode as a source editor extension. It functions as an agent that can automate multi-step project tasks, such as editing files, running terminal commands, and searching across the entire codebase, all while understanding the full context of the current Xcode project. The assistant provides a context-aware chat interface that answers coding questions based on open files, symbols, and recent edits. It also offers diff-based code review, analyzing changes to provide feedback on code quality and potential issues before mer

CodeCompanion is a Neovim plugin that brings large language model capabilities directly into the editor, enabling turn-based conversations with AI models in a dedicated chat buffer. It provides a comprehensive interface for interacting with LLMs, supporting multiple providers through a flexible adapter system that can route requests to various hosted or local language model services. The plugin distinguishes itself through its extensive context-sharing capabilities, allowing users to send buffer contents, visual selections, git diffs, LSP diagnostics, terminal output, quickfix lists, and view

freegpt-webui es una interfaz web autohospedada para interactuar con modelos de lenguaje grandes. Proporciona un frontend basado en chat diseñado para comunicarse con modelos GPT 3.5 y GPT 4. La aplicación permite el chat sin clave de API, permitiendo a los usuarios acceder a IA conversacional para la generación de texto y recuperación de información sin proporcionar o gestionar claves de autenticación personales. El sistema maneja la integración del modelo a través de un gateway de proxy inverso y admite procesamiento de stream asíncrono para la generación de texto en tiempo real. Las preferencias del usuario y el historial de conversaciones se persisten mediante almacenamiento de sesión del lado del cliente.

AIOS is an LLM agent operating system and orchestration kernel designed to manage memory, resource scheduling, and tool execution for multiple autonomous AI agents. It serves as a comprehensive framework for developing and deploying agents, featuring a dedicated resource manager that coordinates model backends, GPU memory, and isolated kernel instances. The system distinguishes itself through a semantic memory engine that uses vector search and autonomous clustering for long-term knowledge management, and a semantic file system that allows users to control computer files and system operations

AICommand es un controlador de editor y herramienta de automatización impulsado por LLM diseñado para el Unity Editor. Integra modelos de lenguaje de gran tamaño para traducir prompts en lenguaje natural a comandos ejecutables, permitiendo a los usuarios manipular la configuración del entorno de desarrollo y los objetos mediante instrucciones basadas en texto. El sistema emplea un pipeline de texto a acción que utiliza mapeo de comandos basado en LLM y descubrimiento de API basado en reflexión para resolver la entrada en lenguaje natural en funciones específicas del editor. Este proceso permite la ejecución de funciones del editor de Unity resolviendo identificadores de cadena a manejadores de código en tiempo de ejecución. La herramienta proporciona una interfaz de chat integrada dentro del entorno de desarrollo para capturar los prompts del usuario. Se centra en automatizar tareas repetitivas de configuración y optimizar los flujos de trabajo del motor de juego reemplazando la navegación manual por menús con control en lenguaje natural.

ChatGPT.nvim es un plugin de Neovim para LLMs de OpenAI que sirve como asistente de código impulsado por IA para refactorizar, completar y corregir fragmentos de código. Funciona como una herramienta de automatización de prompts personalizados y un renderizador de markdown, permitiendo a los usuarios interactuar con modelos de lenguaje directamente dentro del editor. El proyecto se distingue por un framework para definir personas de IA reutilizables y tareas automatizadas de procesamiento de texto mediante prompts del sistema y plantillas. Incluye un sistema de renderizado especializado que transforma las respuestas en markdown estilizado con bloques de código plegables. El plugin cubre interfaces de chat interactivas, prompts conscientes del contexto para archivos de proyecto y acciones de código automatizadas para corrección gramatical y de errores. También implementa una gestión segura de credenciales obteniendo claves de API mediante comandos externos en lugar de almacenamiento estático.

Claudian is a framework that combines AI coding agents, knowledge base integration, and a multi-provider orchestrator for managed interactions with large language models. It functions as a browser extension that connects users to AI services through a sidebar and inline editing interface, providing a system for integrating agents into local directories to perform file operations, bash commands, and workspace searches. The project distinguishes itself with a multi-provider orchestrator that allows switching between different AI backends while maintaining separate conversation states and config