Awesome GitHub RepositoriesCodebase Knowledge Sources

QAnything is a retrieval-augmented generation application framework and self-hosted AI interface. It functions as a system that combines a vector database knowledge base, a document parsing service, and a hybrid search engine to generate answers based on private user data. The project features a modular pipeline architecture that allows users to independently replace components such as parsers, embedding models, and reranking engines. It supports local-first model deployment and offline operation to ensure data privacy, and includes a two-stage retrieval pipeline that merges dense vector embe

OpenChat is a conversational AI agent builder and customer service automation platform that uses large language models to power customer support chatbots across multiple channels. It provides tools for defining AI agent behavior, training on custom knowledge, managing actions, and controlling autopilot responses per channel. The platform enables deploying AI agents on web, phone, email, SMS, and WhatsApp, with a unified inbox for managing conversations across all channels. It includes CRM synchronization, automated workflows, contact segmentation, and analytics for tracking customer satisfact

Casibase is an open-source platform that orchestrates multi-turn conversations with large language models and manages retrieval-augmented knowledge bases from a single interface. It provides a unified system for connecting to over 30 AI model providers, ingesting documents into vector embeddings for semantic search, and running autonomous agent loops that can drive a browser, search the web, execute commands, and integrate with external tools. The platform distinguishes itself by combining AI conversation management with infrastructure and application orchestration capabilities. It includes a

GLM-4.5 is a multimodal large language model and advanced reasoning system. It functions as an AI coding assistant, an autonomous AI agent, and a multimodal content generator capable of processing and generating text, images, audio, and video within a single unified system. The project is distinguished by its deep reasoning capabilities, utilizing chain-of-thought processing to solve complex mathematical, logical, and technical problems. It features an agentic architecture that allows for autonomous task execution, long-horizon goal planning, and the ability to interact with external tools an

scrape-it is a Node.js web scraper and HTML parser designed to extract structured data from websites and HTML files. It functions as a web data extraction tool that retrieves specific information from DOM elements and converts web content into usable data fields. The tool uses CSS selectors to target specific data points and employs schema-driven data mapping to organize unstructured web text into a consistent format. It supports custom value transformation to convert raw extracted strings into specific data formats. The system provides capabilities for web data extraction and automated cont

s2client-proto provides a set of structured data definitions and language-neutral communication protocols used to exchange information between an external client and the StarCraft II engine. It utilizes protocol buffer definitions to establish a binary serialization schema for these data exchanges. The project defines the underlying communication layer necessary for game engine automation, game state analysis, and the development of software agents for competitive gaming. The framework covers interface definition languages to ensure compatibility across programming languages and employs sche

This project is an AI-powered development tool and IDE extension designed for codebase searching, automated code refactoring, and prompt context management. It functions as an LLM-driven code editor that enables users to rewrite code, scan projects, and track task completion using large language models. The system features a prompt context manager that automatically attaches relevant files and rule sets to requests to improve accuracy. It includes a codebase search tool that uses natural language prompts to locate specific logic and provide explanatory notes across a project. The tool covers

Adrenaline is an AI-powered codebase analysis tool and knowledge base designed for analyzing local software projects. It functions as a technical assistant that enables users to chat with their code, retrieve specific logic, and visualize system architectures using large language models. The project distinguishes itself by converting codebase analysis into visual system architectures and technical workflow diagrams. It utilizes retrieval augmented generation to ground responses in project-specific code snippets and documentation, while integrating real-time web search to supplement local know

Entity-Relation-Extraction es un framework de machine learning diseñado para identificar entidades y sus conexiones lógicas dentro de texto no estructurado. Funciona como una tubería (pipeline) que transforma documentos crudos en grafos de conocimiento estructurados utilizando modelos de deep learning y arquitecturas transformer. El proyecto se distingue por un enfoque basado en esquemas, que mapea la información extraída a plantillas relacionales predefinidas para asegurar la consistencia de la salida. Emplea un proceso de varias etapas que combina la clasificación de tokens de etiquetado de secuencias con codificación contextual para delinear los límites de las entidades y clasificar las relaciones entre ellas. El kit de herramientas proporciona componentes para ajustar (fine-tuning) modelos de lenguaje preentrenados y orquestar datos a través de grafos computacionales. Incluye utilidades para evaluar el rendimiento del modelo frente a conjuntos de datos de referencia (ground truth) para verificar la precisión del proceso de extracción.