Awesome GitHub RepositoriesAI Chatbots

NeoPass is a specialized toolset designed to circumvent proctored exam environments. It functions as an AI-powered exam assistant and automated solver that helps users find answers to multiple-choice and coding questions during monitored tests. The project distinguishes itself through a browser-based bypass system that neutralizes portal restrictions. It disables tab-switching detection, overrides clipboard restrictions to enable copying and pasting, and employs a human-like typing simulator to input code letter by letter to avoid detection by automated monitoring systems. The software provi

This project is a comprehensive framework for building AI-powered applications, providing a unified toolkit for orchestrating language models, autonomous agents, and interactive user interfaces. It serves as a central library for managing the entire lifecycle of AI interactions, from initial prompt generation and model provider abstraction to complex, multi-step reasoning and tool execution. The framework distinguishes itself through its deep integration with frontend development, specifically by enabling generative user interfaces that render dynamic components directly from model outputs. I

This is a full-featured chatbot framework and Next.js web application designed for integrating various large language model providers into a web interface. It serves as a template for building AI chatbots that can generate text and structured data through a unified interface. The project functions as an authenticated AI application, incorporating built-in user identity verification and session management. It includes a suite for AI tool integration, allowing language models to execute tool calls and generate structured objects by connecting to external data and functions. The framework provi

This project is a messaging bot bridge and multi-model AI gateway that connects large language models to platforms such as QQ, Telegram, and WeChat. It functions as an AI agent workflow engine, enabling the automation of private and group chat interactions across multiple social communication channels. The system features a multimodal chat interface capable of processing and sending text, voice, and AI-generated images. It includes a web-based management dashboard for administering AI model configurations, monitoring activity, and designing custom bot personalities and persona presets to cont

This project is a framework for building custom AI chatbots capable of PDF document analysis. It implements Retrieval Augmented Generation to connect a large language model to private document data. The system utilizes graph-based agent orchestration to control conversation flow and decision logic. It maintains context across interactions through thread-based state management and delivers AI responses to the user interface via real-time streaming. The project covers PDF document ingestion through chunk-based processing and vector-store retrieval. It includes mechanisms for query-based data r

llm-universe is a structured learning resource and technical guide focused on the development of large language model applications. It serves as a curriculum for mastering model orchestration, the creation of autonomous conversational agents, and the implementation of retrieval-augmented generation systems. The project provides detailed instructions on connecting model APIs with memory and tools to create execution chains. It specifically covers the construction of retrieval pipelines, including the process of cleaning raw documents, generating embeddings, and integrating vector databases to

Shell GPT is an AI-powered command-line interface that generates shell commands and source code from natural language prompts. It serves as a terminal-based tool for automating technical tasks, producing executable commands, and generating code snippets directly within the shell. The tool distinguishes itself through a read-eval-print loop for interactive chatting and the ability to maintain stateful conversational history via named sessions. It supports flexible backend routing, allowing users to connect to cloud-based APIs or local language model hosts for offline operation and data privacy

ChatHub is a browser-based AI workspace and chatbot aggregator that provides a unified interface for interacting with multiple large language models. It functions as a multi-model AI client, allowing users to send a single prompt to several chatbots simultaneously and compare their responses side-by-side. The project distinguishes itself by acting as a cross-model response comparator that aggregates various web-based AI interfaces into a single view. It includes an AI prompt manager for storing and organizing reusable prompts to be used across different model sessions. The system covers a br

PandaWiki is an AI-powered wiki and knowledge base platform that integrates large language models to automate content creation and information retrieval. It functions as a retrieval-augmented generation system for building technical wikis, FAQs, and documentation sites that provide automated answers grounded in a private knowledge base. The system acts as an enterprise knowledge bot, allowing the deployment of AI chatbots via web widgets and messaging applications like Discord. It further extends its operational capabilities by integrating with Model Context Protocol servers to connect the AI

LMFlow is a comprehensive suite for large language model fine-tuning, context extension, multimodal processing, and inference execution. It provides a toolkit for updating model parameters through full tuning or memory-efficient adapter algorithms, alongside an inference engine for executing tuned models via command-line or web-based interfaces. The framework includes a dedicated alignment suite for supervised tuning and reward model training to refine model behavior. It features a context window extender to increase maximum input lengths and a multimodal framework for building chatbots that

Jeesite is a full-stack low-code development framework designed for building enterprise administrative portals using Spring Boot, MyBatis, and Vue. It functions as a comprehensive platform for creating administrative dashboards with integrated role-based access control and organizational data permission systems. The framework distinguishes itself through a combination of automated CRUD code generation and an integrated RAG platform that connects large language models to enterprise data via vector stores. It further incorporates a BPMN-based workflow engine to automate complex business process

This project is a serverless application that integrates OpenAI models with the LINE messaging platform. It functions as a bridge to enable real-time conversations, text generation, image creation, and speech-to-text transcription within the messaging interface. The system is designed for cloud-native deployment on Vercel, utilizing serverless functions and webhooks to handle API traffic. It features environment-driven configuration to manage bot personalities, API secrets, and access controls such as user or group limits. Beyond basic chat, the assistant includes conversational orchestratio

This project is a reference implementation and application template for Retrieval-Augmented Generation (RAG). It integrates Azure OpenAI with Azure AI Search to enable conversational chat interfaces that provide grounded responses based on private enterprise data. The system is distinguished by its multimodal AI interface, allowing it to process and reason over combined text, image, and PDF content. It employs a hybrid search architecture that combines vector and keyword retrieval with semantic reranking to prioritize the most relevant documents for prompt augmentation. The project covers a

Helicone is an AI gateway and observability platform designed to intercept, manage, and monitor interactions with large language models. By acting as a reverse-proxy, it provides a centralized layer for routing requests across multiple AI providers, allowing developers to maintain consistent application logic while gaining deep visibility into model performance, usage, and costs. The platform distinguishes itself through a robust suite of traffic management and prompt engineering tools. It enables policy-driven control, including automatic failover between providers, rate limiting, and edge-b

PartyKit is a serverless WebSocket backend platform for building real-time multiplayer applications. It provides a globally distributed edge computing runtime that runs stateful server code close to users, with automatic scaling and hibernation for idle rooms. The platform handles WebSocket connections, HTTP requests, and durable storage without requiring infrastructure management, and includes a client and server SDK with hooks, storage, and Yjs integration for building collaborative features. The platform distinguishes itself through per-room isolation using Durable Objects, where each uniq

OpenChat est une plateforme de gestion de chatbots IA utilisée pour construire, déployer et gérer des agents personnalisés propulsés par de grands modèles de langage. Elle sert de suite de support client omnicanal qui intègre l'automatisation par modèle de langage avec des canaux de communication incluant l'email, le SMS, les réseaux sociaux et la voix. La plateforme dispose d'un intégrateur de base de connaissances à génération augmentée par récupération (RAG) qui ingère des documents, des sites web et des bases de code pour fournir des réponses contextuelles. Elle inclut une couche de confidentialité dédiée pour la détection et la suppression des informations personnelles et de santé sensibles afin de maintenir la conformité réglementaire. Le système fournit une passerelle API avec une interface REST et des webhooks pour la gestion programmatique, aux côtés d'une passerelle de messagerie multicanal. Il inclut également des outils pour synchroniser les données CRM et helpdesk externes, ainsi qu'un widget piloté par JavaScript pour intégrer des interfaces de chat dans des sites web externes.

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

Corpora est une bibliothèque de corpus textuels et de jeux de données structurés, organisés par domaine. Elle fournit des collections de noms, adjectifs et verbes catégorisés au format JSON, destinés à être utilisés comme données statiques d'entraînement ou de test pour des agents conversationnels et des systèmes automatisés. Le projet organise les données linguistiques dans divers domaines, notamment la science, l'art et la géographie. Ces jeux de données sont distribués sous forme de fichiers autonomes utilisant un schéma neutre vis-à-vis du langage et un modèle de données JSON statique, permettant une importation directe dans les applications sans couche API. La bibliothèque prend en charge la génération de contenu pour chatbots et le développement rapide de prototypes en fournissant une intégration de données structurées. Elle utilise la catégorisation par nature grammaticale et le partitionnement par domaine pour faciliter la création de dialogues et le test de modèles de machine learning.

MallChat est un système backend e-commerce et une plateforme de messagerie en temps réel. Il fournit une infrastructure côté serveur pour gérer les boutiques en ligne, incluant des paniers d'achat intégrés, le traitement des commandes et les flux de travail de paiement. Le système dispose d'un serveur de chat WebSocket pour la communication instantanée avec les clients et d'un moteur de modération de contenu qui utilise la correspondance de modèles pour bloquer le langage sensible. Il intègre des grands modèles de langage pour fournir des chatbots IA conversationnels automatisés pour le support client et les recommandations de produits. La gestion de l'identité est traitée via un système d'authentification basé sur des jetons qui prend en charge la vérification par code QR. La plateforme inclut également une gestion du trafic API pour contrôler la fréquence des requêtes et un flux de travail de modération pour filtrer les phrases interdites en temps réel.

Ce projet est un framework d'agent IA et de chatbot multicanal qui permet à une seule intelligence IA d'être déployée à travers diverses plateformes de messagerie, interfaces web et comptes email. Il fonctionne comme une passerelle IA multi-modèles, fournissant une interface unifiée pour router les requêtes entre différents fournisseurs de modèles de langage. Le système se distingue par ses capacités de planification autonome des tâches et de gestion des connaissances. Il peut décomposer des objectifs complexes en étapes d'exécution séquentielles en utilisant des outils externes et un navigateur headless, tout en extrayant simultanément des informations des conversations pour construire une base de connaissances structurée avec des graphes de relations visuels. La plateforme inclut un système de mémoire à plusieurs niveaux pour la récupération de contexte à long terme, un moteur de plugin de compétences dynamique pour étendre les fonctionnalités, et la capacité d'exécuter des commandes système à distance. Elle prend également en charge les workflows multimodaux, permettant l'échange d'images, de messages vocaux et de fichiers à travers différents canaux de communication. L'instance peut être gérée via une console web, une interface de commande basée sur le terminal, ou via des commandes slash dans le chat.