lm-sys/FastChat
FastChat is an open platform for training, serving, and evaluating large language model based chatbots, featuring multi-model serving, extensive model support, and large-scale evaluation datasets.
Awesome AI Agents › Chatbot Platforms
Hexabot is an open-source AI chatbot and agent builder designed to facilitate the creation and management of multi-channel and multilingual chatbots with ease. It offers a comprehensive platform that supports integration with various large language models (LLMs) such as Ollama, ChatGPT, Mistral, and Gemini, enabling intelligent user intent detection and natural language understanding (NLU). Hexabot is highly customizable and flexible, featuring a visual drag-and-drop editor for designing chatbot flows that include text messages, quick replies, carousels, and more. The platform supports multi-channel deployment, allowing chatbots to operate consistently across web, mobile, and social media platforms. It also includes a plugin system that enables developers to extend functionality through an extensions library, adding capabilities like text-to-action responses and third-party system integrations. Hexabot supports multiple languages, allowing chatbots to interact with users in their preferred language, and integrates dynamic content such as product catalogs and store lists to enhance conversational engagement. User management is robust, with granular roles and permissions, contextual data collection for personalized responses, and subscriber segmentation through labels. The system includes an inbox and handover feature for real-time chat monitoring and seamless transition to human agents when necessary. An analytics dashboard provides insights into chatbot interactions and performance metrics. The project is structured into several components: a React/Next.js frontend admin panel for managing configurations, a NestJS backend API connected to MongoDB for data management, a React-based live chat widget for embedding on websites, and Docker Compose files for easy deployment. Hexabot is designed to be developer-friendly with a CLI tool for project setup and management, comprehensive documentation, and an active community for support and contributions. Licensed under AGPLv3, Hexabot encourages open collaboration while protecting its trademark and requiring attribution.
https://github.com/Hexastack/Hexabot
FastChat is an open platform for training, serving, and evaluating large language model based chatbots, featuring multi-model serving, extensive model support, and large-scale evaluation datasets.
CopilotKit is a React-based framework for building deeply integrated AI assistants, chatbots, and in-app AI agents that enhance user interactions through natural language and contextual understanding.
TypeChat is a library that simplifies building natural language interfaces by using types to define intents and schemas, replacing traditional prompt engineering with schema engineering for improved validation and reliability.
RAGs is a Streamlit app that enables users to build and interact with personalized Retrieval-Augmented Generation pipelines over their own data using natural language instructions.
AdalFlow is a PyTorch-like library that enables building and auto-optimizing large language model applications, including chatbots, RAG, and agents, with a unified framework for prompt optimization and model-agnostic flexibility.
Open-source desktop client that runs an OpenClaw agent locally and bridges it into WeChat, Feishu, Slack and Discord through a graphical setup, with bring-your-own-key and OAuth model access.
LLPhant is a comprehensive PHP generative AI framework inspired by Langchain, supporting multiple LLMs and designed to simplify building powerful AI applications.
Reference implementations of various LangChain agents as interactive Streamlit applications demonstrating conversational AI capabilities and integrations.