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
microsoft/TypeChat
TypeChat is a library designed to simplify the creation of natural language interfaces by leveraging types instead of traditional prompt engineering. Natural language interfaces have historically been challenging to build, often relying on complex decision trees to interpret user intent and gather necessary inputs. The advent of large language models (LLMs) has eased this process by enabling direct natural language input interpretation. However, this introduces challenges such as constraining model responses for safety, structuring outputs for further processing, and validating the model's replies. Prompt engineering attempts to address these issues but is complex and fragile as prompt size grows. TypeChat innovates by replacing prompt engineering with schema engineering. Developers define types that represent the intents their natural language applications support. These types can range from simple interfaces like sentiment categorization to more complex schemas for applications such as shopping carts or music players. Additional intents can be added by extending discriminated unions, and hierarchical schemas can be created using meta-schemas that select sub-schemas based on user input. Once types are defined, TypeChat automates the process by constructing prompts for the LLM using these types, validating that the LLM's responses conform to the schema, and repairing any non-conforming outputs through further interaction with the language model. It also summarizes the validated instance succinctly without using an LLM to confirm alignment with user intent. TypeChat supports multiple programming environments including TypeScript/JavaScript, Python, and C#/.NET, with example projects and comprehensive documentation available to help users get started. The project encourages contributions and follows Microsoft's open source guidelines and code of conduct. In summary, TypeChat offers a robust, type-driven approach to building natural language interfaces that enhances reliability, safety, and maintainability compared to traditional prompt engineering methods.
https://github.com/microsoft/TypeChat
Also in Chatbot Platforms
CopilotKit/CopilotKit
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.
run-llama/rags
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.
SylphAI-Inc/AdalFlow
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.
nexu-io/nexu
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/LLPhant
LLPhant is a comprehensive PHP generative AI framework inspired by Langchain, supporting multiple LLMs and designed to simplify building powerful AI applications.
langchain-ai/streamlit-agent
Reference implementations of various LangChain agents as interactive Streamlit applications demonstrating conversational AI capabilities and integrations.
yym68686/ChatGPT-Telegram-Bot
TeleChat is a versatile AI-powered Telegram bot that integrates multiple advanced language models and APIs to provide multimodal conversational AI, web search, and document processing capabilities within Telegram chats.