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
tgoai/tgo
TGO is a self-hosted customer service platform built around teams of AI agents rather than a single chatbot. It is assembled from several services kept in one repository: Python and FastAPI services for AI operations, core business logic, multi-channel message intake, plugin runtime and retrieval, a TypeScript CLI that also acts as an MCP server exposing more than forty customer service operations to external agents, a Go device agent that provides file and shell access over TCP JSON-RPC, a device control service, and a web administration frontend. Agent orchestration lets an operator configure multiple agents for different business scenarios, connect several LLM providers such as OpenAI and Anthropic, stream responses over server-sent events and retain conversation history for coherent dialogue. Knowledge grounding uses retrieval augmented generation over three kinds of source: uploaded documents, curated question and answer pairs, and crawled website content, retrieved through hybrid semantic and full-text search. Tools come from an MCP tool store that can be enabled per project, alongside custom tools and OpenAPI schemas that are parsed automatically into interactive forms. Messages arrive from an embeddable web chat widget, WeChat official accounts and mini programs, and platform connectors for Feishu, DingTalk, Telegram, Slack and email, all managed from one dashboard, with real-time delivery handled by a WuKongIM integration over WebSocket including read receipts and rich media. When an agent cannot resolve a request, a handoff mechanism transfers the conversation to a human operator who works in a dedicated workspace with visitor details, session assignment and history. A widget system renders structured business objects such as orders, logistics tracking, product cards and price comparisons, driven by a standardised action protocol. Deployment is a single bootstrap script on a server or Docker Compose for local development.
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.
microsoft/TypeChat
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.
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.