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
plurai-ai/intellagent
IntellAgent is a sophisticated multi-agent framework designed for the comprehensive diagnosis, evaluation, and optimization of conversational AI agents through simulated, realistic synthetic interactions. The framework enables users to simulate thousands of diverse and challenging user-agent interactions, which helps uncover hidden failure points and blind spots in conversational agents. This process allows developers to gain actionable insights to improve agent performance, reliability, and overall user experience. The core functionality of IntellAgent revolves around generating highly realistic edge-case scenarios tailored specifically to the agent under test. It simulates a wide spectrum of user interactions with varying complexity levels, providing a thorough stress test for conversational agents. The framework then performs detailed performance evaluations, offering comprehensive analytics to identify gaps, prioritize improvements, and compare results across different experiments. IntellAgent operates through a three-step process: first, it decomposes user prompts into a policy graph and samples relevant policies based on real conversation distributions. Next, it generates user-chatbot interaction scenarios, including system databases, to test these policies. Finally, it simulates the interactions using a user agent and critiques the conversations to provide feedback on the tested policies. The framework supports easy integration with existing conversational agents and offers customization options to tailor simulations to specific environments. It also provides visualization tools via a Streamlit dashboard to analyze simulation results effectively. IntellAgent supports multiple large language model (LLM) providers such as OpenAI, Azure, Vertex, and Anthropic, allowing flexible configuration. The project is open-source under the Apache 2.0 license and encourages community contributions, including new examples and environments. It also maintains transparency by open-sourcing usage metrics while respecting user privacy. The roadmap includes further integration with agent platforms, event generation from databases, API integration, and advanced optimization features. Overall, IntellAgent is a powerful tool for developers and researchers aiming to enhance the robustness and reliability of conversational AI systems through rigorous, data-driven testing and optimization.
https://github.com/plurai-ai/intellagent
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.