Awesome AI AgentsChatbot Platforms

nexu-io/nexu

⭐ 3270 TypeScript repository created 2026-02-25

nexu is an open-source desktop client that runs a personal AI agent, primarily OpenClaw, and connects it to instant messaging channels so the agent becomes reachable from a phone. It ships for macOS on Apple Silicon and Intel and for Windows, and is installed by downloading and double-clicking rather than by setting environment variables or wrestling with dependencies. Built-in channel support covers WeChat, Feishu, Slack and Discord; the WeChat path works with the WeChat 8.0.7 OpenClaw plugin and is set up by clicking connect and scanning a code. Once a channel is linked, the agent stays online continuously and can be used from any device where that messenger is installed, with no separate mobile application. The client bundles native OpenClaw skills together with a full set of Feishu skills so agents can act inside workflows a team already uses without extra integration work. Model access is flexible: top-tier models such as Gemini can be used through a nexu account with no additional configuration, MiniMax, OpenAI Codex and GLM on the Z.AI coding plan support OAuth login with one click, and users who prefer their own providers can add an API key and use the client without creating an account at all. Switching between models is done in the graphical interface rather than in configuration files. The project positions itself as local-first: business data stays on the user's machine and is not routed through vendor servers, and the MIT license allows forking and auditing. A comparison table in the README contrasts this with the official OpenClaw CLI, which requires manual configuration and self-deployment, and with hosted agent stacks that lock users to a platform and charge per seat. The stated audience is one-person companies and small teams.

https://github.com/nexu-io/nexu

desktop-clientopenclawmessaging-integrationlocal-firstchatbot

Also in Chatbot Platforms

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.

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.

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.