Awesome AI AgentsAI Agents

langchain-ai/agent-chat-ui

⭐ 3147 TypeScript added to this list on 2025-03-16 repository created 2025-02-18

Agent Chat UI is a web application built with Next.js that provides a chat interface for interacting with any LangGraph server that supports a `messages` key. It allows users to communicate with LangGraph agents, which can be implemented in Python or TypeScript, through a user-friendly chat interface. The application can be run locally or accessed via a deployed site, making it flexible for different user needs. The setup process is straightforward, involving cloning the repository or using an `npx` command to create the app, installing dependencies, and running the development server. Users are prompted to enter the deployment URL of the LangGraph server, the assistant or graph ID, and optionally a LangSmith API key for authentication when connecting to deployed servers. Environment variables can be set to bypass the initial setup form for convenience. Agent Chat UI supports advanced features such as controlling message visibility during live streaming or permanently hiding messages from the chat interface by using specific tags and message ID prefixes. This allows for customization of the chat experience and better control over what is displayed to users. For production deployment, the app provides two main authentication methods: API Passthrough and Custom Authentication. API Passthrough uses a proxy to handle authentication and requests, simplifying the production setup. Custom Authentication offers a more robust and flexible approach, allowing client requests without requiring a LangSmith API key and enabling custom access controls. Overall, Agent Chat UI is designed to facilitate seamless interaction with LangGraph agents through a chat interface, supporting both development and production environments with configurable authentication and message handling features. It is a valuable tool for developers looking to integrate conversational AI agents powered by LangGraph into their applications.

https://github.com/langchain-ai/agent-chat-ui

agentapi-passthroughassistant-idchatchat-appchat-interfaceconversational-aicustom-authenticationdeployment-urlenvironment-variableslanggraphlanggraph-serverlangsmith-api-keylive-streamingllmmessage-visibilitymessages-keynext.jsproduction-deployment

Also in AI Agents

OpenHands/OpenHands

OpenHands is an AI-powered platform that automates software development tasks, enabling developers to code less and produce more by modifying code, running commands, browsing the web, and integrating APIs efficiently.

usestrix/strix

Strix is an open-source AI-driven security testing platform that autonomously finds, validates, and helps fix application vulnerabilities through dynamic and collaborative AI agents.

aaif-goose/goose

Goose is an open-source, native AI agent available as a desktop app, CLI, and API, designed for diverse tasks like code, research, writing, and automation, supporting over 15 LLM providers.

KeygraphHQ/shannon

Shannon is an autonomous AI pentester for web applications and APIs, analyzing source code, identifying attack vectors, and executing real exploits to prove vulnerabilities.

wshobson/agents

A comprehensive collection of 44 specialized AI subagents for Claude Code that enhance development workflows with domain-specific expertise across software development, infrastructure, security, data, and business domains.

agentscope-ai/agentscope

AgentScope is a transparent, modular, and customizable framework for building LLM-empowered multi-agent applications with real-time control and asynchronous execution.

iOfficeAI/OfficeCLI

OfficeCLI is an open-source command-line interface and API enabling AI agents to read, edit, and automate Word, Excel, and PowerPoint files without needing Office suite installations.

langchain-ai/deepagents

Deep Agents is an open-source agent harness built on LangChain and LangGraph that enables AI agents to plan, execute, and delegate complex long-horizon tasks using customizable tools, subagents, and human-in-the-loop workflows.