← Discover
GitHub · CopilotKit/CopilotKit↑ +366 today

AI Interfaces for Your Applications

CopilotKit offers a React and Angular-based frontend stack for developing artificial intelligence agents and generative UIs. It provides an infrastructure that enables smart capabilities to be integrated into applications via the AG-UI protocol.

Updates

  • November 7, 2026: Stars 38,500 → 38,549, latest release v1.85.0 (November 6, 2026).
  • November 4, 2026: Stars 38,480 → 38,500, latest release v1.84.1 (November 3, 2026).
  • November 3, 2026: Stars 38,346 → 38,480, latest release v1.84.0 (November 3, 2026).
  • October 29, 2026: Stars 38,299 → 38,346, latest release channels/v0.12.0 (October 28, 2026).

What you get

  • It adds dynamic and intelligent interfaces to applications.
  • It provides real-time data sharing between artificial intelligence agents and the user interface.
  • It enables the creation of human-approved workflows and self-learning agents.

Installation

Add with npm
npm install @copilotkit/react-core

If you don't write code

Paste this into your AI agent (Claude Code · Codex · Antigravity)

I want to add artificial intelligence capabilities to my application using CopilotKit. How can I configure the installation according to the infrastructure of my project using the npx copilotkit@latest create -f <framework> or npx copilotkit@latest init commands for my current project? Explain the basic steps I need to follow to get agents to interact with the interface and start using Generative UI features.

Repository: https://github.com/CopilotKit/CopilotKit. Follow the official instructions in the README of this repository for setup and execution.

Before starting, check which OS we are on and if the necessary tools (e.g., Python, Node.js, Git, Docker) are installed. Install any missing ones step-by-step according to this system.

Create a new, empty folder to work in. Do not touch any files outside this folder and do not delete anything. Tell me what you are going to do in one sentence before running each command.

Tell me what I should see on the screen at the end of each step. If an error occurs, I will paste the error message to you exactly as it is, and we will fix it together.

Related dictionary terms

Who it is forIt is suitable for software developers who want to integrate AI-powered intelligent interfaces and agent-based workflows into their applications.
LicenseMIT

Links

TreScout did not build this tool · we found it in GitHub trends and wrote it up. This page describes the repository as of 2026-06-06: The star count and our text belong to that day, the repository may have changed since. Check the repository link for the current state. The introductory text was prepared with AI from the repository's own documentation, and this page was machine-translated from the Turkish original · the Turkish version prevails.