Get early access
Copilot Kit Logo
Back
Introducing the AG-UI Protocol CLI
By Nathan Tarbert
September 4, 2025

Building agentic applications just got a whole lot easier.

We’re excited to release the AG-UI protocol CLI flow- the quickest and easiest way to get started with AG-UI in under two minutes.

Why this matters

Most developers want to test ideas fast without spending hours wiring up configs and boilerplate. The CLI flow solves that by giving you a zero-friction way to:

  • Spin up a new project from scratch
  • Plug into all major frameworks out of the box
  • Or run with our standalone terminal client if you prefer a lightweight setup and are curious about creating your own client integration.
__wf_reserved_inherit

In other words, you can go from nothing to a running agentic application without touching a line of setup code.

How it works

  1. Install the CLI → one command to set everything up npx create-ag-ui-app@latest.
  2. Choose your framework → React, Next.js, Vite, or go terminal-only.
  3. Start coding → you’re instantly connected to the AG-UI protocol, ready to build interactive, agent-powered experiences.

The CLI flow generates the right project structure, wires in AG-UI events, and leaves you with clean, production-ready scaffolding you can actually build on.

Demo GIF

Why developers love it

  • Speed → Get to “Hello Agent” in under 2 minutes.
  • Flexibility → Works across agentic frameworks and terminal environments.
  • Extensibility → everything you scaffold is ready for customization.

Try it today

If you’ve been curious about AG-UI but didn’t want to agonize over setup, I invite you to check it out. The CLI flow is the fastest way to experience the AG-UI protocol and start building agentic apps from scratch.

👉 Check out the AG-UI Protocol on GitHub

👉 Join the growing community of developers building agentic apps

‍

Top posts

See All
Build Generative UI Agents on Amazon Bedrock AgentCore with AG-UI and CopilotKit
Anmol Baranwal and Nathan TarbertJune 30, 2026
Build Generative UI Agents on Amazon Bedrock AgentCore with AG-UI and CopilotKitAmazon Bedrock AgentCore now runs AG-UI agents natively, so auth, scaling, and session isolation come managed. We build one agent that renders charts inline, syncs a todo canvas both ways, and pauses for human input. Pick Strands or LangGraph at deploy time, and the same frontend runs against either.
Switching to Fable 5: The Tuesday That Cost $22,000
Jordan Ritter June 12, 2026
Switching to Fable 5: The Tuesday That Cost $22,000CopilotKit swapped their coding agents to a new model (fable-5) on a Tuesday, and by Wednesday had run up a ~$22,000 Anthropic bill. No bug or runaway script caused it — five engineers doing normal work triggered it, because the new model interpreted their English-prose behavioral rules ("keep sub-agents small," "converge to zero") far more loosely than older models did. The result was four simultaneous drift modes: bloated sub-agents, runaway review loops, exploding fanout, and oversized single turns. What kept it from being far worse was their "skills" system — small, named instruction packs that agents auto-load to encode team conventions. Their instrumentation caught the runaway in 12 hours instead of 12 days, isolated worktrees contained the blast radius, and the fix lived at the rules layer (swapping vague adjectives for hard numeric budgets and machine-checkable gates) rather than in application code. The takeaway: if you let AI agents do real work, you need a guardrails layer that encodes desired behavior separately from the agents — small, composable, and faster to change than a model. Because models will change, and the team with a rules layer pays $22K and writes a blog post; the team without one pays more and writes a press release.
Build AI Agents That Live Inside Your App — CopilotKit Explained
Nathan Tarbert June 12, 2026
Build AI Agents That Live Inside Your App — CopilotKit ExplainedCopilotKit is a complete set of building blocks for developers and teams who want to add agents to their app and assemble, debug, and ship the interface layer between their agents and users. It's also framework-agnostic and supports any LLM and every popular agent framework. There are two options for chat. Pre-built components, if you want something already built or Headless UI, which allows anyone to build custom agent interfaces.
Are you ready?

Stay in the know

Subscribe to our blog and get updates on CopilotKit in your inbox.