· Early access

Get early access
Copilot Kit Logo

Why I joined CopilotKit: Welcoming CopilotKit's New Head DevRel

By Graham McBain
November 18, 2024
Why I joined CopilotKit: Welcoming CopilotKit's New Head DevRel

Why I Joined CopilotKit: Embracing the Future of Open Source AI

Introduction

This past Monday marks my first day at CopilotKit, and I couldn’t be more thrilled to join the team as their Developer Relations Lead. As someone who has spent years in the tech industry building and nurturing developer communities, I am genuinely excited about the incredible open-source ecosystem that CopilotKit has cultivated. In this article, I want to share why I chose to join CopilotKit, highlight my experiences, and discuss how I plan to engage with this vibrant community to create opportunities for building groundbreaking applications using CopilotKit, LangGraph, and cutting-edge Large Language Models (LLMs) like OpenAI and Anthropic.

My Journey in Tech and Community Building

Over the past decade, I’ve had the privilege of working with some amazing teams and communities. My journey began as a Salesforce developer, but I quickly realized that my true passion lay in connecting people, sharing knowledge, and fostering collaboration. This led me to roles focused on developer advocacy and community management, where I helped build thriving ecosystems around various technologies.

I’ve been fortunate to have a hand in organizing some truly great events, like Rocky Mountain RubyFintech Devcon, WalletCon and most recently Farcon. The experience I’m most proud of is when I created the “learn to code” program at Galvanize, a code school based in Colorado. Through that program I was able to teach over fifteen hundred people how to write their first lines of code.

I’ve learned that enabling creativity through technology is what gets me fired up. After playing with the demo of CopilotKit I realized how many people I could reach with this technology and I knew I had to get onboard.

The Allure of CopilotKit’s Open Source Community

When I first learned about CopilotKit, I was immediately drawn to its mission and the passionate community behind it. CopilotKit isn’t just another framework or tool—it’s a movement towards democratizing access to advanced AI technologies.

Already the adoption of CopilotKit is staggering. With over 12k github stars at the time of this posting and 7k NPM installs per week, the project is gaining momentum rapidly.

What’s needed now is someone (me) to harness this community to build a movement. My goal is to empower this community to let any developer build a production ready agentic application in a few hours.

My Vision as Senior DevRel at CopilotKit

Joining CopilotKit feels like a natural next step in my career—a place where I can combine my passion for community building with a technology that has the potential to revolutionize every industry on earth.

The best technology in the world is useless if nobody knows how to use it. What CopilotKit has done is abstract away just enough of the complexity  of building agentic apps to make it easy for the average developer to pick up. What’s impressive is that CopilotKit is also fully compatible with even the most complex agentic workflows.

My goal with this role is to allow any dev team to quickly wrap their head around building an agentic application and make meaningful impact on their buisiness or idea. A space growing this rapidly is scary. It’s my job to simplify the opportunities available and provide a path to execute on them. Luckily the CopilotKit team has done the heavy lifting, I just need light the runway.

Looking Ahead

The future is incredibly bright for CopilotKit and its community. The rapid advancements in AI present both exciting opportunities and important challenges. As we navigate this landscape, my focus will be on ensuring that our community remains at the heart of everything we do.

  • Simplicity: Everywhere possible I want to look to eliminate jargon and complexity, making it easy for anyone to understand how to get their hands on this technology
  • Community: Creating a culture of “give first” and encouraging our community to help each other
  • Support: If you’re building your application on CopilotKit, we’ll be here for you. We’ll help you with problems and celebrate your wins

Conclusion

Joining CopilotKit is more than just a career move for me—it’s a chance to be part of a transformative time in the tech industry. I’m eager to roll up my sleeves and start working with all of you, the brilliant minds that make this community so special. Together, we’ll build amazing things, break new ground, and shape the future of agentic applications.

Here’s to the exciting road ahead!

Let’s connect and start this journey together. Feel free to reach out to me on our community channels or drop me a message. I can’t wait to hear your ideas and see what we’ll create together.

Top posts

See All
The Tuesday That Cost $22,000
Jordan Ritter June 12, 2026
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.
CopilotKit - The Complete Frontend Stack for AI Agents
Anmol Baranwal and Nathan TarbertMay 20, 2026
CopilotKit - The Complete Frontend Stack for AI AgentsCopilotkit is the open source frontend stack for AI agents. Learn about architecture, chat components, hooks, generative UI, persistent memory, debugging tools, and 13+ agent framework integrations for building Agentic UIs.
Are you ready?

Stay in the know

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