Blog

There's no such thing as a free token. For now, LLM inference is quite expensive. It’s getting cheaper, but your near unrestricted access to the frontier of AI on a daily basis costs someone, somewhere quite a lot of money.

Cursor is an incredible IDE for local, AI-assisted development, but there's a pricing problem - especially when it comes to background agents. The solution? Connect cto.new via MCP server. This approach lets you offload heavy lifting to a free, world-class coding agent right from your primary, local IDE experience, without adding bloat.

Most AI benchmarks are built backwards. Someone sits down, dreams up hard problems, and then measures how well agents solve them. The results are interesting, sure. But they don't always tell you what matters: how agents perform on the actual work that's sitting in your queue. That's why we built cto.bench.

The standard developer workflow often starts with friction: setting up a repo by configuring the environment, establishing boilerplate, etcetera. By the time you're ready to write actual code, some of the initial momentum is gone. Cto.new streamlines this process by separating planning from execution, and taking care of the setup along the way. It does this through two distinct modes: Chat and Tasks.

I've spent the last month watching how teams use cto.new, and I've noticed a few patterns in what works and what doesn't. It's not really about the setup, most people figure that out fine. It's about how you think about delegating work to an AI agent.

Jeremy King, a veteran software architect near Raleigh, North Carolina, has turned solo development into a high-velocity operation through AI tools—particularly using cto.new via the GitHub interface. A longtime consultant and hands-on coder, Jeremy now builds full-stack projects like Leaderboard Fantasy and TutorPro by orchestrating a network of AI coding agents. His workflow runs almost entirely through GitHub: he uses Claude to write specs, breaks work into small issues, assigns tasks directly to cto.new for implementation, and uses Copilot for QA reviews.

An alloyed agent runs on more than one LLM in a single agentic loop with shared context.

There has been a lot of chatter in the coding agent world over the last few months about context engineering and managing long contexts. The defining work on this is probably...

The mission is straightforward: put our best in class coding agent behind a task orchestration agent we call cto.new, make it free and empower a generation of software engineers to break through the clouds and soar into wild new levels of productivity.