New: Preconfig Doctor explains a failed setup, and fixes the spec when the cause is there

Ready machines for coding agents

Describe what your project needs once. Preconfiguration writes the setup file each agent platform reads, checks each one, and runs the setup on a clean machine with your tests before any agent starts. When a setup fails, Doctor reads the log, names the cause and, when it's in the spec, writes the fix.

5 platforms

Written from one preconfig.yaml: dev containers, GitHub Copilot, Cursor, cloud-init and a plain setup script

About 1 minute

From a clean Ubuntu 24.04 machine to passing tests, with PostgreSQL and Redis running (49.6 to 73.0 s)

32 of 32

Bugs planted in Core on purpose and caught by its tests. Doctor's tests caught 14 of 14

20 of 20

Doctor's fixes run again on a clean machine, every failure gone: 19 setups READY and Cursor's Dockerfile built

Measured on the Alphas of Preconfig Core and Preconfig Doctor on one Linux machine with 2 CPUs. The Beta measures every number again with real agents on the platforms themselves.

Articles and case studies

All posts →

technology

Introduction

Ready machines for coding agents: describe what a project needs once, and each agent platform gets a setup file it can read, checked against its rules, with the setup run …

technology

How It Works

The idea. Describe the machine a project needs in one short file. preconfig writes the setup file each agent platform reads, checks the files a repository already has, …

Get in touch

Teams running AI coding agents who would like to try the Beta on their own repositories, and anyone with a stack, a platform or a failed setup log the project should test, are welcome to write.

Contact