ArkorAlpha
Oddphin, the Arkor mascot

Build the model behind your product.

Build your first model

By creating an endpoint you agree to the Terms of Service and Privacy Policy.

Fine-tune and deploy your model, all in TypeScript.#

01

Tell your coding agent what model to build

YouClaude Code / Codex

Use Arkor to fine-tune a model that rewrites rough drafts as tweets in my style: https://github.com/arkorlab/arkor Find or prepare a suitable dataset, create the TypeScript training workflow, and tell me when it is ready to review in Arkor Studio.

02

Your coding agent builds the training project

It prepares the dataset, writes the TypeScript trainer, and adds evaluation inside your repo. Review every change before training.

TypeScript Arkor training project showing dataset files and trainer.ts in VS Code
03

Studio opens. You click Run Training.

Your coding agent runs pnpm dev and launches Arkor Studio at localhost:4000. Review the detected trainer, click Run Training, and follow the training progress in Studio.

pnpm devArkor Studio → localhost:4000

Arkor Studio's Overview page with the Run training card showing the detected trainer tweet-editor-v1

You control the run. Arkor handles the compute.

Want to try an open model first?#

Without an account, the endpoint expires after 7 days; sign up to keep yours.

By creating an endpoint you agree to the Terms of Service and Privacy Policy.

Describe the model you want.#

Your coding agent builds the TypeScript project. You review it. Arkor trains and deploys it.