On device
$0
Per token. Bring your own API keys at no markup.
Frontier models and real tools, running on your own device.
Local execution
Security
Can
Can't
Fully open source, so you can check all of this yourself. View the code on GitHub Models
SSD streaming keeps part of a model on your SSD and loads it as needed, so big models run on smaller Macs.
Or bring the cloud
Built-in skills
Pricing
$9.99
Top-ups from $9.99 for hosted models. No subscription.
Let's talk
Setup, custom skills, on-prem.
Self-serve
Official guides
Clear setup steps, from the Draw Things team.
A private AI agent for Apple Silicon, made by the Draw Things team. Frontier models and real tools, running on your own device. Meet Local Code.
Yes. Once a model is downloaded, Local Code works with no connection at all. For air-gapped setups, talk to us. See the privacy and offline guide.
Apple Silicon with 16 GB or more. Qwen 3.8 27B runs from 16 GB (32 GB recommended). DeepSeek models run from 32 GB by streaming from your SSD; we recommend 64 GB for DeepSeek 4 Flash and 96 GB for DeepSeek 4.1 Flash 1017. Choose a model.
On-device models cost nothing per token, and your own API keys have no markup. Hosted models use credit top-ups ($9.99, $19.99 or $99.99), no subscription.
Local Code guide
Quick answers, or an engineer