Run the real app
Codex Desktop lives inside an isolated worker with its own persistent state.
Don’t rebuild it.Just use Codex.
Codex Desktop in a Docker container. Bridge it over HTTP. Keep its native browser, computer use, threads, and free upgrades from OpenAI.
One Docker container · One HTTP API · Full Codex capabilities
HTTP-nativeOne clean API
Real Codex DesktopNot an imitation
Built-in browserCapabilities intact
Persistent threadsContext stays put
Desktop power.
Worker shape.
The shortest path to a capable Codex worker is the one that keeps Codex itself in the loop. JustUseCodex wraps the native app in a container and gives your code a straightforward HTTP surface.
Talk over HTTP
Send turns, inspect status, manage threads, and invoke the native runtime through one API.
Build the thing
Connect your app, automation, or agent. The browser and computer-use surface come along.
Use any inference providers you want in Codex Desktop.
No SDK
required.
If it can make an HTTP request, it can use your worker. Start a turn with JSON and follow the run until Codex is done.
API
Get service health
Check the running Headless Codex worker.
GET
/v1/healthResponse
Not sentChoose “Send request” to preview the response.
Bro, you're not going to out-build OpenAI's coding product from your bedroom.
They have an army of engineers and a mountain of GPUs. That annoying missing feature? They'll probably ship it before you finish rebuilding their entire stack.