Post

We’re announcing Standard Code: a new coding agent with unlimited use, like a cell phone plan. Each line has no 5-hour, weekly, or rate limit and powers one coding session. More lines = more parallel sessions. How is unlimited use possible? 👇

1 repost7 likes

Umans tried unlimited plans and couldn't because people let their agents run 24/7 on the most expensive models. How can you prevent the same from happening to you? People will find ways to abuse offers like that.

Some measured data from the 24/7 side: my scheduled agents did 100 unattended runs and hit the 5-hour session limit once. The trigger wasn't steady load but a catch-up burst after downtime — 23.8M tokens in one window tripped it, 19.9M spread across windows never did.

Yeah I've read the website but I am not sure if the line idea is enough to make sure that 1. You don't go bankrupt 2. Users get decently good service You simply can not serve frontier models 24/7 for $50/month

In Standard Code you don’t pick models, you pick Agents. At launch, two agents are included: - Unlimited One - Sama One (for OpenAI subs) Each is a carefully curated, Pareto-optimized coding agent that uses many models across the various domains in coding.

For Unlimited One, each parallel session requires purchasing a line of service. Just like a cell phone bill, it’s a predictable expense and won’t leave you out of tokens at the end of the week.

Sama One lets you bring your Codex sub to Standard Code, unlocking infinite parallel lines. It sips your weekly OpenAI usage because it, too, is a heavily optimized, curated collection of domain-specific agents built on OpenAI’s latest models.

Standard Code runs in the cloud. Install a tiny daemon on any machine(s), then create new projects from the web, native Mac app, or the CLI coding agent. The expensive agent work is done in the cloud, so even a tiny VPS works great. Close your laptop and walk away.