Standard Code | Always online. Unlimited usage. One flat price.
The how<br>How is unlimited usage possible?<br>Standard Code is able to offer unlimited usage because of its unique lines-of-service billing model and a novel, curated agent architecture .
01 · Lines of service<br>One active session per line<br>Each active Standard Code session occupies a line of service on your plan. Lines of service can be added to your plan at any time if you require additional parallel sessions .
02 · Concurrency, not tokens<br>Each line is unlimited<br>For each active line of service on your plan, you can run a Standard Code session with unlimited usage . Usage is constrained by linear time, not token quota .
03 · Preconfigured sub-agents<br>Standard Code is a swarm of agents<br>Standard Code is made up of a pre-configured, finely-tuned team of expert agents. Each is automatically invoked as needed , and sub-agents do not count against your active lines of service .
04 · Composable agent architecture<br>Sub-agents are full agents<br>Every sub-agent is a specialized domain-specific agent with its own curated prompts, tools, and context . This allows us to tune the agents that make up Standard Code for maximum efficacy per dollar.
Lines of service−+$294/ mo6 × $49/line
Stop configuring, start building<br>Two curated cloud agents built for real-world work.
standardcode · ~/app
Standard Code v0.11.6<br>terminal coding agent<br>~/projects/app
Standard Code — Unlimited One<br>project: ~/projects/app<br>machine: Mac-Studio.local thread: e7c80ca8<br>tool execution: this terminal
❯ migrate our REST layer to tRPC, update every call site, and keep the tests green<br>✓ code_explorer_agent · 214 files mapped<br>✓ research_agent · findings delivered<br>✓ edit src/server/router.ts<br>✓ edit src/api/client.ts (+412 −380)<br>✓ update 37 call sites across 22 files
⣽ compaction_agent compacting context while work continues<br>Goal 2/3 migrate REST → tRPC<br>✓edit the server and client files<br>✓update dependent call sites<br>▸run the test suite
⣽ Working bash: pnpm test · ↑41.2k ↓0.6k · ctx 31%<br>Unlimited One
session 1 of 1 unlimited usage
CLI<br>API<br>Web app<br>macOS app<br>iOS app<br>Always-on cloud coding agent<br>Unlimited One<br>Standard Code's default agent leveraging open weight models. The world's first curated coding agent — powered by a coordinating team of domain-specific agents.<br>A curated collection of domain-specific agents working in concert<br>Unlimited usage per active session<br>Sessions run in the cloud and can be resumed from any connected machine<br>Flat, predictable billing per line of service
Always-on cloud coding agent<br>Sama One<br>Standard Code's same domain-specific agent architecture powered by OpenAI models. Uses your existing ChatGPT Pro subscription.<br>The same novel domain-specific agent architecture<br>Uses your existing Codex token quotas<br>Sessions run in the cloud and can be resumed from any connected machine<br>Does not occupy available lines from your Standard Code plan<br>Requires at least one active line of service.<br>Learn more about using Standard Code with OpenAI models →
provision.ts — northstar-web<br>provision.tsstream.tswebhook.ts<br>1234567891011121314151617181920212223242526<br>const BASE = "https://api.standardcode.ai";<br>const KEY = process.env.STANDARDCODE_KEY!;<br>const auth = { Authorization: `Bearer ${KEY}`, "Content-Type": "application/json" };
// one thread per job, resumable from any client<br>const { threadId } = await fetch(`${BASE}/api/threads`, {<br>method: "POST",<br>headers: auth,<br>body: JSON.stringify({ agent_id: "standard_code_agent", tags: ["ci"] }),<br>}).then((r) => r.json());
// sending a user message starts the agent's turn<br>await fetch(`${BASE}/api/threads/${threadId}/messages`, {<br>method: "POST",<br>headers: auth,<br>body: JSON.stringify({ role: "user", content: "Rate-limit the upload route." }),<br>});
// watch it work<br>const ws = new WebSocket(<br>`${BASE.replace("https", "wss")}/api/threads/${threadId}/stream?token=${KEY}`,<br>);<br>ws.onmessage = (e) => {<br>const f = JSON.parse(e.data);<br>if (f.type === "message_chunk") process.stdout.write(f.chunk);<br>};<br>TypeScriptLn 26, Col 3 · UTF-8 · LF
The Standard Agents architecture<br>CLI<br>API<br>Web app<br>macOS app<br>iOS app<br>Every client connects<br>to the same cloud sessions.<br>How does it work? Take a look behind the scenes
standardcode · ~/app
Standard Code v0.11.6<br>terminal coding agent<br>~/projects/app
Standard Code — Unlimited One<br>project: ~/projects/app<br>machine: Mac-Studio.local thread: e7c80ca8<br>tool execution: this terminal
❯ migrate our REST layer to tRPC, update every call site, and keep the tests green<br>✓ code_explorer_agent · 214 files mapped<br>✓ research_agent · findings delivered<br>✓ edit src/server/router.ts<br>✓ edit src/api/client.ts (+412 −380)<br>✓ update 37 call sites across 22 files
⣽ compaction_agent compacting context while work continues<br>Goal 2/3 migrate REST → tRPC<br>✓edit the server and client files<br>✓update dependent call sites<br>▸run the test suite
⣽ Working bash: pnpm test · ↑41.2k ↓0.6k · ctx 31%<br>Unlimited One
session 1 of 1 unlimited usage
Standard Code is<br>always...