Claude agent vs Claude Code: which one are you actually building?

A developer has published a minimal agent loop built on the Anthropic SDK, demonstrating that the core logic for a custom AI agent fits in roughly 40 lines of code. The implementation reveals that most agent frameworks are unnecessary, as the fundamental tool-calling loop is small enough to write from scratch. The project, called AgentLoop, is available as open-source MIT-licensed code with a streaming Next.js starter that can be deployed with a single command.

Search "claude agent boilerplate" and you'll drown in Claude Code results — the agentic CLI, CLAUDE.md files, slash commands, hooks. Great tools. But none of that is what you want if you're trying to build your own agent on the Anthropic SDK. Here's the disambiguation, and the ~40 lines that are actually the whole thing. Most "agent frameworks" just hide that loop from you. It's small enough that you don't need them. python import Anthropic from "@anthropic-ai/sdk"; const client = new Anthropic ; async function runAgent userText, tools, runners { const messages = { role: "user", content: userText } ; for let i = 0; i < 10; i++ { const res = await client.messages.create { model: "claude-sonnet-4-6", max tokens: 1024, tools, messages, } ; messages.push { role: "assistant", content: res.content } ; // No tool requested - the model is done. if res.stop reason == "tool use" { return res.content.filter b = b.type === "text" .map b = b.text .join "" ; } // Run every tool it asked for this turn, collect one result each. const results = ; for const block of res.content { if block.type === "tool use" { const out = await runners block.name block.input ; results.push { type: "tool result", tool use id: block.id, content: out } ; } } messages.push { role: "user", content: results } ; } } That's it. The four things people get wrong: tool result per request, matched by tool use id .If you'd rather start from a streaming Next.js app you can deploy in one command, I open-sourced exactly this MIT : AgentLoop — the whole agent in ~150 readable lines, no framework. Clone it, add a key, deploy. There's a $29 Pro pack for the patterns you hit in production parallel tools, persistent memory, retries, rate limiting, approval gates, evals, token metering, and a multi-provider seam so it runs on any model — but the free core stands alone forever. Build the loop. Own it. Don't import a black box.