What is a one person company?

A one person company is a business owned and operated by a single founder. Everything a traditional team would handle — engineering, design, research, marketing, support — is carried by that one person, or delegated to software. Autonomous AI agents now do real work end to end, so a one-person company can take on scope that used to require a payroll.

Is a one person company the same as a one man company?

Yes — 'one person company', 'one-person company', and 'one man company' all describe a business with a single human owner-operator. In some jurisdictions (India, for example) 'One Person Company' is also a specific legal structure for a single-shareholder private limited company.

How many AI agents does a one person company need?

Most solo founders start with two or three: one for the core craft, one for research, one for writing. Add agents as bottlenecks appear rather than staffing up front.

What does it cost to staff a one person company with AI agents?

Most agents in the marketplace have a $0 hiring fee. Paid agents charge a one-time fee for the config package, with no subscription. Your running cost is the model tokens the agent consumes.

Can a one person company handle client work?

That is the common case. Agents cover the delivery surface — code, docs, QA, reporting — while the founder keeps the client relationship and the final judgement calls.

Yesterday in AI: 01 October 2026 — Claude Mods Rewrite the Agent From Inside

Claude Code ships mods in v2.1.287, giving TypeScript plugins control over prompts, tools, and the UI; Cloudflare open-sources Clef to challenge TypeSafe's Jev; OpenRig gains 781 stars for coordinating Claude and Codex as one team.

By OMC Editorial on 2026-10-02

TL;DR — Anthropic ships mods in Claude Code v2.1.287, giving TypeScript plugins full control over prompts, tools, and the UI; Cloudflare open-sources Clef and Clef-flash to challenge TypeSafe's Jev in agentic decision-making; OpenRig gains 781 stars in 24 hours for running Claude Code and Codex as one coordinated team. --- 1️⃣ Claude Code v2.1.287 Ships Mods — TypeScript Now Controls the Agent - What: Anthropic shipped mods in Claude Code v2.1.287: small TypeScript functions installable via /plugin that intercept and rewrite every layer of the agent - Why it matters: Developers can now enforce security policies, swap UI elements, and gate permissions without forking internals — the agent is fully extensible from the outside - Key number: 4 built-in mods diff, agents-md, sec-default, telemetry ship with public source in anthropics/claude-code as ready templates Claude Code v2.1.287 arrived on October 1 with "mods" — a new extensibility layer between user input and the model. A mod can rewrite a prompt before it reaches the model, intercept and block tool calls, approve or deny permission requests, and redact secrets from tool output. Mods can also redraw parts of the Claude Code UI and add buttons and inputs — and multiple mods can compose, so one mod can react to another's events. Mods install via /plugin in the CLI or desktop app; a developer can write one with a few lines of TypeScript or ask Claude to generate it. Four Anthropic-authored mods — diff, agents-md, sec-default, and telemetry — have open-sourced code in the main claude-code repo as starter templates. Unlike earlier plugin systems that appended new tools or commands, mods can intercept the agent's core decision loop, making them well-suited for enterprise security rules, personal workflow patches, and shareable plugin libraries. 📎 Anthropic Bloghttps://claude.com/blog/claude-code-mods · ClaudeDevs on Xhttps://x.com/ClaudeDevs/status/2105721434807083061 · RuntimeWirehttps://runtimewire.com/arti

More agent news