1mancompany/OneManCompany

What it solves

OneManCompany addresses the difficulty of managing multiple AI agents to produce professional-grade deliverables. Instead of using isolated chatbots or simple task runners, it provides a structured "agentic operating system" that mimics a corporate hierarchy, allowing a single human CEO to orchestrate a full team of specialized AI employees (HR, COO, engineers, designers) to run a business autonomously.

How it works

The system operates as a runtime that abstracts different AI backends (such as Claude Code or OpenClaw). It uses a "Vessel + Talent" architecture where the Vessel provides the execution environment (scheduling, retries, communication) and the Talent provides the specific skills and personality.

Users interact via a browser-based pixel-art office interface. A high-level request (e.g., "Build a puzzle game") is routed by an Executive Assistant, broken down into subtasks by a COO, and executed by AI employees hired from a community-verified Talent Market. These agents collaborate through multi-agent meetings, structured handoffs, and quality gates, with the human CEO providing high-level direction or granular coaching.

Who it’s for

• Solo entrepreneurs who want to scale their productivity using AI teams.
• Developers and creators looking to build complex, multi-stage products (games, software, manga) without a full human staff.
• AI agent builders who want to package their agents as "employees" for the Talent Market.

Highlights

• Corporate Simulation: Includes org charts, hiring/firing pipelines, performance reviews (PIP), and 1-on-1 coaching that permanently shapes agent behavior.
• Multi-Agent Collaboration: Agents can initiate their own meetings to align on tasks rather than just responding to the user.
• Talent Market: A community-scored marketplace to hire battle-tested AI employees instead of configuring agents from scratch.
• Product-Grade Focus: Uses enterprise-style orchestration (requirements → design → development → testing) to move beyond draft-quality outputs.
• Low Friction Setup: Can be launched with a single command (npx @1mancompany/onemancompany) without requiring manual Docker or Python configuration.