1mancompany/OneManCompany

Build Your Agent Company with OMC

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.

Related

  • Project
    alibaba/UnifiedModel

    UModel (Unified Model) is an open‑source, vendor‑neutral semantic runtime that unifies enterprise schemas, entities, and topology into a single graph. It offers a local service with a web UI, CLI, REST/OpenAPI, and generated Go/Python/Java SDKs. Agents can discover services, traverse relationships, and perform model‑guided root‑cause analysis via built‑in AgentGateway/MCP skills. Quick‑start uses `make quickstart` to launch a demo workspace; the system supports multiple GraphStore back‑ends and is licensed under Apache‑2.0.

  • Project
    Accio-org/CommerceAgentBench

    Commerce Agent Bench is an open‑source benchmark for evaluating autonomous AI agents on real‑world, multi‑step e‑commerce workflows. It provides 107 containerized tasks (CLI, browser, file, API) with mock services, deterministic or LLM‑assisted graders, and detailed metrics (pass rate, steps, time, tokens). The suite runs via the OpenClaw harness in a pinned Docker image, supports multiple model providers, and offers a reproducibility contract and leaderboard.

  • Project
    jnMetaCode/agency-orchestrator

    Agency Orchestrator is a Node‑JS tool that lets you run dozens of AI “expert” roles together. You can write a short YAML workflow or simply give a one‑sentence prompt; AO picks the right roles, builds a DAG, calls LLM providers (Claude, DeepSeek, OpenAI, etc.), runs steps in parallel, and produces a final report. It includes a web Studio UI, role libraries (267 Chinese roles + multilingual packs), support for key‑less providers, acceptance criteria, resumable runs, and integrations with coding assistants via an MCP server.

  • Project
    openchamber/openchamber

    OpenChamber is an open‑source, cross‑platform workspace that lets you run, supervise, and review AI coding agents (powered by OpenCode) from desktop, web/PWA, VS Code, or mobile. It adds persistence, multi‑model comparison, goal‑driven sessions, diff walkthroughs, GitHub PR integration, and encrypted remote access, all under an MIT licence.

  • Project
    echoVic/boss-skill

    boss‑skill is an npm‑distributed skill that equips LLM‑based coding agents with a full‑team, audit‑first workflow. It adds event‑sourced state, non‑bypassable quality gates, and replayable artifacts for each feature, turning a single coding bot into roles like PM, architect, dev, QA and DevOps. Install via `npx skills add echoVic/boss-skill` (or npm), then use slash commands such as `/boss` or `/boss:qa` to run a four‑stage pipeline that produces a `.boss/` folder containing PRDs, designs, test reports and an immutable event log. Designed for Node ≥ 20, it works across OSes and integrates with Claude Code, Codex, OpenClaw, Antigravity and Hermes. MIT‑licensed.