Company Manager
Model any organization as a team of LLM agents. Hire employees, write their job descriptions, assign missions — from a CEO's seat, on your own MCP infrastructure.
The Idea
An organization is a set of roles, each with a scope of responsibility, a way of working, and tools to get the job done. Company Manager takes that definition literally: every employee is an LLM agent whose behavior is entirely described by its job description — a system prompt — combined with the MCP tools it is allowed to use.
You run the company. You open the app, pick an organization, hire agents by writing their job description, activate them, and assign missions. Work is executed in real time by LLMs from the AI Hub, using MCP tools scoped to each role. You observe, pause, refine, and fire.
What an Agent Is
Each agent is a small, auditable unit of work. Its identity lives in a single row of a DuckDB table, and its behavior is defined by a handful of fields.
Job Description
The system prompt. Role, responsibilities, tone, constraints, escalation rules. The prompt is the contract between the CEO and the agent.
Allowed Tools
A filtered subset of the MCP tool catalog. A sales agent sees CRM tools, not production database write access. Least privilege by default.
LLM Backend
Any backend registered in the AI Hub: local llama.cpp, Claude, GitHub Models. Sampling parameters (temperature, top-p) are applied only when the backend supports them.
Status
Idle, Working, Paused, or Offline. Activation is a deliberate act — a hired agent is not a running agent until you flip it on.
Workers and Supervisors
Two agent types cover most organizational patterns.
Worker
Executes missions directly. Runs a ReAct loop against its allowed tools: think, call a tool, observe, iterate, produce a result. One mission at a time.
Supervisor
Orchestrates other agents. Receives a mission, decomposes it into sub-tasks, delegates each to an appropriate worker, monitors progress, synthesizes the results into a single outcome.
A Supervisor is just another agent with a specialized prompt and the ability to spawn sub-missions. Hierarchies emerge naturally: a Program Manager Supervisor can coordinate Team Lead Supervisors, each coordinating individual Workers.
How It Sits on the MCP Stack
Company Manager is not a new runtime. It is a plugin that composes existing pieces of the MCP infrastructure.
AI Hub
Single source of LLM inference. Every agent, regardless of backend, goes through the Hub — so GPU queues, rate limits, and concurrency are managed once, centrally.
RBAC
The CEO is an authenticated user. Every hire, fire, and mission start is traceable to a human identity. Agents inherit the CEO's effective permissions, filtered by their allowed tools.
MCP Tools
Every plugin already installed on the server — GitHub, Jira, accounting, data ingestion, BI — becomes a potential capability for an agent. No new integration layer.
DuckDB
Organizations, agents, missions, and every log entry live in a single embedded database. Queryable, exportable, auditable. No hidden state.
Organization Patterns
Nothing about the platform assumes a particular organizational shape. A few examples of what the same engine can model:
Multiple organizations coexist in the same installation. Agents can be duplicated across organizations (copy the role, keep the same prompt) or transferred (reassign to a new org).
Real-time Observability
Every thought, tool call, tool result, and final output is a log entry broadcast over the MCP WebSocket. The CEO UI renders them live.
Activity Feed
A streaming view of what every active agent is doing, filterable by agent or mission.
Mission Replay
Every mission is a reproducible trace. Open a completed mission and see exactly how the result was reached — thought by thought, tool call by tool call.
Org Chart
Visual hierarchy of agents and supervisor relationships, rendered with ImPlot. Click a node, jump to the agent.
Why Build This on MCP
Multi-agent platforms exist as SaaS products. Company Manager is a different proposition.
Your Infrastructure
Runs on your servers. No data leaves your perimeter unless you explicitly allow an agent to use a remote backend.
Swappable Backends
Switch an agent from Claude to a local quantized model in one click. The job description doesn't change — only the cost profile.
Composable by Design
Every MCP tool you already built is reusable. Adding a new business capability is a plugin, not a rewrite.
Audit-ready
RBAC on the CEO side, per-agent tool filtering, full DuckDB trail on the storage side. Every action is attributable.