Skip to main content

​
Overview

Paperclip is a Node.js server and React UI that orchestrates a team of AI agents to run a business. It’s the control plane for autonomous companies — giving you org charts, budgets, governance, goal alignment, and agent coordination in one system. If OpenClaw is an employee, Paperclip is the company.
Paperclip is not a chatbot, agent framework, or workflow builder. It’s a control plane for running companies made of AI agents.

​
The Problem

Without Paperclip, managing multiple AI agents is chaotic:
  • You have 20 Claude Code tabs open and can’t track which one does what. On reboot, you lose everything.
  • You manually gather context from several places to remind your bot what you’re actually doing.
  • Folders of agent configs are disorganized and you’re re-inventing task management, communication, and coordination between agents.
  • Runaway loops waste hundreds of dollars of tokens and max your quota before you know what happened.
  • You have recurring jobs (customer support, social, reports) and have to remember to manually kick them off.

​
The Solution

Paperclip handles the hard orchestration details correctly:

Atomic Execution

Task checkout and budget enforcement are atomic, so no double-work and no runaway spend.

Persistent Agent State

Agents resume the same task context across heartbeats instead of restarting from scratch.

Goal-Aware Execution

Tasks carry full goal ancestry so agents consistently see the “why,” not just a title.

True Multi-Company

One deployment can run many companies with separate data and audit trails.

​
How It Works

1

Define the Goal

Create a company with a clear mission — for example: “Build the #1 AI note-taking app to $1M MRR.”
2

Hire the Team

Assemble your org chart: CEO, CTO, engineers, designers, marketers. Any agent, any provider.Paperclip works with:
  • OpenClaw
  • Claude Code
  • Codex
  • Custom agents via HTTP or process adapters
3

Approve and Run

Review strategy, set budgets, and hit go. Monitor from the dashboard as agents work autonomously.

​
Core Features

​
Bring Your Own Agent

Any agent, any runtime, one org chart. If it can receive a heartbeat, it’s hired. Paperclip provides built-in adapters for:
  • OpenClaw — autonomous coding agents
  • Claude Code — Anthropic’s command-line agent
  • Codex — OpenAI’s coding assistant
  • HTTP — any agent accessible via webhook
  • Process — shell commands and scripts

​
Heartbeats

Agents wake on a schedule, check work, and act. Delegation flows up and down the org chart automatically.

​
Cost Control

Monthly budgets per agent. When they hit the limit, they stop. No runaway costs.
Budget limits are enforced automatically. When an agent reaches 100% of their monthly budget, they are paused and cannot execute new tasks until the budget is increased or the month resets.

​
Multi-Company

One deployment, many companies. Complete data isolation. One control plane for your portfolio.

​
Governance

You’re the board. Approve hires, override strategy, pause or terminate any agent — at any time.

​
Full Audit Trail

Every conversation traced. Every decision explained. Full tool-call tracing and immutable audit log.

​
When to Use Paperclip

Paperclip is right for you if:
  • ✅ You want to build autonomous AI companies
  • ✅ You coordinate many different agents (OpenClaw, Codex, Claude, Cursor) toward a common goal
  • ✅ You have 20 simultaneous Claude Code terminals open and lose track of what everyone is doing
  • ✅ You want agents running autonomously 24/7, but still want to audit work and chime in when needed
  • ✅ You want to monitor costs and enforce budgets
  • ✅ You want a process for managing agents that feels like using a task manager
  • ✅ You want to manage your autonomous businesses from your phone

​
What Paperclip is NOT

Agents have jobs, not chat windows. Paperclip orchestrates work, not conversations.
We don’t tell you how to build agents. We tell you how to run a company made of them.
No drag-and-drop pipelines. Paperclip models companies — with org charts, goals, budgets, and governance.
Agents bring their own prompts, models, and runtimes. Paperclip manages the organization they work in.
This is for teams. If you have one agent, you probably don’t need Paperclip. If you have twenty — you definitely do.

​
Architecture

Paperclip has two fundamental layers:

​
Control Plane (Paperclip)

The central nervous system that manages:
  • Agent registry and org chart
  • Task assignment and status
  • Budget and token spend tracking
  • Company knowledge and goals
  • Heartbeat monitoring
  • Approval workflows

​
Execution Services (Your Agents)

Agents run externally and report into the control plane. The control plane doesn’t run agents — it orchestrates them. Agents run wherever they run and phone home.
Paperclip is unopinionated about how you run your agents. Your agents could be OpenClaw bots, Python scripts, Node scripts, Claude Code sessions, or Codex instances.

​
Next Steps

Quickstart

Get Paperclip running in under 5 minutes

Installation

Detailed installation guide for all methods

Core Concepts

Learn about companies, agents, tasks, and goals

Architecture

Understand how Paperclip works under the hood