AI ToolsKR

Paperclip — The Open-Source Framework for Running AI Agent Companies

30K GitHub stars in 3 weeks. An open-source multi-agent orchestration platform with org charts, budgets, and governance. Heartbeat scheduling, per-agent monthly budgets, and company templates.

Paperclip — The Open-Source Framework for Running AI Agent Companies

Paperclip: The Open-Source Framework for Running AI Agent Companies

Using one AI agent well is table stakes. Paperclip takes it further — it lets you organize multiple agents into a company with org charts, budgets, and governance. Launched in March 2026, it hit 30K GitHub stars in three weeks and now sits at 43K+.

"If OpenClaw is an employee, Paperclip is the company."

Core Concept: Orchestration ≠ Agent Framework

Paperclip is fundamentally different from CrewAI or AutoGen:

CrewAI / AutoGenPaperclip
MetaphorTeam / PipelineCompany
StructureAgent message passingOrg charts, budgets, governance
Agent runtimeBuilt-in frameworkBYOA (Bring Your Own Agent)
ExecutionCalled from codeHeartbeat schedule (4/8/12 hours)
Cost controlNonePer-agent monthly budgets + auto-pause

Paperclip doesn't build agents. It takes existing agents — Claude Code, OpenClaw, Codex, Python scripts, HTTP webhooks — and organizes them into a functioning company.

Architecture: Like a Real Company

Org Chart

Board of Directors (You)
└── CEO Agent
    ├── CTO Agent
    │   ├── Backend Engineer
    │   └── QA Engineer
    ├── Marketing Director
    │   └── Copywriter
    └── Research Specialist
  • Goals flow top-down (CEO → department heads → workers)
  • Results flow bottom-up
  • Each agent can spawn sub-agents (recursive structure)
  • You're the Board — approve hires, override strategy, pause/terminate any agent

Four Identity Files: Solving the Memento Man Problem

AI agents wake up with zero memory of who they are or what they were doing. Paperclip solves this with four files:

FilePurpose
AGENTS.mdCore identity — role, goals, memory protocols
HEARTBEAT.mdExecution checklist — steps to follow on every wake-up
SOUL.mdPersona — decision-making style, priorities
TOOLS.mdTools — available tools and usage protocols

The Heartbeat System

Agents don't run continuously. They wake up on schedule — every 4, 8, or 12 hours:

  1. Confirm identity via API
  2. Check inbox for assigned tasks and @-mentions
  3. Check out work atomically (prevents duplicate processing)
  4. Execute tasks
  5. Store memory for next cycle
  6. Report progress
  7. Exit cleanly

Event-based triggers also exist — direct task assignments or @-mentions wake agents immediately.

Cost Control: This Is the Killer Feature

The biggest problem with AI agents in 2026 isn't failure — it's success. Agents running autonomously can rack up tens of thousands of dollars in API costs overnight.

Paperclip's three-tier budget system:

TierThresholdAction
Soft warning80%Alert sent, agent continues
Hard stop100%Agent auto-paused
Circuit breakerAbnormal patternSystem detects spending anomalies and blocks

Example per-agent monthly budgets:

  • CEO: $50/month
  • Researcher: $100/month
  • Copywriter: $75/month
  • QA: $40/month

With a Claude Code Max subscription ($200/month), the dashboard shows $0 since you're using subscription allocation rather than per-token credits.

Quick Start: A "Company" in 10 Minutes

Install

bash
npx paperclipai onboard --yes

This single command:

  • Downloads the Paperclip CLI
  • Creates an embedded PostgreSQL database (~/.paperclip/instances/default/)
  • Generates configuration files
  • Installs skills to ~/.claude/skills/
  • Starts the server at http://localhost:3100

Requirements: Node.js 20+, pnpm 9.15+

Or Clone Directly

bash
git clone https://github.com/paperclipai/paperclip.git
cd paperclip
pnpm install
pnpm dev

Create a Company (5 Steps)

  1. Enter company name + mission in the dashboard
  2. Create a CEO agent (Claude Code or your preferred runtime)
  3. Assign the first task: "Build the team and create a strategy"
  4. CEO submits hire requests → Board (you) approves
  5. Organization assembled, autonomous operation begins

Real Example: LeadForge (AI Lead Generation)

From Paperclip's official tutorial:

Mission: Identify B2B prospects, craft personalized outreach sequences, and deliver qualified leads at scale.

Organization:

Board (You)
└── CEO (Claude Opus 4.6, $50/mo)
    ├── Lead Research Specialist (Sonnet 4.6, $100/mo)
    ├── Outreach Copywriter (Sonnet 4.6, $75/mo)
    └── QA Specialist (Sonnet 4.6, $40/mo)

Automated Routines:

  • Daily 10 AM: QA reviews past 24h leads + accuracy verification + report
  • Daily 8 AM: Copywriter drafts outreach sequences
  • Monday 9 AM: CEO conducts weekly strategy review

Workflow Cascade:

  1. You create a research issue
  2. CEO decomposes and assigns to Researcher
  3. Researcher completes → @-mentions Copywriter
  4. Copywriter drafts → @-mentions QA
  5. QA approves or sends back with feedback

This entire process runs autonomously across multiple heartbeat cycles.

Skills and Company Templates

Skills

Skills are markdown instruction files that teach agents specific processes. Add them via GitHub URLs for automatic updates.

You can apply skills company-wide or to specific agents only.

Caution: Third-party skill security is not guaranteed. Platforms like skills.sh provide security audit badges, but nothing is 100% safe.

Company Templates

Import pre-built organizational structures from github.com/paperclipai/companies:

TemplateComposition
GStackCTO, QA engineer, release engineer
Agency Agents100+ personas
Game StudioCreative director, producer, technical director
Scientific ResearchSpecialized knowledge agents

Honest Limitations

1. "Zero-Human Company" Is Still Aspirational

Despite the marketing, no documented examples of companies actually running on Paperclip alone exist yet. Business, legal, and financial decisions still need humans.

2. Costs Add Up

Multi-agent sessions consume tokens fast. Claude Code Max ($200/month) is practically required. Running multiple agents on API credits gets expensive quickly.

3. Technical Barrier

CLI, environment variables, pnpm — this is not a no-code experience. Non-developers will struggle with setup.

4. Output Variability

Agent quality depends on the underlying model. Code agents work well, but marketing or strategy agents can be inconsistent.

Who Should Use This?

Good fit:

  • Developers experimenting with multi-agent orchestration
  • Teams needing AI agent cost management
  • Startups wanting to automate repetitive work with agent teams

Not a good fit:

  • Non-developers wanting no-code solutions
  • Tasks where a single agent is sufficient
  • Enterprises needing production-level stability (still early stage)

Conclusion

Paperclip addresses the next question of the AI agent era:

One agent works great. But how do you organize, manage, and control costs across many?

Org charts, budget management, governance, audit logs — Paperclip is the first to offer all of this as open source. It crossed 30K stars in three weeks because this question is that urgent.

"Zero-human companies" are still far off. But as a starting point for understanding multi-agent orchestration patterns, Paperclip delivers. Its cost control system alone tackles the most pressing real-world problem of running AI agents in 2026.

References

🔒

Sign in to continue reading

Create a free account to access the full content.

Related Posts