Paperclip: Hire AI Agents Like Employees (Live Demo)

1mo ago

I sit down with Dotta, the pseudonymous co-founder of Paperclip, the open-source agent orchestrator that exploded to 30,000 GitHub stars in under three weeks. We walk through a live demo where I pick a startup idea from my idea browser and we spin up a full AI-agent company in real time — hiring a CEO, founding engineer, QA agent, video editor, and content strategist inside Paperclip. Dotta shares practical tips on agent configuration, memory systems, skill installation, and the "Memento Man" mental model for keeping agents on track. The conversation covers everything from token spend management and agentic design patterns to the future of importable, shareable companies and the upcoming Maximizer Mode. Skills to build your agent team: https://startup-ideas-pod.link/skill-suite Timestamps: 00:00 Intro 02:32 What is Paperclip 04:21 Choosing a Startup Idea for the Demo 05:48 Setting Up your agents 07:51 Hiring Your First Agent and Creating a Plan 12:39 Agent Configuration and Persona Setup 17:08 Skills: Installing and Managing Agent Capabilities 21:02 How to Get Top-Quality Output from Agents 24:05 Token Spend Tracking and Subscription Usage 25:49 Agentic Design Patterns and QA Loops 29:05 Taste and Values: What AI Still Cannot Do 30:09 How Many Agents Run the Paperclip Project 32:32 Routines: Automating Recurring Agent Tasks 36:36 Who Is Using Paperclip Today 38:57 Shareable and Importable Companies 42:49 Maximizer Mode and What's Next 44:29 Did Dotta Expect It to Go This Viral? Key Points * Paperclip is a bring-your-own-bot orchestrator: it works with Claude Code, Codex, OpenCode, and any model on OpenRouter, so you are not locked into a single provider. * AI agents are "Memento Man" — they wake up capable but with zero memory, so you need heartbeat checklists, persona prompts, and written context to keep them effective. * The biggest lever for quality output is encoding your own taste and values into agent skills and brand guides, because AI can do everything except know what you actually want. * Agentic design patterns like engineer-to-QA review loops matter more than one-shotting an entire startup; structure prevents compounding errors. * Paperclip tracks every token spent and every task completed, solving the problem of running dozens of agent windows with zero accountability. * Importable, shareable company templates (like Gary Tan's G-Stack or a full game studio) point toward a future where you "aqua-hire" proven agent teams instead of building from scratch. Section Summaries 1. What Paperclip Is and Why It Exists Dotta built Paperclip because he was running 20–30 Claude Code windows at once and could not remember what any of them were doing. Paperclip sits between fully autonomous tools like Pulse and manual coding assistants, giving you a dashboard to define business goals, hire agents, approve work, and track spend — all in one place. 2. Agent Configuration and the Memento Man Model Dotta compares AI agents to the protagonist of the movie Memento: they are highly capable but have zero persistent memory. The solution is a heartbeat checklist that tells each agent who it is, what plan to read, which assignments to check, and how to store memory using a file-based Para system. When agents make mistakes, you add rules directly to their persona prompts. 3. Skills, Security, and Quality Control Skills from repositories like skills.sh extend what agents can do — for example, installing the Remotion skill so a video editor agent can produce animated content. Security is a real concern with third-party skills; badges and GitHub star counts offer directional trust signals but nothing is fully solved. Getting top-quality output still requires you to supply context, brand guides, and reference material. 4. Taste Is the Last Human Moat The frontier models still lack personal taste. The real secret sauce is translating your own values — design sensibility, success criteria, brand voice — into written instructions your