Claude Code + Paperclip Just Destroyed OpenClaw
The video demonstrates Paperclip, an open-source tool for creating AI-only companies with multiple autonomous agents. The creator shows how to set up a complete organization with a CEO, engineers, and other specialized agents that can hire each other, complete tasks, and run continuously without human intervention.
Summary
The video begins with the creator showing his mission control center running seven AI agents with five active tasks for his existing AI automation business. He explains that Paperclip allows users to create companies with no human employees, where AI agents can hire other agents, set goals, and automate entire business operations. The tool launched in early March and gained over 36,000 GitHub stars in just a few weeks, addressing the pain point of managing multiple Claude Code sessions and terminals simultaneously.
The creator demonstrates setting up a new company called 'Proof Shot' from scratch, which aims to provide AI-cleaned customer testimonials. He walks through the onboarding process, starting with creating a CEO agent using Claude Sonnet, setting the first task to hire an engineer, and configuring agent instructions including heartbeat files, soul files, and tools files. The system includes a ticketing system for tracking all conversations and tasks, with an inbox for approvals and comments.
Key features highlighted include heartbeats that keep agents running on schedules (every 4-12 hours), budget controls per agent, the ability to run multiple companies within one dashboard, and integration with GitHub repositories. The creator shows how agents can be assigned different models and providers, and demonstrates the skills marketplace (skills.sh) where users can add capabilities like front-end design and web design guidelines to their agents. He also covers the beta routines feature for recurring workflows and the ability to import pre-built company templates with complete teams of specialized agents. The video concludes with discussion of environment variables and API key management, emphasizing how Claude Code can help optimize Paperclip setups.
About this episode
Full courses + unlimited support: https://www.skool.com/ai-automation-society-plus/about All my FREE resources: https://www.skool.com/ai-automation-society/about Apply for my YT podcast: https://podcast.nateherk.com/apply Work with me: https://uppitai.com/ My Tools💻 14 day FREE n8n trial: https://n8n.partnerlinks.io/22crlu8afq5r Code NATEHERK to Self-Host Claude Code for 10% off (annual plan): https://www.hostinger.com/vps/claude-code-hosting Voice to text: https://ref.wisprflow.ai/nateherk Try Paperclip: https://paperclip.ing/ In this video I walk through Paperclip, a free open-source tool that lets you build and run an entire company with AI agents. I set up a brand new company from scratch, show how the CEO agent hires engineers and delegates tasks, and break down how heartbeats, skills, routines, and budgets all work together. Whether you want to start a fully AI-run company or just automate a piece of your existing business, this covers everything you need to get going. Sponsorship Inquiries: 📧 [email protected] TIMESTAMPS 0:00 My AI Company Dashboard 1:38 What Is Paperclip? 3:48 Free Resource Guide 4:05 Why Paperclip Blew Up 5:07 How to Install & Get Started 5:54 Building a Company From Scratch 8:00 Agent Configuration & Heartbeats 11:03 Setting Up Projects & Hiring QA 14:32 Adding Skills 16:08 Routines 17:34 Importing Company Templates 19:13 Secrets & API Keys With Claude Code 20:07 Final Thoughts
Key Insights
- One of Paperclip's founders explained the pain point that led to the tool's creation: developers were running 20 different terminals and 20 different Claude Code sessions daily, losing visibility and forgetting which agents were doing what tasks
- Paperclip gained explosive growth with over 36,000 GitHub stars in just 3 weeks since launching in early March, indicating strong demand for AI agent orchestration tools
- Heartbeats are crucial for agent proactivity - agents wake up on schedules with fresh context and memory, requiring them to check their work and get familiarized with their environment each time, which is why this feature made OpenClaw blow up
- The creator advocates setting up a dedicated Claude Code project to understand Paperclip's architecture, API, and configurations, arguing that having an AI assistant that knows everything about the tool helps with setup, monitoring, and troubleshooting
- Companies can 'acquire' other AI companies by importing pre-built templates from Paperclip's catalog, with some templates containing up to 48 specialized agents with specific knowledge and skills already configured
Topics
Transcript
[0:00] What you're looking at right here is my mission control center. You can see I've got seven agents enabled. I've got five tasks in progress. You can see what all of them are doing right here. We can see all of the recent activity and all the tasks. And in my inbox, I can see what is needed to be approved by me or what I have to look at. Down here, you can see the seven different agents we have. And you can see what they're actually working on. So, right now, the AIS marketer is running. And for each of our different agents, we can control their instructions, their skills, their configuration, everything. So now in a…
Full transcript available for MurmurCast members
Sign Up to AccessMore from Nate Herk | AI Automation
Fable 5 + Karpathy’s LLM Wiki is Basically Cheating
The video demonstrates how to build a personal LLM-powered knowledge base using Obsidian and Claude, inspired by Andrej Karpathy's approach. By ingesting various data sources (YouTube transcripts, PDFs, URLs) into an interconnected wiki structure, users can create a 'second brain' that helps AI agents understand context and relationships across knowledge domains.
How Claude is Creating a New Generation of Millionaires
Claude, an AI built by Anthropic, is enabling non-technical founders to build million-dollar software companies by automating development work. The transcript outlines why Claude is outpacing competitors, provides real examples like Vulcan, and offers a four-step framework for anyone to start building with Claude today.
How Anthropic Engineers Actually Prompt Fable 5
A guide to effectively prompting Claude Fable 5, covering six key techniques including providing context/intent, using negative prompting, letting the model act once ready, verifying outputs, avoiding reasoning requests, and keeping instructions concise. The speaker emphasizes that Fable 5 is expensive and should only be used 5-15% of the time, with pricing at $10 per million input tokens and $50 per million output tokens.
Stanford's Method Turns Claude Into a PHD Level Research Team
A researcher demonstrates the STORM method from Stanford, which uses five expert perspectives (practitioner, academic, skeptic, economist, historian) to create verified research reports. The method produces 25% more organized articles than competing approaches and is packaged as a reusable Claude skill that generates HTML briefings with peer-reviewed citations.
Is Claude Mythos Coming?
A YouTuber analyzes the brief appearance of 'Claude Mythos' on Anthropic's API, arguing it signals a marketing move rather than an imminent public launch. Despite competitive pressure from OpenAI and IPO timing, the creator believes Mythos capabilities will quietly fold into future Opus models rather than release publicly under that name. Three possible scenarios are outlined ranging from a limited gated release to Mythos remaining permanently restricted to vetted security partners.