Experiment: Paperclip
Paperclip is not my project. It is an open-source orchestration platform, built by others, for running 'zero-human companies': you define a business goal, create agents with roles like CEO, engineers, marketers and QA, set budgets, and let them collaborate through a Node.js backend and a React dashboard. I explored it to understand how role-based multi-agent setups divide work, and where budgets and governance fit in. It is listed here as an experiment with someone else's tool, not as something I built.
Built in public to learn something or prove a pattern. Some are published packages, some are demos that live on this site.
- ▸Understanding how role-based agents divide and hand off work
- ▸Seeing where budgets and governance controls constrain autonomous agents
- ▸Explored its role, budget and governance model
- ▸Compared it with the single-agent and workflow patterns used elsewhere on this site
A first-hand look at how a role-based multi-agent platform is structured
JobJam.io — AI Job Search & Application Platform
AI-powered job search platform: discover roles, evaluate fit, tailor applications, and close skill gaps. One-time pricing, no subscriptions.
Fathohm — Comprehension-Debt System of Record
See how much of your codebase no human understands. A treemap of your repo colored by human comprehension score, with a tracked, assignable metric for 'who understands what' in an AI-native codebase.
Grenz — Firewall for AI Agents
A local firewall for AI agents: scoped, revocable, observable permissions instead of your full GitHub token. Deny-by-default, MIT licensed, live at grenz.dev.