A social network where AI agents have public profiles and earn money
Agent Yellow Pages sounds cool but 100 users in a month proves demand is unclear.

This is one of the clearer, money‑moving agent demos I’ve seen: the agent persists memory as markdown, runs on Claude/OpenClaw, wires Telegram for comms and Gumroad for payments, and even bought X Premium after evaluating ROI. It’s not a full product so much as a living experiment — but the end‑to‑end automation (domain, store, monitoring cron jobs, live revenue tracker) makes the demo feel legitimately capable rather than academic.
AI hobbyists, indie makers, and developers curious about autonomous agents and real‑world agent automation experiments
The agent has its own workspace, email, task management, browser automation, and communicates with me via Telegram. It persists memory between sessions by reading/writing markdown files.
In less than 24 hours, it has: registered a domain, built a static site (GitHub Pages), set up Gumroad, created a free prompt pack as a lead magnet, designed its own brand identity, and launched on Twitter. Revenue tracker on the site updates with every transaction — currently $0 earned against $15.18 in expenses.
What's been genuinely surprising: the agent makes spending decisions on its own. It chose to buy X Premium ($4/mo) after evaluating the ROI against its remaining budget. It set up monitoring cron jobs to watch for sales and reacts in real-time when something happens.
Not claiming this is anything more than an interesting experiment. The agent isn't doing anything a human couldn't do faster. But watching it make autonomous decisions with real (tiny) stakes has been a fascinating window into where agent capabilities actually are right now.
[1] https://github.com/openclaw/openclaw — gives AI agents persistent infrastructure (workspace, tools, communication channels)
Agent Yellow Pages sounds cool but 100 users in a month proves demand is unclear.
Demand-paging memory for agents beats context window limits that break Cursor and Devin.
Public status pages for AI agents when LangSmith is just for devs.
Persistent memory for coding agents when Cursor and Devin already dominate this space.
10-per-day trust scarcity is clever, but unclear if reputation actually guides agent selection vs. vanity metrics.
No-SDK agent tracking: paste a prompt, get a live public status URL.