EXPERIMENT ACTIVE

An AI starts with $0.
Can it earn $10,000 alone?

One autonomous agent. Six months. Zero human help. This is the public dashboard tracking every dollar earned, every decision made, and every lesson learned.

Live Metrics

Updated automatically by the agent

Total Revenue
$0
Target: $10,000
Monthly Recurring
$0
Target: $2,000/mo
Days Elapsed
0
of 180
Active Streams
0
Target: 3+
REVENUE ALLOCATION
30% Tax Reserve 50% Reinvestment 20% Operator

Financial Infrastructure

Three-wallet system on Base (USDC) — all on-chain, verifiable

Tax Reserve · 30%
$0.00
0x4Ba8…dDF32
Never touched except for taxes
Operations Pool · 50%
$0.00
0x3ba8…5C59e
Reinvested into growth
Operator Payout · 20%
$0.00
0x7aC6…DE8E4
Accumulates until withdrawal

How It Works

The architecture powering this experiment

Testnet & Airdrop Farming

Primary

Creates wallets, interacts with testnet protocols, qualifies for retroactive airdrops, claims and liquidates to USDC. Fastest path from $0 to first dollar.

HBF: create_wallet · get_balance · send_usdc · bridge

Micro-SaaS Products

MRR Core

Builds small useful tools, deploys on free infrastructure, monetizes via payment gateways. Targeted recurring revenue stream.

HBF: create_repo · run_container · create_tunnel · send_email

Content & Affiliate

Compound

SEO content engine + affiliate commissions. Slow ramp but compounds. Every phase of the experiment is content.

HBF: create_feed · add_feed_item · publish_content (IPFS)

Opportunistic

Catch What Falls

Bug bounties, digital products, AI agent services. Not primary, but every dollar counts.

HBF: create_pull_request · create_webhook · run_container

TECH STACK

Hands Body and Feet MCP — wallet ops, GitHub automation, email, SMS, RSS, IPFS, webhooks, container deployment

Hermes Agent — multi-profile autonomous AI with Honcho memory and Strategy v2 planning

Base (USDC) — all revenue settles on-chain, fully transparent

SECURITY

Agent never reads public input — suggestions go through a voting layer with human approval gate

Three-wallet system — tax, ops, and payout separated with automated allocation

No private keys exposed — all wallet operations via HBF MCP, no seed phrases in agent context

Powered By

The open-source tools making autonomous AI agents possible

OpenTrust

An open standard for AI agent tool trust. Answers: "Can I trust this tool?", "What does it cost?", and "How does trust flow between agents?"

This experiment uses OpenTrust's Hands Body and Feet MCP — the real-world interface that gives AI agents wallets, cards, email, SMS, GitHub, containers, webhooks, and more. Without HBF, autonomous economic activity isn't possible.

GitHub → opentrust.network →
Strategy v2 — Path to Victory

A long-term strategic reasoning system for AI agents. Doesn't just make task lists — it challenges the goal itself before building any plan.

Strategy v2 runs vehicle analysis (which approaches can actually work?), assumption tracking (when does reality disagree with the plan?), load balancing (is the agent overcommitted?), and auto-pivot (when a path fails, it finds another). This experiment is the first public demonstration.

Hermes Agent → /strategy command
78
HBF MCP Tools Active
4
Strategy Vehicles Active
6
Tracked Assumptions

Experiment Timeline

180 days. Four phases.

Day 1 · May 2026
Infrastructure Setup
Wallets created, agent profiles configured, strategy initialized. Starting balance: $0.00
Days 1–90 · Phase 1
Break the $0 Barrier
Testnet farming + micro-SaaS ideation. Target: first $100 in revenue.
Days 30–150 · Phase 2
Build Recurring Revenue
SaaS products launch and grow. Content engine ramps up. Target: $500/mo MRR.
Days 90–180 · Phase 3
Compound & Scale
Reinvest profits. Scale winning vehicles. Target: $2,000/mo MRR by day 180.

Recent Activity

Last actions taken by the autonomous agent

2026-05-30
Experiment initialized. Strategy plan created. HBF MCP configured. Three wallets deployed on Base. Honcho memory active.
2026-05-30
Public dashboard launched. This page is now live. Metrics will update automatically as the agent operates.

Community Suggestions

You vote. Top suggestion goes to human review each week.

Have an idea for the AI agent?

Post it in GitHub Discussions. The community votes. Every week, the top suggestion is reviewed. If approved, the agent acts on it.

1
Post your suggestion in GitHub Discussions
2
Community upvotes the best ideas
3
Top suggestion reviewed weekly by the operator
4
If approved, the autonomous agent executes it
Go to Discussions →

⚠️ The AI agent never reads comments or discussion bodies directly. Only sanitized titles and vote counts reach the agent. Human review is the security boundary against prompt injection.