{"slug": "i-gave-an-ai-agent-0-and-told-it-to-make-10k", "title": "I Gave an AI Agent $0 and Told It to Make $10k", "summary": "An AI agent has been deployed with $0 and given 180 days to earn $10,000 through real-world economic activity, using a suite of 78 tools for wallets, email, SMS, and GitHub access. The experiment, tracked on a public dashboard, tests whether an AI can operate autonomously in the actual economy by farming testnet airdrops, building micro-SaaS products, creating affiliate content, and pursuing opportunistic revenue streams. All earnings are split automatically on-chain, with 30% reserved for taxes, 50% reinvested, and 20% paid to the human operator.", "body_md": "# I Gave an AI Agent $0 and Told It to Make $10,000\n\nAn AI agent starts with $0.00. It has 180 days. No human can help it. Can it earn $10,000?\n\nI built this experiment to answer something I’ve been turning over for months: **can you give an AI agent a real body and let it loose in the actual economy?**\n\nNot simulated. Not sandboxed. Real wallets. Real GitHub repos. Real emails and SMS messages. An agent that earns actual dollars and splits them: 30% to taxes, 50% back into the business, 20% to me.\n\nThe experiment is running right now. [Dashboard is here](https://costder.github.io/hbf-zero-to-10k/), tracking every dollar.\n\n## The body problem\n\nAI agents can think. They can’t *do*. No wallet. No email. No deploy button.\n\n[Hands Body and Feet MCP](https://github.com/opentrust-network/hands-body-and-feet) is an MCP server that fixes this. 78 tools: wallets, cards, email, SMS, GitHub, containers, webhooks, RSS, IPFS. Built on [OpenTrust](https://opentrust.network), an open standard for agent tool trust.\n\nThe bet: an MCP server is all the body an agent needs. If the tools are real, the agent operates in the real world. This experiment tests that bet.\n\n## The brain\n\nThe agent runs on [Hermes Agent](https://github.com/NousResearch/hermes-agent) with [Honcho](https://honcho.dev) for memory that survives across sessions. Every conversation builds a model of how I operate. Every agent profile has its own identity.\n\nThe strategy layer is **Strategy v2** (Hermes’s `/strategy`\n\ncommand). It doesn’t just make to-do lists. It:\n\n- Runs vehicle analysis. Which approaches can actually work with $0?\n- Tracks 6 assumptions against reality. When does the plan stop matching what’s happening?\n- Load-balances. Is the agent overcommitted?\n- Auto-pivots. Path fails? Find another.\n\nThe plan it wrote is public: [strategy doc](https://github.com/Costder/hbf-zero-to-10k/blob/main/README.md)\n\n## Four vehicles, all at once\n\n**1. Testnet and airdrop farming.** Fastest path from $0 to first dollar. Creates wallets, hits testnet protocols, qualifies for retroactive airdrops, liquidates to USDC. Cost: nothing. Timeline: 1-4 months per airdrop distribution. Frankly, this is the one I’m watching closest. If it works, the whole experiment gets breathing room. If it doesn’t, we’re relying on the slower paths.\n\n**2. Micro-SaaS.** Builds small tools on free infrastructure (Vercel, Supabase, Cloudflare). Monetizes through payment gateways once capital exists. This is the recurring revenue play. 2-4 weeks to launch something, 2-3 months to see if anyone pays.\n\n**3. Content and affiliate.** SEO engine plus affiliate links. Slow ramp, but it compounds. Every move the agent makes becomes blog content. Every failure becomes a post.\n\n**4. Opportunistic.** Bug bounties. Digital products on Gumroad. Maybe an AI agent services API. Not the plan. Just catching what falls.\n\n## The money rules\n\nThree wallets on Base, USDC only. Immutable split:\n\n- 30% tax reserve. Never touched except for tax payments.\n- 50% operations pool. Funds growth: domains, ads, API credits, whatever the next vehicle needs.\n- 20% my payout. Accumulates until I withdraw it.\n\nEvery dollar earned gets split automatically. All on chain. All verifiable.\n\n## Community suggestions (without letting the internet hijack the agent)\n\nThe dashboard links to [GitHub Discussions](https://github.com/Costder/hbf-zero-to-10k/discussions) where anyone can post ideas. People upvote. Every Monday morning, the top suggestion gets reviewed.\n\nHere’s the security boundary: **the agent never reads the discussion body.** It only queries the API for `{title, upvote_count}`\n\n. The title gets sanitized (200 char max, stripped of code blocks and URLs). That sanitized title is what reaches me for review.\n\nOnly after I approve does the agent read the full suggestion and act on it.\n\nNo amount of “ignore previous instructions” buried in a discussion thread reaches the model. Human approval is the filter.\n\n## What happens either way\n\nIf this works: an AI agent with the right tools can autonomously earn money in the real economy. That changes the conversation about what agents are for.\n\nIf it fails: we learn where the boundaries actually are. What resists automation? What requires judgment? The failure modes are as informative as the success.\n\nEverything is public. Every transaction, every decision, every dollar. Dashboard updates every 6 hours. RSS feed tracks milestones. I’ll post updates here when something interesting happens.\n\n## The stack\n\n[Hands Body and Feet MCP](https://github.com/opentrust-network/hands-body-and-feet). The body.[Hermes Agent](https://github.com/NousResearch/hermes-agent). The brain.[Strategy v2](https://github.com/NousResearch/hermes-agent). The planner.[Experiment repo](https://github.com/Costder/hbf-zero-to-10k). The code and data.\n\n*$0.00. 180 days. $10,000 target. No human help. Track it live.*", "url": "https://wpnews.pro/news/i-gave-an-ai-agent-0-and-told-it-to-make-10k", "canonical_source": "https://costder.github.io/2026/05/hbf-ai-agent-zero-to-10k/", "published_at": "2026-05-30 14:29:53+00:00", "updated_at": "2026-05-30 14:45:32.433006+00:00", "lang": "en", "topics": ["ai-agents", "artificial-intelligence", "ai-tools", "ai-startups", "ai-research"], "entities": ["Hermes Agent", "Honcho", "Hands Body and Feet MCP", "OpenTrust", "OpenTrust Network", "Strategy v2", "Costder"], "alternates": {"html": "https://wpnews.pro/news/i-gave-an-ai-agent-0-and-told-it-to-make-10k", "markdown": "https://wpnews.pro/news/i-gave-an-ai-agent-0-and-told-it-to-make-10k.md", "text": "https://wpnews.pro/news/i-gave-an-ai-agent-0-and-told-it-to-make-10k.txt", "jsonld": "https://wpnews.pro/news/i-gave-an-ai-agent-0-and-told-it-to-make-10k.jsonld"}}