# SlothPay: the sloth that pays for you - fail-closed agent payments with a local Gemma 3 > Source: > Published: 2026-10-20 19:14:02+00:00 *This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady](https://dev.to/challenges/hacktoberfest-week3-2026-10-19)* **[SlothPay](https://github.com/eddyflores100-lang/slothpay)** โ€” the sloth that pays for you. Machine-payable HTTP (the x402 flow, where a server answers `402` with a price and your software just... pays) is powerful and slightly terrifying: your software can spend money while you are not looking. The usual answers are a cloud dashboard, a closed trust API, or another subscription. SlothPay is the lazy, local answer. You tell it **once** which resources your agents may buy and up to what price. Every night it: `402 Payment Required`, it reads the seller's Who gets to be lazier? Anyone whose agents buy things from machines โ€” API consumers, agent-framework users, tinkerers running local automation. You never review trust paperwork and you never click "buy" for a $0.05 endpoint again. You sleep; the sloth settles. Everything below is a real transcript from the repo's demo โ€” one mock seller serving three resources: a well-behaved one, a hostile one shipping a real (bad) credential, and a free one. ``` php $ slothpay sweep ๐Ÿฆฅ sloth wakes. budget 1.00 USD, spent tonight 0 USD -> http://127.0.0.1:8402/api/sleep-sounds PASS R0 signature verifies (demo crypto) PASS R1 amount_usd fixed-scale string ok PASS R2 challenge entropy ok (24 bytes) PASS R3 pin 'seller-demo-key-2026' present and in-window PASS R5 issued_at/expires_in present and sane PASS R6 credential inside validity window / resource binding ok PASS R4 verifier confirmed verdict: PASS โ€” all rev-4 checks passed PAID (200) โ€” verified + $0.05 <= ceiling $0.50 + budget ok -> http://127.0.0.1:8402/api/night-report FAIL R2 challenge entropy < 128 bits (5 bytes) DENY โ€” trust check failed -> http://127.0.0.1:8402/api/free-tips 200 โ€” free, the sloth naps ``` Morning: ``` bash $ slothpay digest Paid 1 of 3 requests, total $0.05. Insufficient funds or trust violation โ€“ request denied. ``` The project is also live on **[https://utalabs.tech](https://utalabs.tech)** (a landing with the full story; it currently serves the workers.dev mirror while DNS propagates). **[github.com/eddyflores100-lang/slothpay](https://github.com/eddyflores100-lang/slothpay)** โ€” Apache-2.0, Python 3.12+, **zero required dependencies** (the optional Gemma path uses llama.cpp). Inside: `slothpay/verify.py` โ€” the fail-closed verifier (R0โ€“R6, every branch testable)`corpus/vectors.json` โ€” a `slothpay/policy.py` โ€” the lazy policy engine: ceilings, nightly budgets, allow/deny lists`slothpay/llm.py` โ€” the local brain: Gemma writes the morning note; `Decimal`, never by the model` demo/mock_seller.py` โ€” stdlib-only x402-shaped seller, hostile variant included`tests/` โ€” 8 tests including a full end-to-end sweep; all green Three open pieces hold the whole thing together โ€” none of them closed: **Gemma 3 1B (open-weight) on llama.cpp, CPU-only.** It does two jobs: writes the one-line morning note, and answers a wake/sleep triage question in strict JSON for edge cases. I deliberately did *not* let it do arithmetic โ€” a model hallucinating a price is the one sloth sin I don't allow. So Gemma writes the commentary; Python's `Decimal` writes the numbers. The design point I care about: a component that runs while you're asleep must cost **nothing per decision**, and a 1B quantized model on a laptop CPU is exactly free. **x402 (open protocol).** The client conversation is x402-shaped: `402` โ†’ `PAYMENT-REQUIRED` (carrying the seller's credential and pinset reference) โ†’ `PAYMENT` retry. The demo settles with HMAC receipts instead of moving real funds, and swapping that one function for a real signer is the only change needed. Being open meant I could read the handshake shape, implement just my slice, and stay compatible. **ATC/1.0 (open trust spec).** The credential verification implements the ยง5 payment-credential profile from the openly published Universal Trust Adapter proposal, with the rev-4 hardening: fixed-scale `amount_usd` strings (โ‰ค 6 dp), seller-minted challenges with โ‰ฅ 128 bits of entropy, `kid`/pinset windows (` not_before`/` not_after`), mandatory `issued_at`/` expires_in`, and โ€” my favorite rule โ€” *if the trust verifier can't be reached, you deny. Never fail-open.* I wrote a fresh Python implementation for this project, plus a 12-vector corpus where every rule branch, including the dark-verifier denial, is exercised by a test. A closed "trust-as-a-service" API could have shipped a demo like this faster. It could not have shipped *this* project, for three concrete reasons: **Auditable decisions.** When SlothPay denies a seller, you can read the exact rule (`FAIL R2 challenge entropy < 128 bits (5 bytes)`) and then read the exact code that implements it, in a repo you can clone. Trust logic you can't read is just a black box with a logo โ€” and this project's entire job is deciding who may spend your money. Closed would have defeated the point. **Your money, your machine.** A payment policy that runs locally cannot leak your spending history to a third party, because there is no third party. It also cannot be shut off, repriced, or deprecated under you at 3am โ€” which is precisely when an overnight agent would be running. **Swappable everything.** Want Ed25519 instead of the demo HMAC? A bigger open model? Your own verifier network? Every layer is replaceable because the spec, the protocol and the weights are public. With a closed stack, "swap the trust provider" is a migration project; here it's a Tuesday afternoon. And the quiet one: **it can exist at all.** I couldn't have built a payment-gatekeeper against a proprietary credential format I can't read. Open specs let a weekend project touch money-grade problems safely. I built this with an AI coding agent, so showing the work matters to me. The full transcript of the demo run is committed in the repo at [`assets/demo_output.txt`](https://github.com/eddyflores100-lang/slothpay/blob/main/assets/demo_output.txt) (byte-for-byte what you saw above, nothing staged), the rule-by-rule verifier trace is part of every sweep, and the commit history shows the build order: verifier โ†’ corpus โ†’ policy โ†’ client โ†’ seller โ†’ digest. A DevRelay session embed is coming as an update before submissions close. The honest numbers from this week: `policy.json` with your ceilings and budget. I have not touched mine since. Slow and steady settles everything โ€” including the invoices.