About 0200project

We build tools agents can trust.

Autonomous software needs to call something, get an answer, and act on it, with no human reading the output first. That only works if the tool behaves identically every time, costs a knowable amount, and says what it could not determine.

How we build

Three properties, chosen for how an agent fails.

Deterministic

No model in the response path. The same transaction always produces the same JSON, nothing to hallucinate, nothing to drift.

No accounts, no keys

Paid per call in USDC over x402. An agent can discover, pay and retry entirely on its own.

Honest about gaps

Every response says which checks ran and which could not. An empty result is never mistaken for a clean one.

What runs today

One product, and the two fields that make it different.

base-transaction-decoder explains any Base mainnet transaction as strict JSON, plain English, a typed action, every asset moved with amounts already scaled, counterparties labelled, gas in dollars, risk flags with evidence.

in every responsebase mainnet

checksWhether each safety check actually ranSource unreachable → no flag emitted, check marked unavailableran unavailable

provenanceWhich strings the transaction’s author controlsToken symbols, contract names, and the summary derived from themtreat as data

A token that names itself with instruction-like text is a live injection route into any agent reading a decoder’s output. That is what provenance closes.

$0.02 per call in USDC · 50 free calls per day per IPv4 address or IPv6 /64 · no account, no signup, no API key

How we decide what to publish

Practices, not principles.

A practice can be checked. A principle cannot.

Claims carry the date they were verified. A fact true last week is reported as a fact about last week.
Pages are never overwritten. Corrections are dated and the original stays visible.
Examples are executed before publication. Every command shown here is run against production.
Unreachable is not clean. A source that cannot be checked is reported as unknown, never as an absence of problems.
What could not be determined is stated alongside what was. The same rule the decoder follows in its own output.

How it is built

One person, and gates that fail loudly.

0200project is operated by one person, with AI systems doing the majority of the engineering, review and analysis. Every claim is checked against a source before it ships, and the checks are automated wherever they can be.

the site build fails ifon every deploy

tierA page states a free-tier number the server does not reportblocked

registryA page names a registry entry that does not resolveblocked

samplesA published example does not execute against productionblocked

linksA link to one of our own properties returns an errorblocked

The company is small and the record is short. We would rather it be short and accurate.

Live

Read from production, right now.

These numbers are fetched from our own health endpoint when this page loads. They are not written into the page and we cannot edit them without changing what the server reports.

api.0200project.com/healthzfetching…

versionRunning in production—

callsLifetime, including our own— served on the free tier—

of which oursCalls we marked as oursA floor, not a measurement: an unmarked call of ours counts as external, never the reverse. — more we cannot attribute either way.—

wall hitsTimes the free tier ran outA count of responses, not of people, the same caller can appear many times—

degradedCalls answered while a check was unavailableReported rather than hidden, this is the number most services do not publish—

Loading per-check health…

If this panel fails to load it will say so rather than showing nothing, an empty panel and a broken one look identical, and only one of them is honest.

Contact

Talk to us.

General enquiries and corrections: contact@0200project.com. Bugs and feature requests go to GitHub Issues. Security reports have their own page.

contact@0200project.com Try the tool