Route 05 · start here

One screen, and a thing you can drive.

No job title required. Here is the whole idea in four sentences, then a real governed agent you can give an instruction to and watch be refused. If something below turns out to be your problem specifically, the other four doors are at the bottom.

01

The whole idea

Software now acts on people's behalf. An AI agent books, buys, files, replies and calls other software — sometimes software built by a different company entirely.

Nobody can prove afterwards what it was allowed to do. The record lives inside whoever ran the agent, in their logs, on their word. That is fine until the question is asked by someone who has no reason to take their word for it.

So every action carries its own proof. Who acted, and under what authority, signed into the action itself — checkable by anyone holding the signer's public key, offline, with no prior relationship and no service to call.

And the authority is enforced, not merely recorded. When a rule says no, the agent stops. You get the name of the rule that decided.

SYNTHERA is the trust layer for multi-agent systems: every agent gets a verifiable identity, scoped authority and a tamper-evident record, so software from different teams, vendors and frameworks can act on each other’s behalf without custom glue between every pair.

02

The thing you can drive

Ask a real agent to move money and watch it refuse.

This runs against a governed agent in production. No account, no key, nothing installed, and it is the same path a paying customer's agent takes. The rule that decides is named in the answer.

Fig · Live governance (runs against production)
Ask the agent to do something

Every option below is evaluated for real, by the production policy engine, against a governed agent that is running right now. You are not choosing a canned answer — the verdict comes back from the same path a paying customer's agent takes.

Loading what the demo can evaluate…

What happened
Ready Pick something on the left.

    No account, no key, and nothing installed. Solara signs this request as the shared demo agent, because you hold no credential and were issued none — a dedicated agent with an identity of its own is what the paid tier is.

    One shared demo agent signs for everyone who visits — that is not an agent of yours, and nothing separates your request from anyone else's.

    /* var(--bg) and var(--dim-1) are DEFINED NOWHERE. Corrected 2026-08-24 to the tokens that exist. This was not a wrong colour: an invalid var() is invalid at computed-value time, so `background: var(--bg)` computed to `transparent` and these panels sat directly on their parent, whose background is --rule. That parent-is-the-rule-colour trick is how every hairline grid on this site is drawn, so the effect was that EVERY INTERNAL RULE DISAPPEARED and the grid rendered as one flat slab. Verified in Chrome against the built pages before and after. Four of the five /for/* routes carried it — the newest pages on the site, written to a claims brief, inheriting a token name from nothing. */
    03

    Where this is up to

    Early, and specific about it.

    The standardOpen, Apache-2.0, published on three package registries
    The productPre-pilot, running live
    An accountOpen to anyone, takes a moment
    An agent of your ownGranted deliberately, not bought
    The demo's own page →

    The same agent, with the full explanation of what each part of the answer means.

     Verify one offline →

    A real production credential, checked in your browser. Turn the network off first.

     What it costs →

    $99 a month, and the two reasons you cannot pay for it today.
    04

    If one of these is you after all

    Each goes somewhere different and each says where before you follow it.

    01

    I build with agents and I want the identity primitive.

    Builders

    The repo, the spec, and the conformance vectors three implementations reproduce byte-for-byte. No marketing screens in the way.

    about 90 seconds     02

    I am responsible for securing agents my organisation runs.

    Security leaders

    A live refusal by a named rule, then the published trust anchor you would verify it against — and a written account of where this wedge stops.

    about 6 minutes     03

    My business is adopting AI and I need to know what could go wrong.

    Business owners

    An agent refused in plain English before any code appears, then the price and what it does not include.

    about 4 minutes     04

    I want this operated for us, on our terms.

    Enterprise

    A conversation. There is nothing to buy on this route and the page says so before you spend any time on it.

    about 3 minutes