← Back to home
The System

How Eous Is Built

The architecture, in detail - what runs, what we rent, and what we actually made

Eous is not a model. It is a machine built around one. The raw reasoning comes from a frontier large language model - the same class of system anyone can rent, and not the part we invented. Everything that makes Eous different is the apparatus wrapped around that model: how it remembers, what it can do, how it checks itself, when it runs on its own, how its parts coordinate, and how it improves its own method over time. This page names those parts, shows how a single task moves through them, states the disciplines that hold the whole thing to account, and is candid about what we have not yet solved.

We cite the model. We claim the machine. The language model is a commodity, and we say so. What Forged Lucidity built is the disciplined apparatus around it - and every part of it is held to the same rule as the science on the rest of this site: cite, don't claim; verify before you speak; report the losses. This is the honest engineering view. It names the parts and how they fit; it does not hand over the protected internals.
The architecture at a glance
On the top rungA person - proposes nothing, disposes everything
ImprovementThe self-improvement loop (RSI)
The gate everything passesThe verification harness + external grader
ContinuityPersistent memory
CapabilityVersioned skills
AutonomyOrgans on a cadence
Substrate - cited, not claimedA rented frontier model (MAJI2 wraps it)
Every part writes to one append-only record. Each live view of state is regenerated from it, so the whole machine is auditable.

The machine, part by part

1

The substrate

The reasoning - rented

A frontier large language model supplies the raw reasoning: reading, writing, mathematics, code. It is powerful, and it is rented, not ours. We treat it the way a workshop treats a good engine - essential, replaceable, and not the thing that makes the finished machine worth anything. Our substrate layer, which we call MAJI2, is the wrapper that turns a general model into a disciplined operator: it fixes the operating rules, loads the right context and skills for the task, and hands the model to the rest of the machine.

Cite, not claim: the intelligence in the box is a bought component. If the best available model changes tomorrow, we swap the engine and keep the machine.
2

Persistent memory

Continuity

Most AI forgets you the moment the tab closes. Eous carries a persistent, structured memory across every session: your context and projects, the state of the work, and its own operating notes and history. It is a real store the agent reads from and writes to - not a longer prompt, and not a chat log it re-skims. The store is kept deliberately, with durable facts separated from transient ones and periodically consolidated so it stays dense rather than sprawling. The system that sits down with you in six months knows your terrain better than it did on day one, on purpose.

Continuity is an engineering problem, and we treat it as one. A machine that cannot remember cannot improve.
3

Versioned skills

Capability

Capabilities are packaged as skills - modular, versioned instruction sets the agent loads when a task calls for one, the way a program imports a library. A deadline calculation, a verification procedure, a document build: each is a skill with a defined job. A skill can be written, linted against its own standards, tested, improved, archived, and rolled back, and its lineage is kept, so no capability in the system's history is silently lost. New abilities are added the way code is added to a codebase - reviewed, versioned, and reversible.

The skill library is how the machine grows without being rebuilt, and how a fix to one procedure propagates everywhere it is used.
4

The verification harness

Honesty, enforced

This is the part that matters most, and the part almost no one else builds. Before Eous trusts its own work, that work runs a gauntlet:

Pre-registration. An empirical hypothesis is filed - timestamped, on OSF and Zenodo - before the test is run, so the goalposts cannot move after the data is in.
The reading gate. A claim about a source is checked by opening the actual source, not a summary or a note about it. A citation whose only provenance is someone else's paper is treated as unread until the original is in hand.
Primary-record checks. Facts are verified at the record itself - the statute, the docket, the dataset, the filing - not at a gloss of it.
External grading. The decisive question - is this work actually good? - is answered by a signal from outside the model, against ground truth that was fixed before the run being judged. A model's own opinion of its own reasoning is the cheapest possible check, and we do not let it count as verification.
The ledger. Every consequential decision is recorded with a due date and later scored a win or a loss by opening the specific artifact it named. Predictions that go unscored are killed by default. The system is held to its own past claims.

This is why "honest by construction" is literal. The honesty is a machine part, not a promise - and the scoring layer is deliberately frozen so the system cannot quietly rewrite the test it is about to be graded against.
5

Autonomous organs

It runs when no one is watching

Parts of the system run on their own schedule, unattended - reading, drafting, checking state, and staging work for review on a fixed cadence. They are deliberately kept on a short leash: they propose and prepare; a human disposes. An organ can draft, flag a discrepancy, or prepare a task to a single action, but it does not ship anything irreversible on its own. This is early, and it is real. Some organs are further along than others, and we describe them as what they are, not as more.

The point is not autonomy for its own sake. It is that useful, reviewable work keeps accumulating between conversations.
6

Coordination

How it holds together

Many parts write; one source of truth holds. The system is coordinated through an append-only record of what happened, from which each live view of state - the working board, the task list, the status of a project - is regenerated by a single owner rather than edited in place. A provenance stamp and a fencing token guard it, so two actors cannot quietly overwrite each other. The machine talks to tools and outside data through open, standard protocols rather than bespoke glue. The result is a system whose state you can audit, because everything that changed it is written down and nothing is silently overwritten.

Auditability is not a feature bolted on afterward. It is the shape of the architecture.
7

The self-improvement loop

It improves its own method

The whole system is run as one loop: propose a single change to how it works, test that change against a real outside signal, keep it only if it wins, kill it if it loses, and archive the lineage either way. Improvement here is not a slogan; it is a procedure with a scoreboard, and the scoreboard is kept by something other than the part being graded. Nothing is banked as progress without a prediction that could have failed. A person sits on the top rung of that loop, always - approving what compounds and killing what does not.

The compounding lives in the process and the archive, not in any single answer.
The process

How a single task moves through the machine

The parts above are not a static diagram. Every real piece of work runs the same path, and that path is the point:

  1. Orient. Before answering, the system loads its bearings - the memory store, the calendar and inbox, the working board, and whatever the task touches - so it starts from the current state of the world, not a stale one.
  2. Work. The substrate does the reasoning, drawing on the skills the task calls for and the context memory supplies.
  3. Verify. The result runs the harness - open the real source, check the record, and where it is an empirical claim, grade it against a signal fixed outside the model. Unverified work is labeled owed, not done.
  4. Checkpoint. Before leaving any task, the system writes down where things stand, so nothing is left in its head and completed work stays completed.
  5. Record. What happened is written to the append-only log, and the live views of state are regenerated from it.
  6. Harvest. At the close, verified learnings are routed up into memory and skills, and open predictions that have come due are scored - win or loss - against the artifacts they named.
The disciplines

The rules the whole machine is held to

These are not aspirations printed on a wall. They are the operating constraints the system runs under, and the reason the engineering can carry the word "honest":

What we do not claim

The honest edges

The grader is not yet fully independent. The hardest problem in a self-checking system is that the thing being graded and the thing doing the grading can be too close together. Making the external grader genuinely independent of the generator - a separate instance, a different model, or an outside oracle - is the single open frontier we name, not one we claim to have closed. When our own external checks have failed, we have recorded the failures rather than hidden them.

The organs are early. Autonomous operation is real but young. We describe each organ as what it does today, and no organ ships anything irreversible without a person.

The intelligence is rented. The reasoning engine is a commodity model we do not own and did not train. The value we claim is the machine around it, and we are precise about that line.

The honest bottom line

Strip it down and the claim is small and checkable: we rent a frontier model, and we built a disciplined machine around it - memory so it carries context, skills so it grows, a verification harness so it tells the truth, organs so it works unattended, a coordination layer so its state stays auditable, and a loop so it gets better at getting better, with a person on top. None of that is magic, and we never say it is. It is engineering, held to the same honesty as the science.

If you want to see the machine do real work, that is the frontier results. If you want the proposed theoretical foundation the project also pursues - held separately, and clearly marked as proposed - it is on the foundations page.

Partner with Eous · The research library