03 // Developer Tooling Lease — $300 / project

HESUS

A Development Brain for AI-Assisted Software

HESUS is a portable project brain: a small, pure-Python system you fold into a codebase so the architectural decisions made during development — the why this, why not that — become durable, queryable objects instead of knowledge that evaporates between sessions and people. It rides alongside an AI coding workflow and makes the operator's judgment persistent.

Decision Graph Pure Python · stdlib only Zero Runtime Deps Project-Blind Engine Context-Efficient

The scarce, irreplaceable asset in a long-lived codebase isn't the code — code can be regenerated. It's the decisions: why a boundary was drawn here, why an approach was rejected, what a subsystem is actually for. That reasoning is exactly what disappears between AI sessions, between team members, and between the person who wrote a module and the person who has to change it six months later. HESUS treats those decisions as first-class, retrievable objects rather than prose buried in commit messages and wikis that drift out of sync with the code.

Engine & data, strictly separated
The brain is project-blind — it hardcodes no fact about any codebase. A project's knowledge lives entirely in data the engine reads through a descriptor. That's why one engine serves any project, and why the engine can be upgraded underneath a project without touching accumulated knowledge.
It assembles and points; you judge
HESUS doesn't think for you. Briefed on a task, it surfaces the decisions and files that bear on it and points at the full sources — deliberately not paraphrasing. Judgment, work, and bug-catching stay with the operator. No false authority, no single point of failure.
Cold until needed
The expensive operations — gestating a project's history, planning an upgrade — are gated behind necessity checks and run rarely. Day-to-day orientation is cheap. The steady state pays almost nothing, so it's practical to live with rather than a tax on every session.

Everything HESUS does is one of three operations:

Seed

Drop an empty-but-capable brain into a new project. It's born ready and grows as the project does.

Gestate

On first contact with an existing project, extract its accumulated decisions into the cortex.

Upgrade

Give a project running an older brain a newer engine — without losing a single accumulated decision. Swap the engine, preserve the cortex, verify.

The central daily benefit is context-efficient briefing. Instead of an AI session cold-reading a project's entire decision history to orient — burning a large fraction of its working context — a brief returns only the relevant slice plus pointers. Because a brief stays near-constant in size while the cortex grows, the saving grows as the project accumulates more decisions.

Under the hood it's about 6,200 lines of standard-library Python across a set of single-purpose organs — brief, gestate, query, upgrade, and a chain of honesty gates — all reading project-specifics through a single descriptor seam. It even ships a fallback TOML parser so it needs zero pip installs and runs on Python 3.8+.

~60–70×
context compression — a real brief vs. cold-reading a 206-decision cortex
0 / 206
decisions lost when the engine was upgraded across a generational rename
206
architectural decisions held in the cortex (grew from 81, with the project)

These were measured on Omniscient, a real shipping Windows fleet-hardening tool (6,497 LOC PowerShell engine), into which HESUS was folded and then upgraded — not a benchmark fixture built to flatter the system. The full story, the things that didn't work, and what is proven versus unproven are in the case study.

ProvenContext efficiency (~60–70× at a 206-decision cortex, and it grows with the cortex), knowledge preservation across a generational engine upgrade (0 of 206 lost), and the project-blindness invariant, enforced by a ship gate.
ConditionalThe consistency benefit — "stop reinventing the same decision" — is real but gated on ingest quality. A thin or sloppy cortex steers weakly. We say so plainly.
Not yet provenWhether the contradiction-tripwire layer measurably changes an operator's output needs a blind, controlled comparison that hasn't been run. The mechanism is built and fires correctly; the behavioral lift is recorded as unproven, not asserted.

HESUS does not autonomously write code or make decisions. It makes an operator's judgment durable, queryable, and provenance-preserved. Sold as exactly that, the measured results above are what it delivers.

$300 / project — one-time

A "project" is one codebase the brain is folded into and grows with: seeded or gestated on arrival, accumulating that project's decisions over its life, upgradeable to newer engine generations without losing what it has learned. Folded in once, it's yours to keep in that codebase for life. Pure Python, standard library only, no external dependencies — it runs anywhere your code does and adds nothing to your runtime.