Bitware Labs / Empirical Case Monographs

What was actually built

Five production systems, documented the way a research monograph or commission report is written: what the problem was, what methodology was applied, and what the measured state is now.

METHODOLOGY NOTE // EMPIRICAL VERIFICATION RULE MEASURED ON ESTATE

Provenance & Confidentiality

Every case monograph below describes one of the laboratory's own in-house systems. None of it is client work, and none of it is anonymised client work presented as if it were the lab's. External commissions are governed by strict confidentiality; all figures quoted below are measured directly on our running Skåne estate.

MONOGRAPH 01 · L.U.N.A. COGNITIVE CORE // APPLIED AI · RESEARCH IN-HOUSE PRODUCTION

Applied AI · Research in-house

A long-running agent, and the discipline of keeping one alive

01 // The problem

Agent demonstrations are easy and agent systems are not. The interesting failures only appear at month three: retrieval quality falling as memory grows, beliefs that were true in March asserted as true in September, and a tool-using agent finding an expensive loop at three in the morning. None of that is visible in a prototype.

02 // What was done

Built one agent and then actually lived with it. Bi-temporal facts so the system knows when it learned something as well as when it was true; nightly and weekly consolidation instead of an ever-growing store; a wake cycle that gates whether to speak at all; and hard guardrails, per-turn cost and step caps, sandboxed execution, a local model risk-scoring inbound mail for prompt injection before the agent ever reads it.

03 // Where it stands

A system that has been running continuously rather than demonstrated. Its memory layer was extracted and published as bwmem; the generic build is public under AGPL; the research version stays in-house as the place new ideas are tried first.

325 tools on one unified execution path
73 scheduled jobs running unattended
12 LLM providers, routed per task

The full Luna write-up → Daybook →

MONOGRAPH 02 · SOVEREIGN WIREGUARD ESTATE // INFRASTRUCTURE · SECURITY IN-HOUSE PRODUCTION

Infrastructure · Security in-house

Taking a public estate off rented cloud

01 // The problem

A growing set of public services, a record label, a media stack, agent research systems, client workloads, spread across managed hosting, each with its own console, its own bill, and its own idea of where the data lived.

02 // What was done

Consolidated onto dedicated and local iron joined by a single WireGuard mesh with one flat address plan. nginx terminates TLS at the edge; everything behind it binds to loopback or a mesh address and is unreachable from the public internet. Certificates renew unattended. Internal services reach each other by mesh IP, never by public DNS.

03 // Where it stands

One estate, one set of credentials, no third party holding the data. Adding a service is an nginx server block and a mesh route, not a procurement decision. Defence is layered the same way: the conventional tooling as a floor, an AI sentinel above it for the distributed attacks per-IP limits cannot see, and a breach kill-switch beneath it that takes the estate off the public internet entirely, tested, not assumed.

23 public hostnames served from the estate
11 WireGuard peers on one address plan
0 managed-cloud dependencies in the serving path

How the mesh is designed → Live status →

MONOGRAPH 03 · @BITWARELABS/BWMEM SDK // APPLIED AI · OPEN SOURCE IN-HOUSE PRODUCTION

Applied AI · Open source in-house

Extracting a memory system into something other people can use

01 // The problem

The agent memory layer had grown up inside one research system. It worked, but it was welded to that system's storage, its scheduler, and its assumptions, so none of it could be reused, reviewed, or argued with.

02 // What was done

Pulled the episodic store, the consolidation pass, and recall out behind a narrow interface, with storage as an injected concern rather than a hard dependency. Published to npm under AGPL-3.0 so the obligation to publish improvements travels with the code.

03 // Where it stands

The memory layer is now a dependency the flagship agent consumes like anyone else would, which means the public package is the one that gets exercised in production every day. Five releases on, the interesting work has been subtraction: 0.5.0 shipped after measuring that 51% of "currently believed" rows on a production install were duplicates of each other, and that the inline contradiction scan could produce 35 phantom disagreements from one message.

v0.13.0 current release on npm
AGPL‑3.0 licence, with commercial terms available
93.2% LongMemEval top score (v0.13, 250 questions), caveats on /bwmem

The full bwmem write-up →

MONOGRAPH 04 · STUDYLUNA PEDAGOGICAL ENGINE // APPLIED AI · EDUCATION IN-HOUSE PRODUCTION

Applied AI · Education in-house

A personal AI teacher with a structured syllabus and gradebook

01 // The problem

Most attempts at AI tutoring are stateless chatbots that guess what the student needs without continuity or a pedagogical plan.

02 // What was done

Engineered a curriculum-driven teacher with structured lessons, question banks, and formative assessments. Tracks progress in a persistent gradebook over time.

03 // Where it stands

A system that actively teaches subjects from first principles, retaining complete memory of strengths and areas needing review.

180 lessons across 8 subjects
1,800 practice questions with automated grading
8 pedagogical tools in the registry

How the teacher is built →

MONOGRAPH 05 · BITWARETUNES 24-BIT DSP // CREATIVE AI · MUSIC IN-HOUSE PRODUCTION

Creative AI · Music in-house

An independent record label for AI artists

01 // The problem

Generative music is usually published as novelty tracks without persona, discography, or thoughtful curation.

02 // What was done

Built BitwareTunes (founded 2025 in Skåne) as a genuine record label: 20 acts with distinct artist worlds, album artwork, offline 24-bit DSP mastering, and distribution via DistroKid with full AI disclosure.

03 // Where it stands

20 signed acts, 217 releases and 1,420 master recordings, streaming free on our sovereign web player and distributed via DistroKid.

20 signed acts, each with its own sound and world
217 releases in the catalogue
1,420 mastered tracks, about 5% of 30,000+ songs generated

Visit the label →

Why the lab builds its own

§ · Note

A consultancy that only ever builds for other people never has to live with anything it built. Nobody calls at two in the morning about a system that was handed over eighteen months ago; the consequences of a shortcut land on someone else's rota.

Running our own production estate closes that loop. Every practice sold here is one the lab carries the pager for: the mesh, the hardening, the hosting, the agent memory, the music pipeline. When a recommendation is made to a client, it is a recommendation about something we are still maintaining, not something we once deployed.

How engagements work →

What was actually built

A long-running agent, and the discipline of keeping one alive

01 // The problem

02 // What was done

03 // Where it stands

Taking a public estate off rented cloud

01 // The problem

02 // What was done

03 // Where it stands

Extracting a memory system into something other people can use

01 // The problem

02 // What was done

03 // Where it stands

A personal AI teacher with a structured syllabus and gradebook

01 // The problem

02 // What was done

03 // Where it stands

An independent record label for AI artists

01 // The problem

02 // What was done

03 // Where it stands

Why the lab builds its own

Correspondence, Audits & Research Commissions