Software that ships itself

Last month, 97% of our software shipped to production without an engineer.

476 of 490 production releases in July were made by our AI agents, not a person. That's what two and a half years and 51 billion tokens of real client work bought us — and it's the platform we now hand to customers.

Book a demo →See the platform

Built with fabric

Context Architecture

51 billion tokens processed at 94% cache efficiency.

Context architecture engineered for deterministic efficiency at enterprise scale.

How We Achieved This →Latest Dev Report →

CONTEXT

CACHE

CONTEXT INPUT

5.4%

Written once, cached

CACHE REUSE

94%

Massive scale efficiency

51B

TOKENS PROCESSED

94%

CACHE HIT RATE

87.3M

OUTPUT TOKENS

5.4%

CONTEXT WRITTEN

The Architecture

·Large 1M-token contexts written once, then read hundreds of times

·94% of all tokens served from cache, not recomputed

·Standards inherited by every agent instead of pasted per prompt

·The stable part of a prompt kept byte-identical, so it stays cacheable

What It Unlocks

·Retries cost almost nothing, so an agent can fix itself

·16 agents on one codebase without the bill scaling with them

·476 of 490 releases shipped with no engineer in the loop

·Proven on 51B tokens of real client work, not a benchmark

The Result

Software that ships itself.

We engineered ourselves out of the loop.

MACE INNOVATIONS

* Token and cache figures are actual organization-wide Anthropic API consumption over the trailing twelve months; cache efficiency = cache-read input tokens ÷ total input tokens. Development metrics (commits, active repos, lines) are pulled from the GitHub API. Every number on this site comes from source data — nothing is fabricated.

JULY 2026 DEVELOPMENT

3,401 Commits. 490 Publishes.

Our biggest month yet — and 490 trips to production, as customers began shipping on Fabric themselves.

Real data — not marketingPulled live · GitHub + Anthropic APIs

⚡

Total Commits

📦

Active Projects

🚢

Publishes to Prod

📈

Lines Added

Work Breakdown

2,280 commits

General Updates72332%

Iterative Refinement66829%

New Features59126%

DevOps / Config814%

Documentation2099%

Code Style80%

Jerry closes the loop now. With AI the first pass is a starting point, so most “fixes” are refinements rather than bugs — but in July the refining stopped going through us. 476 of 490 production releases were shipped by Jerry himself; 14 were a human merging by hand.

Stack & Focus

Platform

FabricJerryNeoMulti-Agent Platform

Delivery

One-Button Go-LiveVercelPreview Envs

Lending

Encompass / ICEMeridianLinkOptimal BlueLoanscapeFigure HELOC

Data

Experian CreditResWare Title & Fees

Comms

Feather Voice AITwilio SMSEmailSecure Delivery

UI Kit

@mace registryshadcn components

Infra

SupabasePostgres MigrationsClerk Auth

Languages

TypeScriptC#PythonPLpgSQLShellJavaScript

Impact Metrics

16.43B

TOKENS PROCESSED

94.0%

SERVED FROM CACHE

+1.01M

NET LINES

110/day

AVG COMMITS

LANGUAGES

203

TOTAL REPOS

Every commit above shipped through fabric — the multi-agent platform we run internally.Explore Fabric →

How We Achieved This→July Development Report→

// Five months, measured

We publish our own numbers. Every month.

Pulled from the GitHub and Anthropic APIs, not written by marketing. The second chart is the one that changed our business — it counts how many times code reached production, and before June the answer was zero because customers couldn't ship it themselves yet.

Commits

Across every Mace repository

759

Mar

520

Apr

1,741

May

2,493

Jun

3,401

Jul

Publishes to production

Times code actually went live

0

Mar

0

Apr

0

May

51

Jun

490

Jul

Real data — not marketingPulled live · GitHub + Anthropic APIsRead the monthly reports →