In early access · a small number of partners

A programming language
built from a different foundation.

HexStellar (HXS) is a native runtime for GPU inference. Measured across five independent labs' flagship models on one NVIDIA H100: 17.2–27.4% less energy per card, up to 15°C cooler, +167% more capacity at the same latency, 100% identical output.

See the results ↓ Get in touch

17.2–27.4%Less energy per card

Up to −15°CCooler, per model

+167%More capacity, same latency

100%Identical output

How this started

Found by accident.
Followed on purpose.

HexStellar wasn't the plan. It surfaced while we were building the infrastructure behind Trust Carbon Infrastructure — our other venture, a verification platform for carbon and environmental data, legally operated by Zenith Flow Innovations. We ran into a computational bottleneck that shouldn't have existed, went after it anyway, and months of quiet investigation later found something bigger than the problem we started with.

Hex + Stellar

HEX

Six sides. It's nature's most efficient tessellation — honeycombs, carbon rings, basalt columns, snowflakes. It's also the language machines use to talk to themselves: hexadecimal is the base of every byte, every color, every memory address. Hex is the shape of the architecture itself.

STELLAR

Not a metaphor for ambition — a reference to efficiency. A star is the most efficient energy-conversion system that exists: fusion turns mass into energy at a ratio no engineered system has matched. That's the standard "Stellar" refers to. Not speed. An efficiency bar set by physics itself.

The runtime

Initialize once.
Runs automatically.

HexStellar ships as a native runtime component. A single integration point — no language to learn, no syntax to write, nothing to tune, and no changes to your model.

● Single integration point — no per-model work
● Outputs checked for incorrect results under our protocol
● No hidden dependency chain — 0 external deps at the core
● Verified at 100% identical output across every model tested

hexstellar · native runtime

// Native runtime component.
// One integration point. Your model and
// serving setup stay as they are.

// Integration details are shared under
// NDA with companies evaluating HexStellar.

HXS runtime · v1.0 ✓ evaluation under NDA

Measured, not marketed

A few of the numbers.

Measured across five independent labs' flagship models on one NVIDIA H100 80GB, running vLLM — the layer on versus off, at identical load.

Capacity +167%

More capacity, one card, same latency 109.8 → 293.7 requests/sec at the same latency target — nearly three times the traffic.

Energy 17.2–27.4% Less energy per card, across five models Alibaba, Meta, DeepSeek, Google, and Microsoft's flagship models, each on identical hardware.

Thermal Up to −15°C Cooler, per model 62.4°C → 47.4°C on Meta's Llama 3.3 70B — the largest drop measured.

Reliability 100% Identical output Same answers, identical results, across every model tested — zero errors.

This is the complete result, not a curated sample. See the full breakdown →

What's next

This is the first result.
It is not the last.

There is more measured, and more still running. We publish one result at a time, each finished before the next one goes up — some of what's queued we re-ran several times before we believed it ourselves.

Published

Five flagship models, one NVIDIA H100

Energy, temperature and serving capacity — the layer on versus off, at identical load.

See the measurement →

In progress

More, on fronts we haven't published yet

Each one goes up finished — the write-up and the signed file held to the same standard as the result beside it. We would rather be late than be corrected.

Over the coming days

Companies evaluating HexStellar see results before the site does. Get in touch →

Where it fits

Today, next, and where
it's headed.

One runtime, rolled out where the measured advantage is largest first.

Today · Servers

Servers & inference clusters

Search, retrieval, classification, batch work — anywhere the same requests come back. One install, wrapped around the system that already runs.

Next · Devices

Phones, laptops, on-device models

Where the prize isn't only speed — it's battery and heat. Less work reaches the silicon, so devices stay cool. Fully offline, fully local.

Horizon · Silicon

Chips & accelerators

Built directly into the hardware that runs inference. Early-stage conversations, not yet a product.

Our position

"Performance is a moral question — every wasted joule is a choice someone made when designing a language."

We didn't build HexStellar to be a "green" language. We built it to be the most correctly engineered language. The environmental consequence — less energy, less heat, less hardware stress — is the natural outcome of getting the foundation right.

● Patent Pending

The company behind it

Trust Carbon Infrastructure

The venture we were building when HexStellar found us — and the reason we know how to hold an engineering claim to a standard that survives scrutiny.

Digital MRV & Verification Platform · Est. 2023

Trust Carbon Infrastructure is a methodology-agnostic verification platform for carbon credit and biodiversity projects, built to work under real field conditions — offline-first data collection from a smartphone, with anti-fraud safeguards like GPS-spoofing detection and cryptographic hashing of every record. It supports major methodologies including Verra, Gold Standard, CDM and LuxCS, in 17 languages.

Over two million lines of code across the web platform and the mobile app — and almost none of it borrowed. The field app runs completely without an internet connection: no third-party APIs, no external services to call, and its own navigation system rather than a hosted map. That was not a preference. The places this platform is used do not have a signal, so anything rented from the cloud simply would not run there.

That constraint is also where HexStellar came from. Building a system that had to do everything itself, on whatever hardware was in someone's hand, is what turned a computational bottleneck into a question worth chasing.

The platform was named one of five global winners of the DPI for People and Planet Innovation Challenge, out of 540 startups from 73 countries — a $100K award, judged by the Gates Foundation, BCG and JICA. It's the same discipline — auditable, reproducible, sealed against drift — that HexStellar's benchmark numbers are held to.

Trust Carbon Infrastructure is legally operated by Zenith Flow Innovations LLC, a U.S. company based in California.

2M+ lines of code Fully offline field app Own navigation · no third-party APIs Verra · Gold Standard · CDM · LuxCS 17 languages $100K DPI Challenge award Zenith Flow Innovations LLC · California, USA

A programming languagebuilt from a different foundation.

Found by accident.Followed on purpose.