What does SophiaXT do?

SOPHIA XT is an operator-built AI implementation company in St. Louis, MO. It runs technical service businesses (The Appliance Guys, HVAC Guys), ships the operational software those businesses need (ServiceLens, Lead Leak Scanner, Sophia Key 3M), and publishes underlying research as open releases (Cassandra T1 on GitHub, Apache 2.0).

Who founded SophiaXT?

Thomas Garren founded SOPHIA XT in 2024. Operating partner Chris Becker (Becker Service Group).

Where is SophiaXT located?

St. Louis, Missouri, United States. Serves the United States and worldwide via remote engagement.

Does SophiaXT tell clients when AI is unnecessary?

Yes. SophiaXT reviews the workflow first and recommends skipping AI when a process change, dashboard, API integration, or simpler automation would be more cost-effective.

What's unusual about SophiaXT compared to other AI consultancies?

SOPHIA XT operates real service businesses, so its AI recommendations have to survive on its own dispatch board before being shipped to clients. Operator + builder + researcher under one roof is rare in AI consultancies.

What is Cassandra T1?

Cassandra T1 is an open-released masked-diffusion language model from SOPHIA XT, available at github.com/Chorozion/Casandra-t1-diffusion-edge-model under Apache 2.0. The repo includes a verified epoch-5 FP16 checkpoint (~2.66 GB), tokenizer, PyTorch architecture, and training/inference scripts. T1-Base is a 28-layer transformer with 2,048 hidden, 32,768 vocabulary, GQA (16 query / 4 KV heads), RoPE, RMSNorm, SwiGLU, and 12 default denoise steps.

Does Cassandra T1 publish benchmark numbers?

No. SOPHIA XT does not publish benchmark numbers it has not measured publicly. The repo includes a captured 10-prompt qualitative coherence comparison and recorded training-loss values, but does not include MMLU, HumanEval, GSM8K, or similar standard-suite results.

How do I contact SophiaXT?

Email contactus@sophiaxt.com or use the contact page at sophiaxt.com/contact. The booking CTA on the site is 'Book with Thomas Garren.'

What does the XT in SOPHIA XT stand for?

Extended knowledge. Sophia is the Greek word for wisdom; XT denotes the architecture of pairing a base language model with extended context through LTMi-XT topological memory indexing, forced-anchor decoding and multi-agent orchestration, so the system reasons over more than its raw token window.

What does the 'XT' in SOPHIA XT stand for?

eXTended-knowledge. SOPHIA is the Greek word for wisdom (σοφία); XT denotes the architectural pattern of pairing a base language model with extended context (LTMi-XT Layered Topological Memory Indexing), forced-anchor decoding, and multi-agent orchestration so the system reasons over more than its raw token window.

What is anchor-token masking?

Anchor-token masking is a training-and-decoding technique introduced by SOPHIA XT for masked-diffusion language models. During training, a subset of high-information tokens are designated 'anchors' and given special unmask treatment. At decode time, those anchors are forced first, then the surrounding text is generated conditioned on them. The technique is documented in the open-access preprint at Zenodo DOI 10.5281/zenodo.20496783 and used in Cassandra T1.5 / T1.6.

What is the Constellation orchestrator?

Constellation is SOPHIA XT's 6-lane multi-agent orchestration framework: Planner, Critic, Retrieve, Execute, Memory, and Verifier lanes, coordinated by an ARBITER controller. It is a local-first orchestrator that runs on operator hardware, not a cloud SaaS. Documentation: https://sophiaxt.com/research/constillation.

CT1-XT is SOPHIA XT's humanoid diagnostic-robotics platform: a Jetson Orin Nano Super edge compute core with dual STM32H7 motor controllers, 4x Li-ion packs, CAN-FD and RS485 buses, and a build-tier system from research-grade up to deployable field unit. Full 42-page Rev E engineering pack is published at https://sophiaxt.com/robotics/ct1-xt.

SophiaForge — the SophiaBuilds agentic dev environment

A ticket becomes a pull request.

SophiaForge is the SophiaBuilds agentic dev environment. Drop a ticket on the board; the Constellation arbiter routes it to a charter-bounded lane, an agent builds it inside its own isolated git worktree, and you review the pull request. It is bring-your-own-model, memory-backed, and it never merges on its own.

Complete for this release. Access by invite.

Looking for the design system? That is Sophia Design Forge.

See it run

A live Constellation round: the arbiter routes the ticket, the lanes run over the recursive kernel, the verifier gates it, and a pull request opens for a human to merge. Nothing here is a mockup. It is the real loop.

Access

An invite opens the board.

Invites are links. One use, fourteen days. Paste the code from yours below, or ask for one and Thomas will read the request himself.

Ask for an invite Watch the lab, live →

How it works

The Constellation arbiter

Every ticket is scored against six charter-bounded lanes — planner, retrieve, execute, critic, verifier, memory — with a written rationale and a confidence floor it refuses to cross.

One ticket, one worktree

Each ticket spins up its own git branch and isolated worktree. Parallel agents never collide. The agent path ends at review — a human merges. Agents never merge.

LTM + NCn memory

Node-round memory shards recall per lane, so routing sharpens with every ticket instead of staying a frozen keyword map. The board gets better the more it's used.

Bring your own model

Claude, Codex, a shell adapter, or a local model — per lane. A key vault with a hard TTL and a budget gate on every run keep cost and secrets in check.

The loop

backlog → route → in-progress → review · PR → human merge → done

The agent path ends at review. There is no merge call anywhere in the agent code path — every merge is recorded against the human who made it.