Skip to content
@Vext-Labs-Inc

Vext Labs

AI research lab. How a model grows new capability and proves that it grew. Six preprints with DOIs, open weights, and the experiment ledger.

Vext Labs

An AI research lab working on how a model can grow new capability — and prove that it grew.

Most of the field makes a model better by making it bigger, or by retraining it. We work on a third path: add capacity to a model that already exists, train only the new capacity, freeze everything that came before, and refuse the result unless it passes a gate. Growth that cannot be verified does not ship.

Product juwel.ai — JUWEL, an agent workspace
Lab vextlabs.ai
Papers vextlabs.ai/research · Vext-Labs-Inc/research
Models huggingface.co/VextLabsinc
Author Annalea Layton — ORCID 0009-0001-3695-9569

Research

Six preprints, each with a DOI, and each published together with its LaTeX source, figure code, and underlying experiment data in Vext-Labs-Inc/research.

Paper DOI
Beyond the Scaling Ceiling: Verified, Non-Forgetting, Provable Capability Accretion 10.5281/zenodo.21628058
The Accretion Model: A Growable, Non-Forgetting, Externally-Fueled Model Type with a Cryptographically Verifiable Growth History 10.5281/zenodo.21628429
The Leakage Signature: Falsification and Solver-Certified Capability Enlargement in Sequence Models 10.5281/zenodo.21628524
Verifier-Centric Capability Growth: A Measured Mechanism Map and a Research Program 10.5281/zenodo.21628544
Sound Compounding: A Verifier-Frontier Ratchet for Capability Acquisition and a Believed-versus-True Test for Self-Improvement Leakage 10.5281/zenodo.21628552
Capability Injection via Reverse Abliteration 10.5281/zenodo.21628566

All six are CC BY 4.0 and collected in the Vext Labs community on Zenodo.

On scope. These papers describe a mechanism, not a frontier system. Most positive results are measured at CPU scale or on small models, and every paper states which. We make no state-of-the-art or frontier-parity claim anywhere. The negative results are the majority of the program — the published ledger accounts for 81 pre-registered experiments, 43 of which were killed, nulled, or found to be leakage — and those are published too, because a growth claim is worth only as much as the tests it survived.

Models

Open weights on Hugging Face: three JUWEL bases and sixteen GEM specialists.

  • JUWELSjuwel-garnet · juwel-emerald · juwel-sapphire (vision-language)
  • GEMS — sixteen domain specialists composed on a shared base: alexandrite, aquamarine, bloodstone, citrine, jade, lapis, opal, pearl, peridot, ruby, sardonyx, spinel, tanzanite, topaz, tourmaline, turquoise
  • pentest-7b — security-testing model from our earlier work

The bases are derived from Qwen models under Apache-2.0, and each model card says so. We do not claim from-scratch weights or our own tokenizer.

Open source

Agent SDKtheron-agent-sdk. Open-core client for building agents against our fleet. Any model, any provider. MIT.

Stoa — an agent-native memory specification and runtime: memory an agent can write to, query, and carry between sessions, with provenance attached to each fact. Spec CC BY 4.0, runtime Apache-2.0. These repositories are archived and read-only; the design is published for reference and the ideas continue inside JUWEL.

stoa-spec · stoa-sdk · stoa-bus · stoa-edge · stoa-graph · stoa-identity · stoa-conformance

Earlier work: autonomous security testing

Vext Labs began as a security company, building agents that ran real tools against authorized bug bounty targets. That work is where the verification discipline in the research above comes from: a finding you cannot reproduce is not a finding. These repos date from that period and are kept for reference.

  • vext-pentest-7b — 7B model for autonomous penetration testing. Parses 25+ security tools, plans, and classifies findings.
  • vext-shield — detection suite for prompt injection and related attacks on AI systems.
  • sentry-benchmarks — audited benchmark results with raw responses, test cases, and a SHA-256 receipt per score.

Contact

Vext Labs, Inc. Incorporated March 2026. Built in Maryland.

Popular repositories Loading

  1. vext-pentest-7b vext-pentest-7b Public

    Open-source 7B language model for autonomous penetration testing. Parses 25+ security tools, plans attacks, classifies vulnerabilities, and generates remediation. Apache-2.0.

    Python 5 1

  2. coderabbit-test coderabbit-test Public archive

  3. pretty-in-pink pretty-in-pink Public archive

  4. wifipineapplepager-themes wifipineapplepager-themes Public archive

    Forked from hak5/wifipineapplepager-themes

    The Official WiFi Pineapple Pager Theme Repository

    HTML

  5. vext-shield vext-shield Public

    AI-native security skill suite for the agentic era. Detects prompt injection, semantic worms, cognitive rootkits, and other threats traditional scanners cannot see. Runs inside OpenClaw.

    Python 1

  6. sentry-benchmarks sentry-benchmarks Public

    Official benchmark results and full audit trails for the Sentry model family. Every score includes raw responses, test cases, errors, timestamps, and SHA256 receipts.

Repositories

Showing 10 of 16 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…