Frontier Accuracy.
Special.Small.Special. Owned.Purpose-built models that run inside your infrastructure.
95.6% accuracy on held-out tool calls · 88.1% F1 on Privacy-Bench documents · Apache-2.0
The trust layer for enterprise AI.
Two jobs every AI rollout needs.
Guard
Personal data and credentials stay inside your perimeter.
PII Extractor
Every personal detail, located precisely.
68M · 32M · 17M · 4M
Exact-match span F1, Privacy-Bench docs (656 human-annotated pages)
0.06 false values per 1,000 characters on text with no PII (68M), against 1.6–3.6 for the other models.
Secrets Detector
Every secret, found.
32M · 17M
Span F1, real-world issue reports (949 secrets)
Grade
Every agent response and tool call, scored.
Tool-Select Judge
Every tool call, verified.
2B · 0.8B
Accuracy, held-out test (3,904 calls, 50/50 right and wrong)
RubriX
Rubric scoring. In a single pass.
8B
Exact accuracy vs. human labels, held-out rubrics (6,749 judgments)
27.5–28.3 ms per judgment on an H100 with cached levels: 7.7x faster than Jev and 18.8x faster than a Qwen3-8B judge.
Why ownership pays
Your edge stays with you
Every model runs on your infrastructure, so your data improves your systems alone.
An asset, not a subscription
Apache-2.0 weights you keep, tune and build on, at the same cost however much you use them.
Runs where your data lives
On CPU or GPU, in your cloud or on-premise, beside the systems you already run.
Where it runs
Pre-commit hook
Run the secrets detector on every diff before it leaves your machine.
Log pipeline
Run the PII extractor over logs and tickets before they hit storage.
Agent eval harness
Run the tool judge and RubriX in CI, on every agent change.
Deployed and tuned by the team that built them.
Deploy
On your cloud or on-premise, wired into your pipelines and CI.
Fine-tune
Adapted to your documents, labels and rubrics.
Build the next one
A purpose-built model for the job your business needs next.