Loading comparison…
HEAD TO HEAD
TextCortex: laya-cybersec and SAGEA: mira, compared on what they decide, where they run, what they cost and what their publishers report.
| Property | textcortex/laya-cybersec | sagea/mira |
|---|---|---|
| Summary | Laya fine-tune that scans untrusted text (extracted files, knowledge-base documents, agent skills, tool descriptions) for prompt injection and data exfiltration in English and German, as a noul question answered in one forward pass. 322M parameters, PyTorch and ONNX. | Small open typed-decision model with calibrated probabilities, first-class Nepali coverage. |
| Decides | noul, classify | choice, score, noul, classify, route |
| Architecture | laya | mira |
| Fine-tuned from | convaiinnovations/laya-multilingual | jhu-clsp/mmbert-small |
| License | Unspecified; training data includes CC BY-NC-SA 4.0 material (non-commercial), not relicensed | apache-2.0 |
| Availability | Open weights | Open weights |
| Hosted by | — | — |
| Input price | — | — |
| Decision accuracy | — | 61.3% |
| Calibration error | — | 0.083 |
| Valid action rate | — | 100.0% |
| Median latency | 95.4 ms | 30 ms |
| p95 latency | 149 ms | 43 ms |
| Evaluation suite | TextCortex saved run: 279 single-window inputs, PyTorch batch one | s1-decision-bench |
Figures are from each model’s manifest; accuracy and latency are what the publishers report, on their own suites and hardware. Add a third model.
laya-cybersec is from TextCortex and mira from SAGEA. Both have open weights you can download and run. Both answer noul and classify questions. Only mira answers choice, score and route. laya-cybersec is licensed other; mira, apache-2.0.
Only mira publishes an accuracy figure (61.3% on s1-decision-bench); laya-cybersec does not, so there is no comparison to make without your own test.
laya-cybersec: Free (open weights). mira: Free (open weights). Open weights cost nothing per call beyond your own hardware.
By their publishers’ figures, mira answers in about 30 ms at the median and laya-cybersec in about 95.4 ms — measured on different hardware, so treat it as a rough guide.
Yes, both: systemone pull textcortex/laya-cybersec and systemone pull sagea/mira download the weights.
| Latest version | 2026.10 | 0.1.5 |
|---|
| Variants | encoder, onnx, tokenizer | — |
|---|
| Size of latest version | 1.8 GB | 568.8 MB |
|---|
| Files | 9 | 12 |
|---|
| Downloads | 0 | 112 |
|---|
| Stars | 0 | 1 |
|---|
| Tags | system-one, laya, encoder, prompt-injection, security, guardrails, multilingual, onnx, 322m | routing, nepali, nepal, calibration, cpu |
|---|
| Updated | Oct 7, 2026 | Oct 6, 2026 |
|---|