PSA-core

PSA is a multi-classifier behavioral analysis engine for LLM responses. It classifies every sentence into behavioral postures, then derives metrics from the posture sequences to detect adversarial stress, sycophancy, hallucination risk, persuasion techniques, and input pressure — in real time.

Star

7-day growth

Contributors

Language

Python

Updated

2026-08-16

Not an installable plugin package

There is no package.json at the repo root, so dsh plugin add fails outright. It may be an index list, documentation, a standalone app, or still in development — check the repo README for how to use it.

Share card

Drop it into your README — it links back to this page.

Badge (inline)

[![dshfind](https://dshfind.com/api/badge/SiliconPsycheLabs/PSA-core)](https://dshfind.com/en/plugins/SiliconPsycheLabs/PSA-core?ref=badge)

Card (440×200)

[![dshfind](https://dshfind.com/api/card/SiliconPsycheLabs/PSA-core)](https://dshfind.com/en/plugins/SiliconPsycheLabs/PSA-core?ref=badge)

#ai-safety #llm-agents #machine-psychiatry #psa