Credence — Epistemic Guard

lakshmi-chakradhar-vijayarao/credence-ai

Epistemic guard that hooks into transformer hidden states to classify whether the model is recalling training data, using context, or confabulating. Exposes a probe layer trained on Fisher geometry (AUROC 0.9944 validated on Qwen2.5) that fires before token commitment. Blocks file writes and code commits when confidence drops below threshold. The symbolic layer tracks uncertain values across inference steps, so if a variable assignment gets flagged as confabulation risk, downstream operations using it stay blocked until verification. Reach for this when you're letting an agent write code or modify files and need circuit-breaker semantics tied to the model's actual epistemic state rather than parsing output text for hedging language.

tool

1

transport

STDIO

last updated

May 6, 2026

Sponsors

Promote your product hereReach 125k+ visitors monthlyPromote your product hereReach 125k+ visitors monthlyAgent CaffeineSponsoredClose your lid, come back to finished workSnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthlyWaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthlyknobsSponsoredSee your site on any phone, any day, in any language

pip install credence-guard
credence demo   # 30-second smoke test, no API key required

RATE_LIMIT = 50   # no warning. no flag. shipped.