PsiGuard – real-time hallucination monitoring for LLM apps
Hallucination detector for LLMs, but existing tools like Guardrails and Langfuse already do this.
Lightweight, model-agnostic hallucination risk engine for LLM outputs
Yet another hallucination checker when Guardrails and LMQL already cover this.
Developers building production LLM pipelines
Guardrails AI · LMQL · Arize Phoenix
It checks three things before your output moves forward: does it match the schema you expected is it consistent across runs does it actually align with the context you provided
Returns a confidence score and a risk level. That's mostly it.
Works with OpenAI, Anthropic, Gemini, Ollama and a few others. Sync and async both supported. It's heuristic, not a guarantee. If your context is bad, the scores will be too. Hit a star, if you found this useful.
Try now: pip install hallx
Hallucination detector for LLMs, but existing tools like Guardrails and Langfuse already do this.
Lightweight retry loop that improves IFEval instruction-following from 69% to 76% accuracy.
Detects sycophancy and jailbreak drift in LLMs without needing model weights.
Peer-reviewed LLM hallucination detector using uncertainty quantification, published in JMLR and TMLR.
The demo implements post-generation admissibility checks and returns structured refusals (decision codes, rule triggered, divergence metrics and a stable prompt fingerprint) so you can audit enforcement decisions. It's a crisp, focused proof-of-concept for runtime enforcement — useful as a starting pattern — but it stops short of addressing bypass/adversarial vectors, deployment integration, or guarantees that make it enforceable at scale.
Schema-valid evidence packs for AI agents when generic evals miss domain nuance.