#ai-safety

hegelion

Hmbown / Hegelion

Dialectical reasoning architecture for LLMs (Thesis → Antithesis → Synthesis)

clarity-gate

frmoretto / clarity-gate

Stop LLMs from hallucinating your guesses as facts. Clarity Gate is a verification protocol for your documents that are going to be provided to LLMs or RAG systems. Place automatically the missing uncertainty markers to avoid confident hallucinations. HITL for non-directly verifiable claims.

clarity-gate

frmoretto / clarity-gate

Stop LLMs from hallucinating your guesses as facts. Clarity Gate is a verification protocol for your documents that are going to be provided to LLMs or RAG systems. Place automatically the missing uncertainty markers to avoid confident hallucinations. HITL for non-directly verifiable claims.

clarity-gate

frmoretto / clarity-gate

Stop LLMs from hallucinating your guesses as facts. Clarity Gate is a verification protocol for your documents that are going to be provided to LLMs or RAG systems. Place automatically the missing uncertainty markers to avoid confident hallucinations. HITL for non-directly verifiable claims.

hardstop

frmoretto / hardstop

Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.

hardstop

frmoretto / hardstop

Don't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era.

factcheck

DeepCitation / deepcitation-js

Official JavaScript/TypeScript SDK for DeepCitation. Add citations with verifications to any LLM system.

intent-analysis

az9713 / icr

🛡️ Make AI show its work before it does the work. The intent problem? Fixed.