SE-CoVe: Software Engineering Chain-of-Verification plugin for Claude Code
Make Claude admit when it half-assed your task. A Claude Code skill. (Now, can be used for Codex as well as Antigravity).
A lightweight anti-hallucination wrapper for LLMs using Chain-of-Verification.
This open-source Python application demonstrates an interactive way to apply various NVIDIA NeMo Guardrails to an LLM. It features a custom implementation of the Chain-of-Verification (CoVe) technique.
A verification gate combining Chain-of-Verification, Self-RAG, and Constitutional AI. Cited verdicts, policy checks, CI exit codes.
Draft an answer, generate independent verification questions about its claims, answer them, and revise: a self-verification loop (CoVe) that reduces hallucination.
Implementation of the Self-Critique Chain pattern for automated research paper summarization using Claude AI.
🧬 Mythos — Research-grade agentic framework for Claude Code. Paper-backed reasoning (CoVe, Self-Consistency, ToT, GVU), shell-layer hallucination defense, epistemic tier system, 274/274 self-tests.
Turn your documents into verified quiz questions — RAG retrieval, evidence-span grounding, and multi-LLM cross-verification. Self-hosted, works offline with Ollama.
Add a description, image, and links to the chain-of-verification topic page so that developers can more easily learn about it.
To associate your repository with the chain-of-verification topic, visit your repo's landing page and select "manage topics."