Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.

Last-night exam-cram coach as a Claude Agent Skill: turns your slides, notes and past papers into a chaptered knowledge base + quiz bank, teaches only what's in your materials, and never fabricates (measured 100% out-of-scope abstention). Bilingual EN/中文 — the 期末极速备考 skill.

Anti-hallucination research mode for Claude Code. Toggle on/off to enforce citation requirements and source grounding.

Score any document. Prove every claim.

Give your AI assistant real web search, full-page reading, and multi-source research with citations that are never fabricated.

Helix — a private, local-first, anti-hallucination Personal Health Intelligence platform on the ruvnet stack (Ruflo + RuVector + Cognitum Seed + MetaHarness/Darwin).

Native rules, hooks, and guards that prevent Claude Code and Codex from hallucinating code, duplicating files, or shipping unverified changes.

Reduce hallucinations through first-principles reasoning, verification, self-critique, and explicit uncertainty for AI agents.

Hierarchical RAG architecture scaling to 693K chunks on consumer hardware (4GB VRAM). Features 3-address routing, hybrid vector+graph fusion, and SetFit classification.

Persistent memory MCP server for AI agents — Rust, 19 tools, knowledge graph, Hebbian learning, episodic memory, contradiction detection, prospective triggers, Bayesian calibration, zero-config Docker setup.

Reliable research infrastructure for AI agents. Evidence-backed web search with citations, confidence scores, and Clarity anti-hallucination. MCP server, REST API, Python SDK.

65 plugins that turn Claude Code into an autonomous development team. 24 agents, 34 skills, 5 hooks. Includes 12-plugin anti-hallucination suite. One-line install.

A minimal graph engine for grounded AI — records, associates, and retrieves, but never invents. Written in Rust.

Archive snapshot repo of the original concept and 0-1 invention features, please utilize the constantly updated cypher-tempre-genesis repo for running the skill.

Local DeepSeek V4 proxy: reduces hallucinations strengthens system prompt following stops reasoning loops repairs empty tool-call replies — with built-in session analysis and GUI. / 本地 DeepSeek V4 代理：降低幻觉、增强 system prompt 遵循、防思维循环、修复空回复 自带会话分析与 GUI。

Evidence-grounded research agent for Claude Code & Codex: every claim gets a confidence rating + source-family tag, and adversarial gates block unsupported claims before they reach your report. Ships with a multi-model dispatcher.

.NET SQL Agent MCP server featuring raw SQL input, strict AST validation, and an embedded Admin UI. Eliminates LLM hallucinations and security risks across 6 major databases.

Git-versioned, provenance-grounded knowledge layer extracted from a codebase, served to humans and AI agents via MCP

A completion-claim gate for Claude Code. Refuses to let the agent say done without evidence.

Claude Code plugin: catches LLM-fabricated names before they hit disk + restores deleted sessions. 89.3% measured hallucination reduction (n=400, p<1e-26)