REA
Verified · 34 days agoReverse engineer anything from your terminal or agent with one CLI and MCP server.
Detect fabrication and hallucination in any LLM output. 30+ models supported.
claude mcp add mcp-server -- npx -y @arkheia/[email protected]
Focuses on detecting fabrication or hallucination in LLM outputs across a large set of supported models. It is for teams building QA, evaluation, or trust-and-safety checks into model-assisted products. The problem area is important, but these claims should be treated carefully because hallucination detection is inherently hard and the repository signals still suggest an early-stage offering.
Reverse engineer anything from your terminal or agent with one CLI and MCP server.
Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.
AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
Draw and visually collaborate with your agents on tldraw's canvas.
Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.
Keyword research, site audits, rank tracking and AI visibility for your AI agent.