petergpt.github.io
LLMs Bullshit Benchmark is listed in the WorkFlowAI resources directory under AI Benchmarks. Broken Premise Detection Benchmarks Official site: petergpt.github.io.
Broken Premise Detection Benchmarks
If you are assembling an AI stack — local models, agents, automation, or creative tooling — LLMs Bullshit Benchmark appears frequently in the AI Benchmarks category. Pair it with our automation workflows and MCP directory when you need runnable recipes, not just links.
Automated workflow: Chat with local LLMs using n8n and Ollama. This workflow integrates 4 different services: stickyNote, chainLlm, lmChatOllama, chatTrigger...
Automated workflow: Create AI-Ready Vector Datasets for LLMs with Bright Data, Gemini & Pinecone. This workflow integrates 14 different services: stickyNote,...
Automated workflow: Dynamically switch between LLMs Template. This workflow integrates 10 different services: stickyNote, code, chainLlm, set, stopAndError....
🐍 🏠 🍎 🪟 🐧 - An MCP server for [JupyterCAD](https://github.com/jupytercad/JupyterCAD) that allows you to control it using LLMs/natural language.
[](https://glama.ai/mcp/servers/@gzoonet/gzoo-cortex) 📇 🏠 - Local-first knowledge graph for developers. Watches project files, extracts entities and relationships via LLMs, builds a queryable knowledge graph with web dashboard and CLI. Provides 4 MCP tools: get_status, list_projects, find_entity, query_cortex.
🍎 🪟 🐧 ☁️ 🏠 🐍 - Magg: A meta-MCP server that acts as a universal hub, allowing LLMs to autonomously discover, install, and orchestrate multiple MCP servers - essentially giving AI assistants the power to extend their own capabilities on-demand.