llama.app
Llama.cpp is listed in the WorkFlowAI resources directory under Local LLM Engines. Self-Hosted Transformer-Based LLMs · GitHub Official site: llama.app.
Self-Hosted Transformer-Based LLMs · GitHub
If you are assembling an AI stack — local models, agents, automation, or creative tooling — Llama.cpp appears frequently in the Local LLM Engines category. Pair it with our automation workflows and MCP directory when you need runnable recipes, not just links.
Integrate Manual Trigger and Sticky Note and Ollama and Microsoft Outlook and Split In Batches and Markdown and Set and Filter and If and LangChain and Merge...
Integrate Code and Split Out and LangChain and Ollama and Manual Trigger and Set and Merge and Filter and Execute Workflow Trigger and Aggregate and Sticky N...
Integrate Sticky Note and LangChain and Ollama automatically using n8n.
🐍 🏠 - Bridge to local Ollama LLM server. Run Llama, Mistral, Qwen and other local models through MCP.
[](https://glama.ai/mcp/servers/smart-mcp-proxy/mcpproxy-go) 🏎️ 🏠 🍎 🪟 🐧 - Local MCP proxy with BM25 tool filtering, quarantine security, activity logging, and web UI. Routes multiple servers through a single endpoint.