{"slug": "llama-macos-agentic-and-mcp-native-macos-front-end-for-llama-cpp", "title": "Llama-macOS – Agentic and MCP Native macOS Front End for Llama.cpp", "summary": "The GGML organization released Llama-macOS, a 4 MB macOS menu bar app that runs local LLMs via llama.cpp, featuring a local server at http://localhost:9931/v1, automatic model installation, and one-click model recommendations. The app is 100% local, supports GGUF models from Hugging Face, and includes options to expose the server to the network and append custom server arguments.", "body_md": "Llama is a macOS menu bar app for running local LLMs.\n\n```\nbrew install --cask llama-app\n```\n\nOr download from [Releases](https://github.com/ggml-org/Llama-macOS/releases).\n\nWhen you start Llama, it runs a local server at `http://localhost:9931/v1`\n\n.\n\nIf you have llama.cpp installed, Llama uses it. Otherwise, it installs a prebuilt binary for your Mac. Models you've already installed via llama.cpp show up in the app automatically. You can install any GGUF model from Hugging Face, and Llama also recommends models that fit your Mac's hardware.\n\nYou can chat with any model in the built-in WebUI, connect other apps (coding agents, chat UIs, editors), or use the API directly. Models load when requested and unload when idle, so they don't take up memory when not in use.\n\n**100% local**— Models run on your Mac; no data ever leaves it** Small footprint**—`4 MB`\n\nnative macOS app**Zero configuration**— models are auto-configured with optimal settings for your Mac** Model recommendations**— a built-in list of models your Mac can run, installable in one click** Standard storage**— models live in the Hugging Face cache, shared with`llama.cpp`\n\nand other tools**Built on llama.cpp**— from the GGML org, developed alongside llama.cpp\n\nList installed models:\n\n```\ncurl http://localhost:9931/v1/models\n```\n\nSend a message to a model:\n\n```\ncurl http://localhost:9931/v1/chat/completions \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"model\": \"ggml-org/gpt-oss-20b-GGUF:MXFP4\",\n    \"messages\": [{\"role\": \"user\", \"content\": \"Hello\"}]\n  }'\n```\n\nSee complete API reference in the llama.cpp server [docs](https://github.com/ggml-org/llama.cpp/tree/master/tools/server#api-endpoints).\n\n**Expose to network** — By default, the server is only accessible from your Mac (`localhost`\n\n). This option allows connections from other devices on your local network. Only enable this if you understand the security risks.\n\n```\n# bind to all interfaces (0.0.0.0)\ndefaults write app.llama.Llama exposeToNetwork -bool YES\n\n# or bind to a specific IP (e.g., for Tailscale)\ndefaults write app.llama.Llama exposeToNetwork -string \"100.x.x.x\"\n\n# disable (default)\ndefaults delete app.llama.Llama exposeToNetwork\n```\n\n**Custom server arguments** — Extra CLI arguments appended to the `llama serve`\n\ncommand, for server flags the app doesn't expose (e.g. `--api-key`\n\n). They come after the app's own flags, so where the server honors the later occurrence they can override the app's settings. Takes effect on the next server start.\n\n```\n# append custom arguments to the server command\ndefaults write app.llama.Llama extraServerArgs -string \"--api-key secret\"\n\n# remove (default)\ndefaults delete app.llama.Llama extraServerArgs\n```\n\n", "url": "https://wpnews.pro/news/llama-macos-agentic-and-mcp-native-macos-front-end-for-llama-cpp", "canonical_source": "https://github.com/ggml-org/Llama-macOS", "published_at": "2026-08-17 08:49:31+00:00", "updated_at": "2026-08-17 09:11:26.082408+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "developer-tools"], "entities": ["GGML", "Llama-macOS", "llama.cpp", "Hugging Face"], "alternates": {"html": "https://wpnews.pro/news/llama-macos-agentic-and-mcp-native-macos-front-end-for-llama-cpp", "markdown": "https://wpnews.pro/news/llama-macos-agentic-and-mcp-native-macos-front-end-for-llama-cpp.md", "text": "https://wpnews.pro/news/llama-macos-agentic-and-mcp-native-macos-front-end-for-llama-cpp.txt", "jsonld": "https://wpnews.pro/news/llama-macos-agentic-and-mcp-native-macos-front-end-for-llama-cpp.jsonld"}}