# llama_cpp C+ bindings for [llama.cpp](https://github.com/ggml-org/llama.cpp)'s C API, in two layers: - **Raw FFI** generated straight from the upstream headers with [`cpc-bindgen`](/docs/tooling) (`build.sh`), so the binding tracks the C API rather than reimplementing it. - **A hand-written safe facade** — `Session`, with `load` / `generate` / `tokenize` / `decode` / `sample` — over that raw layer, so day-to-day use is ownership-safe C+ rather than raw pointers. It links `libllama` and `libmtmd`; point the manifest `[link]` search-path at a local llama.cpp build: ```toml [link] search-paths = ["/path/to/llama.cpp/build"] ``` See [Modules & packages](/docs/modules-and-packages) for the `[link]` table. The `llama_cpp_smoke` recipe in the compiler repo shows greedy generation end to end. This is the runnable counterpart to the [field journal on porting ggml to C+](/blog/porting-llama-cpp-ggml-core-to-cplus).