GAMESLASHllama.cpp
By ggml-org contributors
A local language-model runtime with GGUF support and an HTTP server offering OpenAI-compatible endpoints. A building block for dialogue backends, not a complete NPC system.
Use the official documentation to select a compatible model and installation route. The current guide documents llama cli for terminal interaction and llama serve for an API and web interface. Prototype the dialogue backend separately before connecting it to gameplay.
Game integration, character state, safeguards and latency testing remain your work. Model licensing and hardware needs vary. This listing is based on documentation only; no model was downloaded or run.
Official sources: https://llama.app/ · https://llama.app/docs/introduction · https://llama.app/docs/api