Search

Fresh builds of llama.cpp with AMD ROCm™ acceleration

Home Assistant LLM integration for local OpenAI-compatible services (llamacpp, vllm, etc)

handwritten harness for AI, not vibecoded, everything is a module/plugin, tailor made for use with local models, tiny system prompt (around 1k by default), support for exclusive llamacpp features, strong security, strict zero-trust-in-the-ai policy (the code hard limits the ai, no amount of prompt engineering will bypass it)