1 Commits

Author SHA1 Message Date
Joachim Friberg 0aabfc8a72 Add llama-server and open-webui apps for local LLM inference
- llama-server: llama.cpp REST API server, 8G memory, port 8080
- open-webui: Chat UI connecting to llama-server, 2G memory, port 3000
- Both include x-casaos metadata for ZimaOS app store
- README with model download instructions and API examples
2026-04-19 22:25:22 +02:00