OmniWired 9ce8d59470 docs: add local LLM on Mac guide (llama.cpp + MLX) ...

Comprehensive guide covering:
- llama.cpp and MLX (omlx) setup on Apple Silicon
- Model selection and memory optimization (quantized KV cache)
- Real benchmarks on M5 Max comparing both backends
- Hermes connection instructions

Cherry-picked from PR #2590.

2026-04-06 21:26:03 -07:00

..

developer-guide

feat(skills): add skill config interface + llm-wiki skill (#5635)

2026-04-06 13:49:13 -07:00

getting-started

docs: add post-update validation guidance

2026-04-06 21:26:03 -07:00

guides

docs: add local LLM on Mac guide (llama.cpp + MLX)

2026-04-06 21:26:03 -07:00

integrations

docs: add WSL2 networking guide for local model servers (#5616)

2026-04-06 13:01:18 -07:00

reference

fix: replace stale 'hermes login' refs with 'hermes auth' + fix credential removal re-seeding (#5670)

2026-04-06 17:17:57 -07:00

user-guide

docs: add 'setup' command to docker run example

2026-04-06 21:26:03 -07:00

index.md

docs: comprehensive documentation audit — fix stale info, expand thin pages, add depth (#5393)

2026-04-05 19:45:50 -07:00