Initial commit: llm-router — smart OpenAI/Anthropic/Ollama router

A stdlib pre-router in front of Ollama with LiteLLM backend:
- auto model selection by content/tools/modality, with fallbacks
- OpenAI /v1, Anthropic /v1/messages, and Ollama-native /api/* endpoints
- Whisper-shaped /v1/audio/transcriptions + in-chat audio
- key-based fleet policies (e.g. force a client onto uncensored models)
- optional Bearer auth; launchd/systemd service install
- benchmark harnesses (speed, quality, agentic tool use) with sample results

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

apikey.example

@@ -0,0 +1,8 @@
+Copy this file to `.apikey` and put a single secret token in it (no newline needed).
+When `.apikey` exists, run.sh sets ROUTER_API_KEY and the router requires
+`Authorization: Bearer <token>` on all /v1 requests.
+
+If `.apikey` does NOT exist, the router runs OPEN (no auth) — fine on a trusted
+LAN, NOT fine if you expose it to the internet.
+
+Generate one:  openssl rand -hex 24