feat: localchat, a Go + Templ + HTMX chat app for local Gemma models

Streams replies over SSE from any OpenAI-compatible server (oMLX,
llama.cpp, Ollama, ...). Single binary that can install itself as an
OS service; docker compose bundles llama.cpp + Gemma 4 E2B.

.env.example

@@ -0,0 +1,14 @@
+# Where your OpenAI-compatible model server lives (llama.cpp, oMLX, Ollama, LM Studio, ...)
+LLM_BASE_URL=http://127.0.0.1:8080/v1
+# Leave empty to use the first model the server lists
+LLM_MODEL=
+# Only if your server requires one
+LLM_API_KEY=
+
+# Make it yours
+LOCALCHAT_TITLE=localchat
+# SYSTEM_PROMPT="You are a patient Go tutor. Keep answers short and show small code examples."
+
+# LOCALCHAT_ADDR=127.0.0.1:3000
+# MAX_HISTORY=20
+# LLM_TIMEOUT=5m