deploy/launchd/com.offgrid.hermes.plist

<?xml version="1.0" encoding="UTF-8"?>
<!-- Hermes brain: an OpenAI-compatible llama.cpp server the backend points at via
     INFERENCE_BASE_URL. Template — scripts/setup_mac.sh fills the __PLACEHOLDERS__
     and installs into ~/Library/LaunchAgents. -->
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN" "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
  <key>Label</key><string>com.offgrid.hermes</string>
  <key>ProgramArguments</key>
  <array>
    <string>__LLAMA_SERVER__</string>
    <string>-m</string><string>__MODEL_GGUF__</string>
    <string>--host</string><string>127.0.0.1</string>
    <string>--port</string><string>8080</string>
    <string>--ctx-size</string><string>8192</string>
    <string>--jinja</string>          <!-- enable the tool-calling chat template -->
  </array>
  <key>RunAtLoad</key><true/>
  <key>KeepAlive</key><true/>
  <key>StandardOutPath</key><string>__HOME__/Library/Logs/offgrid-hermes.log</string>
  <key>StandardErrorPath</key><string>__HOME__/Library/Logs/offgrid-hermes.log</string>
</dict>
</plist>