Document live OpenVINO NPU sidecars

openvino-genai-npu-worker/README.md

@@ -19,7 +19,7 @@ The worker does not write memory, does not restart Atlas/Hermes, does not change
 - `worker.py` — stdlib HTTP API plus CLI wrapper.
 - `smoke_llm_npu.py` — direct GenAI smoke test with NPU busy-time verification.
 - `tests/test_worker.py` — unit tests with a fake GenAI pipeline and synthetic busy-time counter.
-- `systemd/openvino-genai-npu-worker.service` — optional user-service template; not installed by this prototype.
+- `systemd/openvino-genai-npu-worker.service` — reviewed local-only user-service template for `127.0.0.1:18820`.
 
 ## Model/cache
 
@@ -129,9 +129,18 @@ OV_GENAI_NPU_PORT=18820
 
 Only `127.0.0.1` is accepted by the current prototype; wider binds require an explicit code change and approval.
 
-## Optional systemd user service
+## Systemd user service
 
-A draft unit exists at `systemd/openvino-genai-npu-worker.service` for later review. Do not copy, enable, or autostart it unless Will explicitly approves persistent service enablement. Foreground smoke on `127.0.0.1:18820` plus positive sysfs NPU busy-time delta is required before any installation discussion.
+A reviewed local-only unit exists at `systemd/openvino-genai-npu-worker.service` for persistent background use after foreground smoke succeeds with a positive NPU busy-time delta:
+
+```bash
+install -m 0644 systemd/openvino-genai-npu-worker.service ~/.config/systemd/user/openvino-genai-npu-worker.service
+systemctl --user daemon-reload
+systemctl --user enable --now openvino-genai-npu-worker.service
+systemctl --user status openvino-genai-npu-worker.service --no-pager
+```
+
+The service remains isolated: do not route primary Atlas/Hermes chat, gateway output, or automatic memory writes to it without a separate approved integration.
 
 ## Safety boundaries