Inspect RuView sensing hardware, including ESP32 nodes, mmWave radars, and LiDAR distance sensors. Find connected devices, read logs and live measurements, and use SSH to access supported read-only tools on another machine.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Reach RuView sensing hardware from the machine it is attached to — ESP32 CSI nodes (serial + UDP stream), 60 GHz MR60BHA2 / 24 GHz LD2410 mmWave radars, RPLIDAR and iPhone LiDAR — and from other machines over SSH, read-only.
설치하기 전에 에이전트에게 전달되는 지시 내용을 확인할 수 있습니다.
Hardware tools must run on the host the device is plugged into. A cloud
agent cannot see your USB ports. Run npx @ruvnet/ruview locally, start a
local Claude Code session there (claude remote-control in the repo if you
want to drive it from the Claude app), or add the machine as an SSH host.
npx @ruvnet/ruview doctor --group python,serial,devices,remote
npx @ruvnet/ruview devices # USB VID:PID → likely ESP32 / mmWave / RPLIDAR + confirm command
| Device | Command | Confirms |
|---|---|---|
| ESP32 node (USB) | ruview doctor --port <p> --probe, ruview monitor --port <p> | chip id; CSI callbacks in the serial log (the monitor never resets the node; C6/S3 USB-Serial/JTAG builds log on the native USB port) |
| ESP32 / Realtek node (network) | ruview esp32 --seconds 10 [--udp-port 5005] | per-node CSI rate, sequence loss, RSSI, CSI shapes, device vitals; Realtek RAC1 CSI and heartbeat-only senders |
| Realtek RTL8721Dx (USB, PL2303) | ruview monitor --port <p> --baud 1500000 | RUVIEW_CSI: frame # lines in the Ameba log |
| Live CSI → kernel | ruview esp32 --seconds 45 --analyze [--node-id N] [--backend napi] | kernel vitals summary at the measured frame rate (no reference measurement) |
| 60 GHz MR60BHA2 | ruview mmwave --port <p> --model mr60bha2 | valid frames, checksum errors, presence/distance/device HR+BR |
| 24 GHz LD2410 | ruview mmwave --port <p> --model ld2410 | target state and distances |
| RPLIDAR | ruview lidar --source rplidar --port <p> [--baud 115200] | points, revolutions, range, angular coverage |
| iPhone LiDAR | export RUVIEW_LIDAR_TOKEN=…; ruview lidar --source iphone --url ws://HOST:8787/ws/lidar | depth frame rate, confident fraction, median depth |
The UDP capture cannot share port 5005 with a running sensing server; stop the server or have the nodes target another port.
npx @ruvnet/ruview hosts add --name lab-pi --ssh ruv@lab-pi.local
ssh ruv@lab-pi.local true # pin the host key once
npx @ruvnet/ruview hosts run --host lab-pi --tool ruview_devices_scan
npx @ruvnet/ruview hosts run --host lab-pi --tool ruview_mmwave_read --args-json '{"port":"/dev/ttyUSB0"}'
Remote hosts run a pinned @ruvnet/ruview and accept only read-only tools.
Flash, train, and calibrate on the host itself.
Device readouts are MEASURED readings, not accuracy results. mmWave
heart/breathing values are the radar's own estimates. Hardware validation
still means a captured log or stream from real silicon, recorded with the
command that produced it.
아직 리뷰가 없습니다. 사용해 본 소감을 남겨 주세요.
로그인 없이 쓸 수 있습니다. 사용 후기, 질문, 작동하지 않은 환경 등을 편하게 남겨 주세요.
아직 댓글이 없습니다. 첫 댓글을 남겨 보세요.
Build advanced AgentDB workflows with database synchronization, multiple databases, and search that combines meaning with attribute filters. Covers similarity measures, diverse search results, and operational patterns for distributed AI applications.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Create AgentDB learning plugins that use recorded experience to improve agent decisions. Choose a learning method, store states, actions, and rewards, train models, and evaluate suggested actions through CLI and API workflows.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Build AI agents that retain conversation history, user preferences, and useful interaction patterns with AgentDB. The skill covers persistent storage, meaning memories survive between sessions, plus retrieval, context management, and ReasoningBank integration.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Tune AgentDB memory use and search speed through quantization, which stores vectors more compactly, search indexes, caching, and batch operations. Includes configuration examples and benchmarks to help balance accuracy, speed, and storage as datasets grow.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Build document search with AgentDB that finds related content by meaning. Store documents as numerical representations, combine similarity search with metadata filters, and retrieve relevant passages for systems that generate answers using source material.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Automate browser tasks with agent-browser, using snapshots that label page elements for the agent. Handle login flows, fill and submit forms, extract page information, and capture screenshots through a repeatable navigation and interaction workflow.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.