SharpAI/DeepCamera is an open-source camera platform that analyzes surveillance video locally with vision-language models, object detection, and related AI skills. It is for home and CCTV monitoring, and its catalogue skills add pluggable camera capabilities to the platform.
Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add SharpAI/DeepCamera --skill yolo-detection-2026-coral-tpu-macosgit clone --depth 1 https://github.com/SharpAI/DeepCameraWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sharpai/deepcamera/yolo-detection-2026-coral-tpu-macos)<a href="https://agentmods.dev/skills/sharpai/deepcamera/yolo-detection-2026-coral-tpu-macos"><img src="https://agentmods.dev/badge/skills/sharpai/deepcamera/yolo-detection-2026-coral-tpu-macos/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sharpai/deepcamera/yolo-detection-2026-coral-tpu-macos"><img src="https://agentmods.dev/badge/skills/sharpai/deepcamera/yolo-detection-2026-coral-tpu-macos.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00031 | $0.01368 |
| Opus 5 | $0.00015 | $0.00684 |
| Sonnet 5 | $0.00006 | $0.00274 |
| Haiku 4.5 | $0.00003 | $0.00137 |
Grade A, and why
yolo-detection-2026-coral-tpu-macos scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Coral TPU Object Detection
Real-time object detection natively utilizing the Google Coral Edge TPU accelerator on your local hardware. Detects 80 COCO classes (person, car, dog, cat, etc.) with ~4ms inference on 320x320 input.
Requirements
- Python 3.9–3.13
How It Works
┌─────────────────────────────────────────────────────┐
│ Host (Aegis-AI) │
│ frame.jpg → /tmp/aegis_detection/ │
│ stdin ──→ ┌──────────────────────────────┐ │
│ │ Native Python Environment │ │
│ │ detect.py │ │
│ │ ├─ loads _edgetpu.tflite │ │
│ │ ├─ reads frame from disk │ │
│ │ └─ runs inference on TPU │ │
│ stdout ←── │ → JSONL detections │ │
│ └──────────────────────────────┘ │
│ USB ──→ Native System USB / edgetpu drivers │
└─────────────────────────────────────────────────────┘
- Aegis writes camera frame JPEG to shared
/tmp/aegis_detection/workspace - Sends
frameevent via stdin JSONL to the local Python instance detect.pyinvokes PyCoral and executes natively on the mapped USB Edge TPU- Returns
detectionsevent via stdout JSONL
Platform Setup
Linux
# Uses the official apt-get google-coral packages natively
./deploy.sh
macOS
# Downloads and installs the libedgetpu OS payload framework inline
./deploy.sh
Important Deployment Notice: The updated
deploy.shscript will natively halt execution and prompt you securely for your OSsudopassword to securely register the USB drivers (libedgetpu) system-wide. If you refuse the prompt, it gracefully outputs the exact terminal instructions for you to configure it manually.
Performance
| Input Size | Inference | On-chip | Notes |
|---|---|---|---|
| 320x320 | ~4ms | 100% | Fully on TPU, best for real-time |
| 640x640 | ~20ms | Partial | Some layers on CPU (model segmented) |
What ships with it
52 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- _config.yml 26 B
- .gitignore 1.3 KB
- .travis.yml 1.5 KB
- CODE_OF_CONDUCT.md 1.9 KB
- config.yaml 2.2 KB
- CONTRIBUTING.md 1.6 KB
- Contributions.md 1.0 KB
- deploy-linux.sh 7.5 KB runs code
- deploy-macos.sh 7.1 KB runs code
- deploy.sh 1.6 KB runs code
- docker_out.log 8.7 KB
- docker-compose.yml 1.3 KB
- docker/compile.sh 2.7 KB runs code
- docker/docker-compose.yml 1.4 KB
- docker/Dockerfile 3.2 KB
- docker/README.md 2.3 KB
- driver/edgetpu.dll 849 KB
- driver/libusb-1.0.dll 158 KB
- driver/UsbDk_1.0.22_x64.msi 6200 KB
- ext/lib/udev/rules.d/60-libedgetpu1-max.rules 164 B
- ext/usr/lib/x86_64-linux-gnu/libedgetpu.so.1 1157 KB
- ext/usr/lib/x86_64-linux-gnu/libedgetpu.so.1.0 1157 KB
- ext/usr/share/doc/libedgetpu1-max/changelog.gz 484 B
- ext/usr/share/doc/libedgetpu1-max/copyright 220 B
- ext/usr/share/lintian/overrides/libedgetpu1-max 276 B
- input.json 100 B
- lib/edgetpu.dll 849 KB
- lib/libedgetpu.so.1 1157 KB
- lib/libedgetpu1-max_16.0_amd64_0ac21f1924dd4b125d5cfc5f6d0e4a5e.deb 379 KB
- lib/libusb-1.0.dll 155 KB
- lib/local_deb/lib/udev/rules.d/60-libedgetpu1-max.rules 164 B
- lib/local_deb/usr/lib/x86_64-linux-gnu/libedgetpu.so.1 1157 KB
- lib/local_deb/usr/lib/x86_64-linux-gnu/libedgetpu.so.1.0 1157 KB
- lib/local_deb/usr/share/doc/libedgetpu1-max/changelog.gz 484 B
- lib/local_deb/usr/share/doc/libedgetpu1-max/copyright 220 B
- lib/local_deb/usr/share/lintian/overrides/libedgetpu1-max 276 B
- libedgetpu.deb 379 KB
- libedgetpu.so.1 1157 KB
- LICENSE 1.0 KB
- models/README.md 1.2 KB
- output.txt 694 B
- README.md 4.2 KB
- requirements.txt 701 B
- scripts/compile_model_colab.py 3.1 KB runs code
- scripts/compile_model.py 5.2 KB runs code
- scripts/detect.py 20 KB runs code
- scripts/detect.py.bak 24 KB
- scripts/install_pycoral.py 2.3 KB runs code
- scripts/tpu_probe.py 3.6 KB runs code
- skills.json 8.4 KB
- test2.jpg 97 KB
- wsl_test.py 560 B runs code
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 160 lines · 31 tokens per session scan A 1c8a75987b75
yolo-detection-2026-coral-tpu-macos is a skill published in the GitHub repository SharpAI/DeepCamera (3,051 stars, last pushed 2mo ago), licensed MIT. It adds 31 tokens to every session and 1,368 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
flow-nexus-neural
Train and deploy neural networks in distributed E2B sandboxes with Flow Nexus.
physicsnemo-shard-tensor
Official NVIDIA-authored guidance for PhysicsNeMo ShardTensor domain parallelism — integrate domain parallelism into training/inference scripts (new or existing) with DDP or FSDP2, write and register shard patches to enable new layers/ops, and bootstrap multi-GPU correctness tests. Use when working with ShardTensor…
physicsnemo-discover
Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment…
perforatedai
Expert in PerforatedAI library for adding artificial dendrites to PyTorch neural networks. Triggers: 'Perforate my model' (start interactive setup), 'debug my perforated model' (debug/optimize existing integration), 'load my perforated model for inference' (deploy trained models). Also use when: debugging dendrite…
perforatedai-analyze
Analyze PerforatedAI training results and provide optimization recommendations. Trigger: 'Analyze my perforated results' (after training completes). Reviews CSV outputs, identifies performance patterns, recommends configuration improvements. For initial setup or debugging, use the perforatedai skill instead.
perforatedai-distributed
Multi-GPU setup for PerforatedAI with DataParallel or DistributedDataParallel (DDP). Invoked automatically by the perforatedai skill when multi-GPU training is detected. Handles initialization workflow, checkpoint loading, rank 0 handling, and shell script generation for DDP.