agentleFS
Sign inStart free
Seeed-ProjectsSeeed-Projects/Seeed-Jetson-DevelopTool/skills/codex/cvedia-setup/AGENTS.md

Seeed-Jetson-DevelopTool / cvedia-setup

AGENTS.md57 starsChanged 4 months agoMITView on GitHub

Install and run CVEDIA-RT AI inference engine on NVIDIA Jetson for pre-built computer vision applications (crowd estimation, drone detection, vehicle counting, etc.). Requires JetPack 5.1 and a CVEDIA account.

The file

We split this AGENTS.md into the rules it gives an agent

5 rules. About 0 are common, 3 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run one phase at a time. After each phase:

    line 20
  2. Very specific:

    If output contains [STOP] → stop immediately, consult the failure decision tree

    line 21
  3. Very specific:

    If output ends with [OK] → tell the user "Phase N complete" and proceed

    line 22
  4. Distinctive:

    Wait for model and video files to download

    line 90
  5. Distinctive:

    Stop and restart the application for changes to take effect

    line 92

≈ “Common” is an estimate: at least 1 in 5 of the 40,246 AGENTS.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
AGENTS.md

CVEDIA-RT on NVIDIA Jetson

CVEDIA-RT is a modular, cross-platform AI inference engine with pre-loaded applications: crowd estimation, drone detection, fall detection, lane occupancy, vehicle type counter, package detection, and more.

Hardware: NVIDIA Jetson device (tested with reComputer J4012) Software: JetPack 5.1 with all SDK components, internet connection Account: CVEDIA (free sign-up at rt.cvedia.com)

Execution model

Run one phase at a time. After each phase:

  • If output contains [STOP] → stop immediately, consult the failure decision tree
  • If output ends with [OK] → tell the user "Phase N complete" and proceed

Phase 1 — prerequisites check (~30 s)

cat /etc/nv_tegra_release
# Expected: R35 (release) for JetPack 5.x
dpkg -l | grep nvidia-jetpack

[OK] when JetPack 5.1+ with SDK components confirmed. [STOP] if JetPack version is incompatible.

Phase 2 — download CVEDIA-RT (human action + ~5 min)

  1. Visit https://rt.cvedia.com/ and sign in (or create account)
  2. Click Download under "NVIDIA Jetson"
  3. Select "Docker (Recommended)" to download the tar.gz installer

Transfer the file to the Jetson device.

[OK] when tar.gz file is on the Jetson.

Phase 3 — install CVEDIA-RT (~3 min)

mkdir -p ~/cvedia && cd ~/cvedia
tar -xzvf <filename.tar.gz>
sudo ./install.sh

Respond to installer prompts as needed.

[OK] when installation completes without errors.

Phase 4 — run CVEDIA-RT (~1 min)

With internet (first run, downloads models):

./run.sh

Without internet (after first online run):

./run.sh -U

Expected: CVEDIA-RT application opens with pre-loaded solutions.

[OK] when the application UI is visible.

Phase 5 — explore applications (~5 min)

  1. Click on a solution category (e.g. intelligent-transportation-systems)
  2. Click the run button next to a solution (e.g. lane-occupancy)
  3. Wait for model and video files to download
  4. Configure video source: gear icon → Edit Source → select camera/file → Save Instance
  5. Stop and restart the application for changes to take effect

[OK] when inference results are visible on the video feed.

Failure decision tree

SymptomAction
install.sh failsVerify Docker is installed with nvidia runtime. Check JetPack version.
run.sh hangs or crashesCheck Docker logs. Ensure sufficient disk space and memory.
Application won't start offlineMust run each solution at least once with internet first.
Video source not workingStop application, reconfigure source, restart. Check camera connectivity.
Low FPS / poor performanceEnsure JetPack SDK components are installed. Check GPU utilization with tegrastats.

Reference files

  • references/source.body.md — Original Seeed wiki with screenshots and application examples

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free