agentleFS
Sign inStart free
Seeed-ProjectsSeeed-Projects/Seeed-Jetson-DevelopTool/skills/claude/deploy-live-vlm-webui/CLAUDE.md

Seeed-Jetson-DevelopTool / deploy-live-vlm-webui

CLAUDE.md57 starsChanged 4 months agoMITView on GitHub

Deploy Live VLM WebUI on reComputer Jetson for real-time Vision Language Model interaction via webcam. Installs Ollama with llama3.2-vision model and the live-vlm-webui Python package for browser-based VLM streaming and benchmarking. Requires JetPack 6.2 and USB camera.

  • Pipes a download into a shell
  • Installs packages

The file

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

3 rules. About 0 are common, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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 14
  2. Very specific:

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

    line 16
  3. Very specific:

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

    line 17

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.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
CLAUDE.md

Deploy Live VLM WebUI on reComputer Jetson

Live VLM WebUI streams your webcam to any VLM for live AI-powered visual analysis. This skill installs Ollama + llama3.2-vision and the WebUI on Jetson.

Execution model

Run one phase at a time. After each phase:

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

Prerequisites

RequirementDetail
HardwarereComputer Super J4012 (Orin NX 16GB) or similar
JetPack6.2
CameraUSB camera connected to Type-A port
NetworkInternet for model download (~7GB)

Phase 1 — Install and configure Ollama (~10–15 min)

curl -fsSL https://ollama.com/install.sh | sh
ollama pull llama3.2-vision:11b

Verify:

ollama list
# Expected: llama3.2-vision:11b listed

[OK] when model appears in ollama list. [STOP] if download fails or OOM.

Phase 2 — Install Live VLM WebUI (~3 min)

sudo apt install -y openssl python3-pip
python3 -m pip install --user live-vlm-webui
echo 'export PATH="$HOME/.local/bin:$PATH"' >> ~/.bashrc
source ~/.bashrc

Verify:

which live-vlm-webui

[OK] when the binary path is printed. [STOP] if pip install fails.

Phase 3 — Launch and configure WebUI (~2 min)

live-vlm-webui

Open browser at https://localhost:8090, then configure:

  1. VLM API Configuration → select ollama engine → select llama3.2-vision model
  2. Camera and App Control → select USB Camera
  3. Click Run to start inference

[OK] when inference results appear in the browser.

Failure decision tree

SymptomAction
Ollama install failsCheck internet. Retry: curl -fsSL https://ollama.com/install.sh | sh.
Model pull OOM or killed16GB RAM minimum for 11b model. Free memory by stopping other processes.
live-vlm-webui: command not foundEnsure ~/.local/bin is in PATH: source ~/.bashrc.
WebUI not accessible at port 8090Check firewall: sudo ufw allow 8090. Verify process is running.
USB camera not detected in WebUICheck camera: ls /dev/video*. Replug camera.
Inference very slowExpected on 16GB devices. Consider using a smaller vision model.

Reference files

  • references/source.body.md — Full Seeed Wiki tutorial with screenshots, demo video, and configuration details (reference only)

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