deploy-riva-llama2

deploy-riva-llama2 is a skill for Claude Code, Codex from Seeed-Projects/Seeed-Jetson-DevelopTool. It costs 88 tokens per session (1,313 once invoked), scanned B, original, MIT.

A setup guide for building a voice chatbot that runs locally on an NVIDIA Jetson AGX Orin. It combines speech recognition, spoken responses, and Meta’s Llama 2 language model.

In plain words
What is it for?
Use it to install NVIDIA Riva and Llama 2, configure the Jetson, and create a Python chatbot that listens through a microphone and replies through a speaker.
Why use it?
It provides an ordered installation process for the required servers, models, accounts, hardware, and voice demo while keeping processing on the device.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to install NVIDIA Riva and Llama 2, configure the Jetson, and create a Python chatbot that listens through a microphone and replies through a speaker.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seeed-projects/seeed-jetson-developtool/deploy-riva-llama2
Install

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.

Any agent
npx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill deploy-riva-llama2
Clone the repo
git clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopTool

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for deploy-riva-llama2

README.md
[![agentmods](https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/deploy-riva-llama2.svg)](https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/deploy-riva-llama2)
Your own site
<a href="https://agentmods.dev/skills/seeed-projects/seeed-jetson-developtool/deploy-riva-llama2"><img src="https://agentmods.dev/badge/skills/seeed-projects/seeed-jetson-developtool/deploy-riva-llama2.svg" alt="Measured on agentmods" height="20"></a>
Per session 88 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,313 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 6 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Rogue Agent · line 37
    Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
    Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
  • medium Data Exfiltration · line 38
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
  • medium Privilege Escalation · line 70
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 81
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 87
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
  • medium Privilege Escalation · line 88
    Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.
    Fix: Avoid sudo/root unless strictly required. Prefer least-privilege patterns. If elevation is needed, document the justification and scope.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00088 $0.01313
Opus 5 $0.00044 $0.00656
Sonnet 5 $0.00018 $0.00263
Haiku 4.5 $0.00009 $0.00131

Measured 7d ago against content hash 67c120552fda, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade B, and why

deploy-riva-llama2 scanned grade B with 2 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 7d 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

sudo bash -c 'cat > /etc/docker/daemon.json << EOF

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

wget --content-disposition https://api.ngc.nvidia.com/v2/resources/nvidia/ngc-apps/ngc_cli/versions/3.36.0/files/ngccli_arm64.zip
seeed_jetson_develop/skills/openclaw/deploy-riva-llama2/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Local Voice Chatbot — Riva + Llama2 on Jetson

Combines NVIDIA Riva for speech recognition/synthesis with Llama2 for conversational AI, all running locally on Jetson for privacy and low latency.


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

Requirement Detail
Hardware Jetson AGX Orin 32GB+ (e.g. AGX Orin H01 Kit)
JetPack 5.1.1 or later
Audio Speaker + microphone (e.g. ReSpeaker USB Mic Array)
NGC account Required for Riva model download
HuggingFace token Required for Llama2 model access
Docker Installed with NVIDIA runtime

Phase 1 — Configure NGC CLI (~3 min)

cd ~ && mkdir -p ngc_setup && cd ngc_setup
wget --content-disposition https://api.ngc.nvidia.com/v2/resources/nvidia/ngc-apps/ngc_cli/versions/3.36.0/files/ngccli_arm64.zip
unzip ngccli_arm64.zip
chmod u+x ngc-cli/ngc
echo "export PATH=\"\$PATH:$(pwd)/ngc-cli\"" >> ~/.bash_profile
source ~/.bash_profile
ngc config set

Enter your NGC API Key when prompted (obtain from NGC → Account → Setup → Get API Key).

[OK] when ngc config set completes. [STOP] if download or auth fails.


Phase 2 — Install and start Riva server (~20–30 min)

cd ~ && mkdir -p riva_setup && cd riva_setup
ngc registry resource download-version nvidia/riva/riva_quickstart_arm64:2.13.1
cd riva_quickstart_v2.13.1

Edit config.sh to disable unused services:

sed -i 's/service_enabled_nlp=true/service_enabled_nlp=false/' config.sh
sed -i 's/service_enabled_nmt=true/service_enabled_nmt=false/' config.sh

Configure Docker for NVIDIA runtime:

sudo bash -c 'cat > /etc/docker/daemon.json << EOF
{
    "default-runtime": "nvidia",
    "runtimes": {
        "nvidia": {
            "path": "nvidia-container-runtime",
            "runtimeArgs": []
        }
    }
}
EOF'
sudo systemctl restart docker

Read the full file on GitHub · 167 lines

Files

What ships with it

2 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.

Changes

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.

  1. 7d ago First seen · 167 lines · 88 tokens per session scan B 67c120552fda

Subscribe to this mod's changes

deploy-riva-llama2 is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed today), licensed MIT. It adds 88 tokens to every session and 1,313 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

spark-environment-setup

Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13). Use when installing PyTorch/Unsloth/TRL/vLLM on DGX Spark, hitting libcudart or wheel-ABI errors on aarch64, or choosing between NGC containers and bare pip installs.

wshobson/agents · 76 tokens

spark-memory-thermal-ops

Manage unified memory and thermals during long-running ML jobs on NVIDIA DGX Spark. Use when planning memory headroom for a training run on GB10, when a job OOMs on unified memory, or when monitoring temperature and power during multi-hour training.

wshobson/agents · 59 tokens

spark-training-gotchas

Preflight and diagnose the ten known failure modes for ML training on NVIDIA DGX Spark. Use when a training run on DGX Spark fails to start, OOMs below the 128GB limit, slows down mid-run, or before any multi-hour training job on GB10.

wshobson/agents · 63 tokens

llama-cpp

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

davila7/claude-code-templates · 76 tokens

amc-run-rtsp-calibration

Calibrate a new dataset from live RTSP camera streams via the AutoMagicCalib REST API. Use when the user provides RTSP URLs or asks to calibrate live cameras; VIOS records clips, AMC ingests them, then runs calibration.

NVIDIA/skills · 59 tokens

amc-run-video-calibration

Calibrates pre-recorded cam.mp4 datasets through the AutoMagicCalib REST API. Use for user-supplied local MP4s; route live RTSP streams to amc-run-rtsp-calibration.

NVIDIA/skills · 57 tokens