gapi-setup

A setup guide for Gapi, an embeddable API gateway that connects streaming AI microservices, on an NVIDIA Jetson Orin computer.

In plain words
What is it for?
Use it to install the ARM64 Gapi container, open its web interface, configure workflows, and connect AI microservices on a Jetson Orin.
Why use it?
It provides the installation and checks needed to run Gapi in Docker, including its workflow interface and downloadable community services.

Skill for Claude CodeCodex

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.

agentmods
npx agentmods add skills/seeed-projects/seeed-jetson-developtool/gapi-setup
Any agent
npx skills add Seeed-Projects/Seeed-Jetson-DevelopTool --skill gapi-setup
Clone the repo
git clone --depth 1 https://github.com/Seeed-Projects/Seeed-Jetson-DevelopTool

Made for: Claude Code, Codex.

Per session 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 816 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 3 findings. Scan, not verified.
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 $0.00055 $0.00816
Opus 5 $0.00028 $0.00408
Sonnet 5 $0.00011 $0.00163
Haiku 4.5 $0.00006 $0.00082

Measured 2d ago against content hash c52ec4e669a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

gapi-setup scanned grade D with 3 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 2d 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.

| `docker: command not found` | Install Docker: `curl https://get.docker.com \| sh && sudo systemctl enable --now docker` |

Downloads and executes remote codehighSupply chain

curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.

| `docker: command not found` | Install Docker: `curl https://get.docker.com \| sh && sudo systemctl enable --now docker` |

Makes network callslowCapability

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

curl -L https://raw.githubusercontent.com/genai-nerds/Gapi/main/gapiConfigs.zip -o gapiConfigs.zip
seeed_jetson_develop/skills/openclaw/gapi-setup/SKILL.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Getting Started with Gapi on Jetson


Execution model

Run one phase at a time. After each phase:

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

Prerequisites

Requirement Details
Hardware Any NVIDIA Jetson Orin
Software Docker installed and running
Storage ≥1.3 GB for Gapi server
Network Required for Docker pull and web access

Phase 1 — Install Gapi server (~5 min)

mkdir ~/gapiData && cd ~/gapiData
curl -L https://raw.githubusercontent.com/genai-nerds/Gapi/main/gapiConfigs.zip -o gapiConfigs.zip
unzip -q gapiConfigs.zip
docker run -d --name gapi --network host -v ~/gapiData:/opt/gapi/vdata genainerds/gapi:arm64 /bin/bash -c "cd /opt/gapi/bin && ./startGapi.sh"

Verify the container is running:

docker ps | grep gapi

[OK] when the gapi container is listed as running. [STOP] if Docker pull or container start fails.


Phase 2 — Log in to Gapi WebUI (~1 min)

Open a browser and navigate to:

http://<jetson-ip>:8090

Default credentials:

  • User: root
  • Password: !gapi2024

Change the password in Settings after first login. SSL cert setup is covered in the Gapi docs.

[OK] when you can log in and see the Gapi dashboard.


Phase 3 — Explore workflows and micro services

Workflows visually connect Nodes that talk to Micro Services and APIs. Each Node can append or reference rolling Transaction data.

To set up Community Micro Services:

  1. Go to the Micro Services tab in the Gapi UI
  2. Follow the instructions in the blue box to download your custom configuration
  3. Follow the per-service install instructions below that

Community Micro Service storage requirements: ~4 GB to ~10 GB each.

[OK] when at least one micro service is connected and visible in the UI.

Read the full file on GitHub · 100 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. 2d ago First seen · 100 lines · 55 tokens per session scan D c52ec4e669a5

Subscribe to this mod's changes

gapi-setup is a skill published in the GitHub repository Seeed-Projects/Seeed-Jetson-DevelopTool (54 stars, last pushed 3d ago), licensed MIT. It adds 55 tokens to every session and 816 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 3 findings (asks for root, downloads and executes remote code, 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

doca-container-deployment

Use this skill when the user is hands-on deploying an in-bundle DOCA service container (Argus, DMS, Firefly, or UROM service) on a BlueField — kubelet standalone watching a static-pod manifests directory, YAML pod-spec drop, kubelet status / ENTRYPOINT logs / per-service liveness, smoke-before-bulk, and the layered…

NVIDIA/skills · 234 tokens

together-kueue

Install and use the Kueue job-queueing controller on a Together AI Kubernetes GPU cluster to gate jobs on quota. Covers installing Kueue, defining ResourceFlavor, ClusterQueue, and LocalQueue quota, submitting jobs to a queue, and watching quota admit or suspend them. Reach for it when a Together cluster's GPU pool…

togethercomputer/skills · 124 tokens

cloud-run

Deploy headless robotics / sim / demo containers to Google Cloud Run: the build → Artifact Registry → Cloud Run path plus the gotchas that bite sim workloads (no UDP multicast for gz-transport/DDS, CPU allocated only while a request is open, session affinity for per-visitor instances, request timeout / concurrency for…

robium-ai/robium · 224 tokens

mk8s-byok

Runs workloads on your own hardware and provisions managed Kubernetes (mk8s) clusters on Control Plane. Use when the user asks about bare metal, on-prem, data centers, their own servers, mk8s, BYOK, or node pools.

controlplane-com/ai-plugin · 56 tokens

balenify

Guide for converting Docker projects to run on balenaCloud. Use this skill when balenifying or converting an existing Docker/docker-compose project for balena, writing or modifying Dockerfile.template files, setting up docker-compose.yml for balena fleets, choosing between Dockerfile.template and plain Dockerfile for…

balena-io-experimental/skills · 151 tokens

cloud-run-basics

Manages Cloud Run services, jobs, and worker pools. Use when you need to deploy applications responding to HTTP requests (services), run event-triggered or scheduled tasks (jobs), or handle always-on pull-based background processing (worker pools).

google/skills · 53 tokens