Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Format LLM output using Langchain on Jetson for structured smart home control signals. Deploys a local chatbot with Gradio UI that uses LlamaCpp and Langchain's StructuredOutputParser to produce JSON-formatted responses. Requires JetPack 5.0+ and a GGUF model.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Set up the LeRobot environment on NVIDIA Jetson (SO-ARM / JetPack 6.0+). Installs Seeed-fork LeRobot with GPU-enabled torch 2.8, pinned numpy 1.26, OpenCV 4.10, and resolves the torch-overwrite trap from editable install. Use when the user asks to install, rebuild, or fix LeRobot on Jetson.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Distribute LLM inference across multiple Jetson devices using llama.cpp RPC backend with CUDA. Build from source with RPC+CUDA, convert models to GGUF, and run multi-node inference for horizontal scaling. Requires two Jetson devices with JetPack 6.x+.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Deploy a local LLM agent on Jetson Orin NX that translates natural language into structured JSON commands for hardware interface control (GPIO, PWM, I2C). Uses Ollama with a custom system prompt, FastAPI backend, and confidence-gated execution. Requires JetPack and Python 3.8+.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Build a voice-interactive AI chatbot on Jetson using Ollama (LLM), NVIDIA Riva (STT/TTS), and Docker. Supports real-time speech-to-text, local LLM inference, and text-to-speech — fully offline with no cloud dependencies. Requires JetPack 6.0+ and NGC API key.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Build a voice-interactive AI chatbot on Jetson for physical AI applications using Ollama (LLM), NVIDIA Riva (STT/TTS), and Docker. Fully offline voice assistant with real-time speech recognition and synthesis. Requires JetPack 6.0+ and NGC API key.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Run local text-to-image generation on Jetson Orin NX 16GB using Stable Diffusion. Covers three approaches — KerasCV, Hugging Face diffusers, and NVIDIA Jetson Containers (AUTOMATIC1111 WebUI). Includes a Flask API for on-demand image generation. Requires JetPack 5.1.1+.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Deploy a local RAG chatbot on Jetson using LlamaIndex + ChromaDB + quantized Llama2-7b (MLC). Uses jetson-containers Docker environment. Requires Jetson with ≥16GB RAM and JetPack 5.1+.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Install and configure Lumeo no-code video analytics gateway on NVIDIA Jetson. Covers account creation, gateway deployment, camera linking, and building a people detection pipeline. Requires Jetson with JetPack 5.1+ and internet access.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Run MaskCam face mask detection on Jetson Nano 4GB using Docker. Streams results via RTSP. Requires JetPack 4.6 and a USB camera.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Deploy real-time YOLO11 object detection and VGGT 3D reconstruction on Jetson AGX Orin with up to 8 GMSL cameras via the reServer Industrial J501 carrier board and GMSL extension board. Requires JetPack 6.2 and CUDA 12.6.
Seeed-Projects/Seeed-Jetson-DevelopTool
Skill Claude CodeCodex
Install and configure NEQTO Engine for Linux on reComputer J30 series. Covers account creation, API key setup, daemon installation, device registration, and Hello World script deployment via NEQTO Console. Requires any Linux-based Jetson with ≥32MB disk and network adapter.
Seeed-Projects/reCamera_Gimbal-OpenClaw
Skill Claude CodeCodex
A skill for controlling a reCamera Gimbal, a network-connected edge AI camera with a motorized mount.