Seeed-Jetson-DevelopTool / jetson-resource-index
AGENTS.md57 starsChanged 4 months agoMITView on GitHub
Knowledge base index of Jetson software stack, modules, and resources — JetPack SDK, CUDA, TensorRT, DeepStream, TAO, Triton, Riva, Isaac, and Seeed reComputer module lineup with flash guides.
Where files are headingNew AGENTS.md files have more rules about keeping secrets out of the code, and fewer about code style.
Of the AGENTS.md files we read, the 31,774 first seen in the last six months, against the older ones: the kind of rule that gained most share, and the kind that lost most. About files like this in general, not this one, and an estimate, since a kind is a pattern in the words.
In this repository297 other files it gives its agents.
- AGENTS.mdAGENTS.md
- ai-nvrAGENTS.md
- allxon-ota-updateAGENTS.md
- allxon-setupAGENTS.md
- alwaysai-setupAGENTS.md
- backup-restoreAGENTS.md
- bsp-source-buildAGENTS.md
- clawdbot-developmentAGENTS.md
- cochl-sense-setupAGENTS.md
- cvedia-setupAGENTS.md
- dashcamnet-xavier-nx-multicameraAGENTS.md
- deciai-setupAGENTS.md
- deepseek-quick-deployAGENTS.md
- deploy-deepseek-mlcAGENTS.md
- deploy-depth-anything-v3AGENTS.md
- deploy-diaAGENTS.md
- deploy-efficient-vision-engineAGENTS.md
- deploy-frigateAGENTS.md
- deploy-live-vlm-webuiAGENTS.md
- deploy-nvbloxAGENTS.md
- deploy-ollama-anythingllmAGENTS.md
- deploy-riva-llama2AGENTS.md
- developtool-deviceAGENTS.md
- disk-encryptionAGENTS.md
- diy-bsp-buildAGENTS.md
- ethercat-communicationAGENTS.md
- ethercat-setupAGENTS.md
- finetune-llm-llama-factoryAGENTS.md
- fix-browser-snap-jetsonAGENTS.md
- gapi-setupAGENTS.md
- generative-ai-introAGENTS.md
- gpt-oss-liveAGENTS.md
- gr00t-n1-5-deploy-thorAGENTS.md
- gr00t-n1-6-deploy-agxAGENTS.md
- hardhat-setupAGENTS.md
- hybrid-bsp-dk-to-recomputerAGENTS.md
- imx477-a603-setupAGENTS.md
- j501-viola-fruit-sortingAGENTS.md
- jetpack5-ssd-boot-fixAGENTS.md
- jetpack-flash-wsl2AGENTS.md
- jetpack-jetson-overviewAGENTS.md
- jetpack-ota-updateAGENTS.md
- jetson-ai-toolsAGENTS.md
- jetson-docker-setupAGENTS.md
- jetson-faqAGENTS.md
- jetson-pc-wired-shareAGENTS.md
- jetson-project-galleryAGENTS.md
- jetson-tutorial-exercisesAGENTS.md
- ko-module-buildAGENTS.md
- l4t-differencesAGENTS.md
- langchain-output-formattingAGENTS.md
- lerobot-env-setupAGENTS.md
- llama-cpp-rpc-distributedAGENTS.md
- llm-interface-controlAGENTS.md
- local-chatbot-multimodalAGENTS.md
- local-chatbot-physicalAGENTS.md
- local-llm-text-to-imageAGENTS.md
- local-rag-llamaindexAGENTS.md
- lumeo-setupAGENTS.md
- maskcam-nanoAGENTS.md
- The first 60 shown.
The file
We split this AGENTS.md into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 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.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 57
All Jetson modules: https://developer.nvidia.com/embedded/jetson-modules
≈ “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.
Files
Jetson Resource Index
This is a knowledge-base skill. Use it to direct users to NVIDIA Jetson software, hardware modules, and Seeed reComputer documentation.
Execution model
This skill is informational — no destructive commands. Match the user's question to the relevant resource section below.
Phase 1 — identify what the user needs
Determine the category:
- Jetson software stack / SDK → Section A
- Jetson hardware modules → Section B
- Seeed reComputer flash guides → Section C
- NVIDIA Jetson forums → Section D
[OK] when category is identified.
Section A — Jetson software stack
| Component | Description | Link |
| JetPack SDK | Complete dev environment (CUDA-X, Linux kernel, drivers, flash tools) | https://developer.nvidia.com/embedded/jetpack |
| Jetson Linux | L4T driver package, bootloader, kernel | https://developer.nvidia.com/embedded/linux-tegra |
| Cloud-Native | Container runtime for edge | https://developer.nvidia.com/embedded/jetson-cloud-native |
| NVIDIA TAO | Transfer learning toolkit for DL workflows | https://developer.nvidia.com/tao |
| Pretrained Models | Ready-to-use AI models | https://developer.nvidia.com/tao-toolkit |
| Triton Inference Server | Scalable multi-model inference | https://developer.nvidia.com/nvidia-triton-inference-server |
| NVIDIA Riva | Conversational AI SDK (speech, NLP) | https://developer.nvidia.com/riva |
| DeepStream SDK | Stream analytics for video AI | https://developer.nvidia.com/deepstream-sdk |
| NVIDIA Isaac | Robotics SDK (ROS GEM + Isaac Sim) | https://developer.nvidia.com/isaac-sdk |
Full software overview: https://developer.nvidia.com/embedded/develop/software
Section B — Jetson modules used in reComputer
| Module | Compute | reComputer Products |
| Jetson Xavier NX | Up to 21 TOPS | J2011, J2012 |
| Jetson Nano | 0.5 TFLOPS (FP16), 128 CUDA cores | J1010, J1020 |
All Jetson modules: https://developer.nvidia.com/embedded/jetson-modules
Section C — Seeed reComputer flash guides
| Board | Flash Guide |
| J1010 carrier | https://wiki.seeedstudio.com/reComputer_J1010_J101_Flash_Jetpack/ |
| A206 carrier (J1020) | https://wiki.seeedstudio.com/reComputer_J1020_A206_Flash_JetPack/ |
reComputer comes with 16 GB eMMC pre-installed with Ubuntu 18.04 LTS and JetPack 4.6. Re-flashing is only needed if you want to change the OS.
Section D — NVIDIA Jetson forums
Failure decision tree
| Symptom | Action |
| User needs a resource not listed | Check https://developer.nvidia.com/embedded/develop/software for the full catalog |
| Link is broken | Search the NVIDIA developer site or Seeed wiki for updated URLs |
| User unsure which module they have | Run cat /proc/device-tree/model on the Jetson device |
Reference files
references/source.body.md— Original Seeed wiki with full software stack diagrams and module images
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
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.