Seeed-Jetson-DevelopTool / deepseek-quick-deploy
AGENTS.md57 starsChanged 4 months agoMITView on GitHub
Quickly deploy DeepSeek-R1 on Jetson using Ollama. Two-command setup. Requires Jetson with >8GB RAM and JetPack 5.1.1+.
- Pipes a download into a shell
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 31,843 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
- 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-resource-indexAGENTS.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
4 rules. About 0 are common, 1 is distinctive, and 3 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.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Run one phase at a time. After each phase:
- Very specific: line 16
If output contains [STOP] → stop immediately, consult the failure decision tree below.
- Very specific: line 17
If output ends with [OK] → tell the user "Phase N complete" and proceed to the next phase.
- Very specific: line 63
Test with a simple prompt to confirm the model responds.
≈ “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
DeepSeek-R1 Quick Deploy on Jetson
Hardware required: Jetson with >8GB RAM, JetPack 5.1.1+. This is the fastest path to running DeepSeek-R1 locally. For optimized MLC-based deployment with better throughput, see the
deploy-deepseek-mlcskill instead.
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 | Detail |
| RAM | >8 GB (unified memory) |
| JetPack | 5.1.1 or later |
| Internet | Required for install script and model download |
| Disk space | ≥10 GB free for model weights |
Phase 1 — Install Ollama
curl -fsSL https://ollama.com/install.sh | shVerify:
ollama --version
# Expected: ollama version x.x.x[OK] when ollama --version prints a version string. [STOP] if the install script fails — see failure decision tree.
Phase 2 — Run DeepSeek-R1
ollama run deepseek-r1The first run downloads the model weights (~4–8 GB depending on quantization). Subsequent runs start immediately from cache.
Expected: after download, an interactive prompt appears:
>>> Send a message (/? for help)Test with a simple prompt to confirm the model responds. Type /bye to exit.
[OK] when the model responds to a prompt. [STOP] if the process is killed or hangs — see failure decision tree.
Failure decision tree
| Symptom | Action |
curl install script fails with network error | Check internet connectivity. If behind a proxy, set https_proxy env var before running curl. Try downloading the script manually and inspecting it. |
curl install script fails with permission error | Run with sudo or ensure /usr/local/bin is writable. |
| Model download stalls or fails mid-way | Retry ollama run deepseek-r1 — Ollama resumes partial downloads. Check available disk space: df -h. |
| Process killed during model pull (OOM) | Not enough RAM. Free memory by stopping other processes, or use a smaller quantization: ollama run deepseek-r1:1.5b. |
| Model loads but inference is very slow | Expected on smaller Jetson modules. For better performance use the deploy-deepseek-mlc skill which uses MLC-optimized kernels. |
ollama: command not found after install | Add Ollama to PATH: export PATH=$PATH:/usr/local/bin, then reload shell or open a new terminal. |
Reference files
references/source.body.md— full source tutorial with additional context (reference only)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.