nemocode 0.1.12

Terminal-first control plane for NVIDIA Nemotron 3 — agentic coding, RAG, doc-ops, and multi-model formations.

NeMoCode

Agentic coding CLI for NVIDIA NIM. Reads your code, makes edits, runs commands — powered by any model on the NIM API or your own GPU via vLLM.

Community project — not affiliated with or endorsed by NVIDIA.

Install

From source (editable):

pip install -e .

Or from PyPI:

pip install nemocode

Setup

Get a free API key from build.nvidia.com:

export NVIDIA_API_KEY="nvapi-..."
nemo code

Or serve a model locally with vLLM on any NVIDIA GPU:

vllm serve nvidia/NVIDIA-Nemotron-Nano-9B-v2 \
  --trust-remote-code --mamba_ssm_cache_dtype float32 \
  --enable-auto-tool-choice \
  --tool-parser-plugin nemotron_toolcall_parser.py \
  --tool-call-parser nemotron_json
nemo code -e local-vllm-nano9b

No GPU? Rent one via Brev — L40S from $1.03/hr:

nemo setup brev

Usage

nemo code                              # interactive REPL
nemo code "fix the bug in auth.py" -y  # one-shot, auto-approve tools
nemo chat "explain this error"         # chat, no tools
cat log.txt | nemo code "diagnose"     # pipe input
nemo code -f super-nano "refactor"     # multi-model formation

Endpoints

Works with any OpenAI-compatible API. Pre-configured:

Endpoint	Model	Access
nim-super	Nemotron 3 Super (12B/120B MoE)	NIM API key
nim-nano	Nemotron 3 Nano (3B/30B MoE)	NIM API key
nim-nano-9b	Nemotron Nano 9B v2	NIM API key
openrouter-super	Super via OpenRouter	OpenRouter key
together-super	Super via Together AI	Together key
local-vllm-*	Any model on local vLLM	GPU + vLLM
local-nim-*	Local NIM container	GPU + Docker

Formations

Multi-model pipelines — Super plans, Nano executes, Super reviews:

nemo code -f super-nano "implement caching"

Formation	Pipeline
solo	Super does everything (default)
super-nano	Super plans + reviews, Nano executes
local	Nano on local GPU, no internet needed

Local GPU setup

nemo setup          # show all options
nemo setup vllm     # vLLM serving guide
nemo setup nim      # NIM container guide
nemo setup brev     # rent a cloud GPU

More commands

nemo endpoint ls / test     # manage endpoints
nemo model ls / show        # inspect model manifests
nemo formation ls / show    # inspect formations
nemo hardware recommend     # GPU-based recommendations
nemo session ls             # past conversations
nemo obs pricing            # token pricing
nemo init                   # create .nemocode.yaml

Contributing

pip install -e ".[dev]"
ruff check src/ tests/ && ruff format --check src/ tests/
pytest tests/ -v

License

MIT. NVIDIA, Nemotron, and NIM are trademarks of NVIDIA Corporation.