nvidia-model-config
Add the NVIDIA provider to OpenClaw with SecretRef apiKey (no plaintext in openclaw.json). Documents shell vs systemd gateway env so the key actually resolves. Includes Mixtral, Kimi, Nemotron Super, Nemotron Ultra, and MiniMax M2.5 model entries.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/0xli/nvidia-model-configNVIDIA Model Config Skill
Overview
This skill packages three reusable pieces:
- A script (
scripts/merge_nvidia_config.py) that inserts the NVIDIA provider block into anyopenclaw.jsonfile and configuresapiKeyas a SecretRef by default. - Model entries for Mixtral, Moonshot Kimi, Kimi K2.5, Nemotron Super (1M ctx), Llama 3.1 Nemotron Ultra 253B (128K ctx), and MiniMax M2.5 (204.8K ctx) — delete extras or add more from
openclaw models list --provider nvidia --all. - Instructions for backups, secrets, and where
NVIDIA_API_KEYmust be set so the gateway can resolve it (this is not onlyopenclaw.json).
Use the skill whenever you want to replicate the NVIDIA models.providers.nvidia entry without guessing which keys or nested objects to copy.
Quick start
- Copy or download this skill (e.g.,
rsync -av skills/nvidia-model-config /path/to/other/workspace/skills/). - Obtain your NVIDIA API key and keep it secret (do not commit it).
- Run the script from the target workspace:
python skills/nvidia-model-config/scripts/merge_nvidia_config.py \
--config openclaw.json --key "YOUR_KEY" --setup-env ~/.config/openclaw/gateway.env --setup-systemd --backup
--configdefaults toopenclaw.jsonin the current directory.--keyprovides the API key (alternatively, setNVIDIA_API_KEYin your shell).--setup-envwrites the key to a dedicated environment file (e.g.,~/.config/openclaw/gateway.env).--setup-systemdcreates a systemd user override to load the environment file for the gateway.--backupsaves the original file asopenclaw.json.bakbefore overwriting.- By default, the script writes
models.providers.nvidia.apiKeyas:{"source":"env","provider":"default","id":"NVIDIA_API_KEY"}
Manual Environment Setup
If you prefer not to use --setup-systemd, you must set your key in the runtime environment where the OpenClaw gateway runs.
Interactive shell / CLI only (e.g. testing openclaw in a terminal):
export NVIDIA_API_KEY="$YOUR_KEY"
Gateway under systemd (typical on Linux) — the service does not read ~/.bashrc. Put the key in a file the unit loads, for example:
- File:
~/.config/openclaw/gateway.env(mode600):
NVIDIA_API_KEY=your_key_here
- User unit drop-in
~/.config/systemd/user/openclaw-gateway.service.d/override.conf:
[Service]
Environment=NVIDIA_API_KEY=
EnvironmentFile=-/home/YOUR_USER/.config/openclaw/gateway.env
The empty Environment=NVIDIA_API_KEY= clears any inherited value so EnvironmentFile is the single source of truth. Then:
systemctl --user daemon-reload
systemctl --user restart openclaw-gateway.service
You can also keep a personal ~/.config/openclaw/secrets.env and source it from ~/.bashrc for CLI-only use; that does not replace the gateway env above.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-0xli-nvidia-model-config": {
"enabled": true,
"auto_update": true
}
}
}