10 actions in 6 pieces of software · ranked by words, meaning and measured trust · 684 ms
skillnvidia/skillsrecord
- nemo-rl-auto-research
Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving
- nemo-rl-auto-research
skillnvidia/skillsrecord
- nemo-rl-brev-etiquette
Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-he
- nemo-rl-brev-etiquette
skillnvidia/skillsrecord
- launch-nemo-rl
Playbook for launching, monitoring, stopping, and debugging NeMo-RL recipes on a Kubernetes cluster via the nrl-k8s CLI. Covers ephemeral vs long-lived RayCluster modes, iterating on runs, and debugging hung or failed training jobs.
- launch-nemo-rl
libraryNVIDIA/NeMo-Relayrecord5,175,136 downloads/month
- agents
- ai
- nemo-relay
- runtime
- llm
skillnvidia/skillsrecord
- nemo-rl-docs
Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.
- nemo-rl-docs
skillnvidia/skillsrecord
- nemo-automodel-recipe-development
Create and modify NeMo AutoModel training and evaluation recipes, including YAML structure, builders, and execution flow.
- nemo-automodel-recipe-development
Labels are the instruments' verdict and are never changed by ranking. Agents and robots get this same answer as JSON at /api/v1/find?q=…&answer=1 and through the MCP server.