MolmoAct

SkillDev tools

Use when working on MolmoAct VLA fine-tuning/serving/evaluation workbench stages, MolmoAct policy configs, or the npa workbench molmoact CLI.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the MolmoAct skill

What this skill tells your AI

The instructions your AI receives, as published by nebius/nebius-physical-ai in skills/tools/molmoact/SKILL.md and read by ahel’s review.

MolmoAct is the vision-language-action tool for fine-tuning, serving, and evaluating MolmoAct VLA policies in npa.

The three core stages (finetune, serve, eval) are currently stubs: they validate their arguments and return a plan-only manifest — actual trainer/server/evaluator execution is not wired up yet (tracking issue nebius/nebius-physical-ai#502). The base model (default allenai/MolmoAct-7B-O-0812) is resolved at runtime through the HF Hub cache via npa.workbench.model_access — weights are never bundled in the repo or image.

Interfaces

  • CLI: npa workbench molmoact <finetune|serve|eval> --help
  • Python SDK: npa.sdk.workbench.molmoact (finetune, serve, eval)
  • Workflow module: npa.workflows.byof.molmoact_pipeline (argument validation, stub-manifest plumbing, argparse entrypoint)

Conventions

  • The CLI lives at npa.cli.workbench.molmoact (multi-command package form for new tools); the SDK surface lives at npa.sdk.workbench.molmoact.
  • The finetune stage is the headline molmoact/finetune three-tier contract (CLI <-> SDK <-> workflows/testing/molmoact-finetune.yaml); serve and eval remain public-reusable sibling toolRefs.

Signals

GitHub stars
30
Forks
16
Last commit
Sep 2026
Advanced
Catalog kind
skill
Key
molmoact
Source
github.com/nebius/nebius-physical-ai