Setup Workshop Nemoclaw
brevdev/workshop-build-an-agent
Set up the NVIDIA "Build an Agent" DevX workshop as a working JupyterLab environment from INSIDE a locked-down OpenShell/NemoClaw sandbox, and hand the user the token URL + access commands.
Generate inorganic material structures using MatterGen, a diffusion-based generative model.
Install ML Generative Mattergen
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-mattergen -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-mattergen --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/ml-generative-mattergen .claude/skills/ml-generative-mattergen && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "ml-generative-mattergen" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-mattergen into .claude/skills/ml-generative-mattergen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-mattergen", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-mattergenType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-mattergen -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-mattergen --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/ml-generative-mattergen .agents/skills/ml-generative-mattergen && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ml-generative-mattergen" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-mattergen into .agents/skills/ml-generative-mattergen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-mattergen", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-mattergen -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-mattergen --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/ml-generative-mattergen .cursor/skills/ml-generative-mattergen && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "ml-generative-mattergen" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-mattergen into .cursor/skills/ml-generative-mattergen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-mattergen", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/learningmatter-mit/AtomisticSkills.git --path skills/ml-generative-mattergen--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-mattergen -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-mattergen --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/ml-generative-mattergen .gemini/skills/ml-generative-mattergen && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "ml-generative-mattergen" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-mattergen into .gemini/skills/ml-generative-mattergen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-mattergen", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-mattergenInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-mattergen -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/ml-generative-mattergen .github/skills/ml-generative-mattergen && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "ml-generative-mattergen" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-mattergen into .github/skills/ml-generative-mattergen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-mattergen", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-mattergen -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install learningmatter-mit/AtomisticSkills ml-generative-mattergen --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/learningmatter-mit/AtomisticSkills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/ml-generative-mattergen .opencode/skills/ml-generative-mattergen && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "ml-generative-mattergen" agent skill from https://github.com/learningmatter-mit/AtomisticSkills/tree/main/skills/ml-generative-mattergen into .opencode/skills/ml-generative-mattergen/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ml-generative-mattergen", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
ml-generative-mattergen- GitHub stars
- 175
- Token cost
- ~1.8k tokens
- SKILL.md length
- 664 words
- Files
- 9 (incl. scripts)
- Skills in repo
- 129
- Repo updated
- First seen
- Licence
- MIT
At a glance
Generate inorganic material structures using MatterGen, a diffusion-based generative model.
- Works in 9 steps: Prerequisites → Available Models → MCP Tool Usage → …
- Tasks that involve Fine-tuning
- SKILL.md covers 1. Prerequisites, 2. Available Models, 3. MCP Tool Usage and 4. Fine-Tuning (Skill Scripts), plus 5 more sections
- Runs Python and Shell scripts from its folder
What it does
ML Generative Mattergen is an agent skill from learningmatter-mit/AtomisticSkills. Generate inorganic material structures using MatterGen, a diffusion-based generative model.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 12 other files, including scripts (for example `examples/finetuning/README.md`, `examples/finetuning/example_finetuned_model/adapter_config.json` and `examples/finetuning/make_dummy.py`).
It sits in AI & LLM Engineering, covering Fine-tuning. It works with CUDA. The repository describes itself as: Integrating AtomisticSkills into Agentic IDEs (Cursor, Claude Code, Codex, Google Antigravity, Hermes Agent, etc). The licence is MIT.
When your agent uses it
- Tasks that involve Fine-tuning
Example prompts
- “/ml-generative-mattergen”
Requirements
- Python 3
- A Bash shell
Workflow steps
9 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 7f2d86d. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 3 files in scripts/ (Python and Shell), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
github.com
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
ML Generative Mattergen loads about 1.8k tokens when it runs. Until then it costs about 29 tokens; SKILL.md has 664 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from learningmatter-mit/AtomisticSkills at commit 7f2d86d, republished under its MIT licence (© learningmatter-mit). 664 words, ~1,755 tokens.
Download SKILL.mdSave it as
.claude/skills/ml-generative-mattergen/SKILL.md (or your agent's skills folder). This skill also uses 8 other files; get the full folder from GitHub.- name
- ml-generative-mattergen
- description
- Generate inorganic material structures using MatterGen, a diffusion-based generative model.
- metadata.category
- machine-learning, materials
- metadata.venv
- mattergen
MatterGen Structure Generation Skill
This skill provides tools for generating novel inorganic material structures using MatterGen, a state-of-the-art diffusion-based generative model for crystalline materials.
1. Prerequisites
[!IMPORTANT] GPU Required: MatterGen generation needs a CUDA GPU (NVIDIA driver ≥ 525).
Runs as the
mattergenMCP server and its scripts run in themattergenenvironment: on x86_64 a uv environment created on first use (CUDA 12.6 or 13 by driver), on aarch64 thegenerativecontainer image.A MatterGen checkout next to this project as
../mattergen, or anywhere withMATTERGEN_REPOpointing to it. MatterGen's PyPI distribution omits the data files it needs (sampling configs, GemNet scale factors), so it runs from the checkout, as upstream installs it. Fetch it with the setup script, which pins the verified commit, skips the LFS checkpoints (the weights come from Hugging Face) and replacesnp.math, which NumPy 2 removed:bash ${CLAUDE_SKILL_DIR}/../../venv/run mattergen python ${CLAUDE_SKILL_DIR}/scripts/setup_mattergen.pyvenv/runmounts it into the container on aarch64.On aarch64 (e.g. NVIDIA DGX Spark) the image carries PyG's extensions compiled for CUDA, which PyG publishes no aarch64 wheels for; nothing needs building on the host.
2. Available Models
MatterGen provides several pretrained models:
mattergen_base: Base unconditional generative modelmp_20_base: Materials Project base modeldft_mag_density: Model for magnetic density conditioningchemical_system: Model for chemical system conditioning
3. MCP Tool Usage
The MCP tool automatically loads models when needed - no explicit load step required.
Unconditional Generation
Generate novel structures without conditioning:
from mcp_base import mattergen.generate_structures
result = mattergen.generate_structures(
model_name="mattergen_base",
num_structures=10,
batch_size=10,
output_dir="research/my_project/generated"
)Chemical System Conditioning
Generate structures from a specific chemical system (controls which elements appear):
result = mattergen.generate_structures(
chemical_system="Li-Fe-P-O", # Automatically uses chemical_system model
guidance_scale=1.0, # Recommended for chemical system conditioning
num_structures=20,
batch_size=10,
output_dir="research/cathode_materials/generated"
)[!NOTE] Chemical system conditioning controls which elements appear, but NOT the exact stoichiometry. For example,
chemical_system="Li-Zr-Cl"can generate Li3Cl5, LiZrCl4, Li2ZrCl5, etc., but you cannot specify exactly "Li2ZrCl6".
4. Fine-Tuning (Skill Scripts)
Fine-tune MatterGen on custom datasets using the skill scripts:
Step 1: Prepare Training Data
# Convert structures and properties to CSV format
${CLAUDE_SKILL_DIR}/../../venv/run mattergen python ${CLAUDE_SKILL_DIR}/scripts/prepare_training_data.py \
--structures-json training_structures.json \
--property-name "formation_energy" \
--output training_data.csvTraining data JSON format:
[
{
"structure": {<pymatgen Structure dict>},
"properties": {"formation_energy": -2.5}
},
...
]Step 2: Run Fine-Tuning
${CLAUDE_SKILL_DIR}/../../venv/run mattergen python ${CLAUDE_SKILL_DIR}/scripts/run_finetuning.py \
--training-data training_data.csv \
--property-name "formation_energy" \
--base-model "mattergen_base" \
--epochs 100 \
--output-dir finetuned_formation_energyFine-tuning parameters:
--training-data: Path to CSV from Step 1--property-name: Property to condition on (must match CSV column)--base-model: Starting model (mattergen_base, chemical_system, etc.)--epochs: Training epochs (100-200 recommended)--learning-rate: Learning rate (default: 5e-6)--batch-size: Batch size (default: 32)
[!TIP]
- Start with 2 epochs for quick testing
- Use 100-200 epochs for actual fine-tuning
- GPU required (fine-tuning on CPU is extremely slow)
5. Output Files
Generation Output
structure_XXXX.cif: Generated structure filesgeneration_metadata.json: Metadata about generation parameters
Fine-Tuning Output
checkpoints/: Model checkpoint files (.ckpt)config.yaml: Hydra configuration used- Training logs and metrics
Show full SKILL.md (276 more words)Show less
6. Limitations
[!WARNING] Chemical System vs. Stoichiometry
chemical_systemparameter controls which elements are encouraged to be present.- It does NOT guarantee that all specified elements will be in the output structure.
- It does NOT prevent other elements from occasionally appearing if guidance is too low.
- Example:
chemical_system="Li-Zr-Cl"might generate LiCl, ZrCl4, or even structures missing Li, alongside the desired ternaries (e.g., Li2ZrCl6).- Action Required: You MUST write a post-processing script to filter the output
.ciffiles and keep only the ones that match your exact target elemental composition.
[!WARNING] CSP Mode Not Available
- Target composition control (
target_compositionsparameter) requires CSP-trained models- CSP models are NOT publicly available - must be custom-trained
- Public models (mattergen_base, chemical_system, etc.) are generation models only
7. Best Practices
[!IMPORTANT]
- GPU Required: MatterGen requires a CUDA-compatible GPU. CPU is extremely slow.
- Batch Size: Use larger batches (10-50) for efficient GPU utilization
- Guidance Scale: Higher values (1.0-5.0) enforce stronger conditioning
- Composition Filtering: Always filter the generated output CIFs using
pymatgento verify that the structures contain exactly the target elements.- Validation: Always validate generated structures via relaxation and stability analysis
[!TIP]
- Start with unconditional generation to understand model behavior
- Use chemical_system conditioning to explore specific element combinations
- Fine-tune on domain-specific data for specialized applications (e.g., cathode materials)
8. Workflow Integration
MatterGen works well in combination with:
- Structure relaxation: Use MCP MLIP tools to optimize generated structures
- Stability analysis: Calculate E_hull to identify stable phases
- Property prediction: Use MLIPs or DFT to calculate properties
- High-throughput screening: Generate → Relax → Screen workflow
9. Examples
See examples/ for:
- Unconditional generation workflow
- Chemical system conditioning
- Fine-tuning on custom datasets with complete example data
Author: Bowen Deng Contact: GitHub @learningmatter-mit
© learningmatter-mit, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 8 other files (scripts) in skills/ml-generative-mattergen of learningmatter-mit/AtomisticSkills.
- SKILL.md
- examples/finetuning/README.md
- examples/finetuning/example_finetuned_model/adapter_config.json
- examples/finetuning/example_finetuned_model/adapter_model.bin
- examples/finetuning/make_dummy.py
- examples/finetuning/run_finetune_example.sh
- scripts/prepare_training_data.py
- scripts/run_finetuning.py
- scripts/setup_mattergen.py
Open the folder on GitHubat commit 7f2d86d
Compare with similar skills
ML Generative Mattergen next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| ML Generative Mattergen this skilllearningmatter-mit/AtomisticSkills | 175 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Setup Workshop Nemoclawbrevdev/workshop-build-an-agent | 143 | — | ~5.2k | Automated safety check: Pass | Apache-2.0 | |
| Setup GuideRed-Hat-AI-Innovation-Team/training_hub | 100 | — | ~959 | Automated safety check: Pass | Apache-2.0 | |
| Training Hub GuideRed-Hat-AI-Innovation-Team/training_hub | 100 | — | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Cosmos3 Post TrainingNVIDIA/cosmos-framework | 556 | — | ~2.7k | Automated safety check: Pass | Custom licence | |
| Spark Environment Setupwshobson/agents | 40k | — | ~2k | Automated safety check: Pass | MIT |
Similar skills
Setup Guide
Red-Hat-AI-Innovation-Team/training_hub
A skill your agent uses when the user wants to set up LLM training for the first time, or when traininghub is not yet installed/configured in the current environment.
Training Hub Guide
Red-Hat-AI-Innovation-Team/training_hub
Guides users through LLM post-training with Training Hub, including installation, algorithm selection (SFT, OSFT, LoRA), hyperparameter tuning, troubleshooting OOM errors, interpreting loss curves…
- Official
Cosmos3 Post Training
NVIDIA/cosmos-framework
Guide users through Cosmos3 supervised fine-tuning (SFT) post-training: preparing the example dataset and Wan2.2 VAE, converting the base checkpoint to DCP, launching distributed training (paired…
Spark Environment Setup
wshobson/agents
Set up a working ML training/inference environment on NVIDIA DGX Spark (GB10, aarch64, CUDA 13).
- Official
Kermt Finetune
NVIDIA/skills
Finetune a pretrained KERMT encoder on a labeled CSV. An agent skill from NVIDIA/skills.
More from learningmatter-mit/AtomisticSkills
All 129 skills in this repoDrug Binding Site Definition
learningmatter-mit/AtomisticSkills
Define a docking search box (center coordinates + box dimensions in Angstroms) from a co-crystal ligand, binding-site residues, or a saved JSON specification.
Drug Complex System Builder
learningmatter-mit/AtomisticSkills
Build a solvated, charge-neutralized protein-ligand complex for OpenMM molecular dynamics simulation.
Drug Pocket Detection
learningmatter-mit/AtomisticSkills
Identify and rank ligandable pockets on a protein structure or model using geometry (fpocket) or an ML predictor (P2Rank).
Chem Bond Dissociation
learningmatter-mit/AtomisticSkills
Calculate homolytic and heterolytic bond dissociation energies (BDEs) for all single bonds in a molecule using MLIPs with RDKit fragmentation.
Chem Conformer Search
learningmatter-mit/AtomisticSkills
Generate molecular conformers with RDKit ETKDG, relax with MLIPs, and rank by energy with Boltzmann weighting.
Chem DB Mof
learningmatter-mit/AtomisticSkills
Query multiple MOF databases (QMOF via MPContribs; ARC-MOF DB7/Majumdar et al.
Related
Works with
Categories
Questions about ML Generative Mattergen
What does ML Generative Mattergen do?
Generate inorganic material structures using MatterGen, a diffusion-based generative model. ML Generative Mattergen is an agent skill from learningmatter-mit/AtomisticSkills. Generate inorganic material structures using MatterGen, a diffusion-based generative model.
When should I use ML Generative Mattergen?
ML Generative Mattergen fits situations like: tasks that involve Fine-tuning.
How do I install ML Generative Mattergen in Claude Code?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-mattergen -a claude-code`. Or copy the skill folder (skills/ml-generative-mattergen in learningmatter-mit/AtomisticSkills) into .claude/skills/ml-generative-mattergen in your project. Claude Code loads it when a task matches its description.
How do I install ML Generative Mattergen in Codex?
Run `npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-mattergen -a codex`. Or copy the skill folder (skills/ml-generative-mattergen in learningmatter-mit/AtomisticSkills) into .agents/skills/ml-generative-mattergen in your project. Codex loads it when a task matches its description.
Can I use ML Generative Mattergen in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add learningmatter-mit/AtomisticSkills --skill ml-generative-mattergen -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ml-generative-mattergen, .gemini/skills/ml-generative-mattergen, .github/skills/ml-generative-mattergen and .opencode/skills/ml-generative-mattergen in your project.
What does ML Generative Mattergen need to run?
Going by SKILL.md and its folder, ML Generative Mattergen needs Python and a shell for the scripts in its folder. Our summary lists: Python 3; A Bash shell.
Does ML Generative Mattergen access the network?
SKILL.md names 1 domain. As links in the text: github.com. This is read from the text; nothing was executed.
Is ML Generative Mattergen safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does ML Generative Mattergen use?
ML Generative Mattergen is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does ML Generative Mattergen use?
About 1.8k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to ML Generative Mattergen?
Skills that share tags, products or a category with ML Generative Mattergen: Setup Workshop Nemoclaw (brevdev/workshop-build-an-agent, 143 stars), Setup Guide (Red-Hat-AI-Innovation-Team/training_hub, 100 stars), Training Hub Guide (Red-Hat-AI-Innovation-Team/training_hub, 100 stars) and Cosmos3 Post Training (NVIDIA/cosmos-framework, 556 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains ML Generative Mattergen?
learningmatter-mit (a GitHub organization) maintains it in learningmatter-mit/AtomisticSkills, which has 175 GitHub stars. The repository holds 129 skills in this directory. The repository was last updated on October 6, 2026.
Source: learningmatter-mit/AtomisticSkills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.