Flowy lists 23 plugins in the Machine Learning category for Claude Code. training or serving models, neural networks, fine-tuning, ML frameworks. NOT "uses an LLM", which is true of every plugin here Every listing shows what is inside before you install, who built it, and whether it is Auto-invoked, meaning a FLOW.md router fires the right skill as you prompt instead of leaving them dormant.
Gives you a Python library for building and training deep learning models, with tensor math that runs on GPUs and a flexible autograd system for computing gradients. Work in familiar Python and reuse libraries such as NumPy and SciPy.
@pytorchInstall PluginSkills for the MLflow repository that analyze failed GitHub Actions jobs, review pull requests, triage issues, and enforce Python and workflow coding conventions.
@mlflowInstall PluginSkills and an MCP server that let Claude Code work with the Hugging Face Hub, covering model training, dataset creation, the hf CLI, and deploying models to Amazon SageMaker.
@huggingfaceInstall PluginGives a machine learning team one place to define features and serve them consistently, so training data and live predictions use the same values. Covers the offline store, online store and feature server.
@feast-devInstall PluginPlugin for developers of the Civitai codebase, with skills that guide adding new AI model ecosystems, base models, generation support, prompt-enhancement guides, and training support to the app and its trainers.
@civitaiInstall PluginSkills for NVIDIA Model Optimizer, a library for compressing and speeding up machine learning models through quantization, pruning, distillation, and neural architecture search. Includes skills for benchmarking model kernels and comparing evaluation results in MLflow.
@nvidiaInstall PluginSkills for installing, running locally, and integrating OpenRAG, a Retrieval-Augmented Generation tool for semantic document search and AI-powered conversations over your own documents.
@langflow-aiInstall PluginSkills for planning and chaining Nemotron model customization steps such as fine-tuning, RL alignment and pretraining, plus a reference desk for Nemotron Lightning and tools for adding models, steps and patterns.
@nvidia-nemoInstall PluginGives Claude Code a way to describe and analyze images when the current model cannot read images directly. It sends the image to a vision-capable model and returns a text description, for images shared as a local path or URL.
@asuojunInstall PluginTrains large language models with reinforcement learning across many GPUs, asynchronously and at scale. Covers config setup, installation, running evals on checkpoints, the local run dashboard, and building CUDA kernels.
@primeintellect-aiInstall PluginHelps an agent run fair LLM serving benchmarks across SGLang, vLLM and TensorRT-LLM, read profiler traces down to the kernel, and estimate GPU memory and concurrency from startup logs. Ships with skills for model architecture diagrams too.
@bbufInstall PluginSkills for federated learning with NVIDIA FLARE, a Python SDK for adapting existing ML and deep learning workflows to federated training. Covers converting Hugging Face Trainer or SFTTrainer code, and running and reporting Auto-FL optimization of NVFlare jobs.
@nvidiaInstall PluginLets robotics teams build simulated benchmark scenes and test robot policies in them at scale, without hand-writing a separate setup for each robot, object and scenario combination. Covers environment authoring, test runs and pulling evaluation results.
@isaac-simInstall PluginLaunches, monitors and stops LLM inference workloads on one or more NVIDIA DGX Spark machines, so you can serve models across a cluster without Slurm or Kubernetes. Covers installing the tool and setting up the cluster, and managing the recipes that define each model run.
@spark-arenaInstall PluginLibrary for Jacobian descent with PyTorch. It enables the optimization of neural networks with multiple losses (e.g. multi-task learning).
@simplexlabInstall PluginA Claude Code skill that makes Claude act as a thinking advisor using Andrej Karpathy's mental models and communication style. It helps analyze AI reliability, learning methods, industry trends and product design from his perspective.
@alchaincyfInstall PluginHelps coding agents write, evaluate and optimize DSPy programs, from typed signatures and modules to metric-driven optimization and long-context reasoning. Covers the whole workflow so you can build and tune LLM pipelines without relearning the API each time.
@intertwineInstall Pluginovrtx is a C and Python library for embedding Omniverse RTX sensor simulation and visualization directly into applications.
@nvidia-omniverseInstall PluginA website, three games, a benchmark and an agent skill for Laya, the open-source decision model: typed questions in, real probabilities out, one forward pass, no generated text. It runs on your own machine. The live site is at brainfunctioncollapse.com/laya.
@wdobryInstall PluginAn Agent Skill for building task-specific small language models on the distil labs platform: from raw data or production traces, through teacher evaluation and synthetic data generation, to a finetuned, evaluated, deployable student model.
@distil-labsInstall PluginUnofficial skill that teaches coding agents to build with TypeSafe AI's Jev: typed decisions, calibrated confidence, and prior art from 150+ community projects.
@aaddrickInstall PluginEnglish · 简体中文 · 日本語 / v2.0.0 Use Skill Cases Evidence A new view of the formal model. Apparatus layout and beam geometry retained; private instrument identities and scene files excluded. Design the path. Keep the evidence.
@k-teluxInstall PluginAI-powered biologics design campaign agent, multi-agent orchestration with BoltzGen, PXDesign, Protenix, and 200+ cloud tools. Antibodies, nanobodies, de novo binders, and beyond.
@001tmfInstall Plugin