MCP servers and skills: search, filter by where they run, and compare.
1–24 of 654 tools for “bayesian-inference”
Clear allNothing matches every word exactly, so these are the closest matches.
Claude Code plugin marketplace for biostatistics in R — 30 agents, 17 commands, and 45 skills spanning Bayesian modeling (Stan/PyMC/JAGS), indirect treatment comparisons (NMA/MAIC/STC/ML-NMR), tidy R
SkillMIT★ 12No key
Deploys and optimizes AI/ML inference workloads on GKE, using GPUs, TPUs, and model servers. Use when deploying GKE inference servers, configuring GKE GPU resources for inference, or deploying LLMs on
OfficialSkillApache-2.0★ 21k in collectionNo key
AI inference pricing for agents: live + historical model prices, provider comparison, SIT index. Free MCP server + REST API.
PythonMITFew starsNo key
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot clas
in the skill textand may initialize weights when pretrained weights are unavailable. Do not assume `inference.checkpoint: null` loads pretrained weights: `clip inference` currently calls the checkpoint loader with `None
OfficialSkillApache-2.0★ 3.6k in collectionNo key
A library of enterprise-grade AI agents designed to democratize artificial intelligence and provide free, open-source alternatives to overvalued Y Combinator startups.
MCPLink only★ 2.8k
Governed GPU inference ops (vLLM + Ray Serve): latency RCA, scaling, drain, 30 MCP tools (preview)
PythonMITFew starsNo key
MAL (Mask Auto-Label) for weakly-supervised segmentation. Produces segmentation masks from minimal annotations (point or box annotations) using a ViT-MAE backbone. Use when training, evaluating, or ru
in the skill textannotations) using a ViT-MAE backbone. Use when training, evaluating, or running inference for a TAO MAL model. Trigger phrases include "train MAL", "Mask Auto-Label
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Start, query, and stop a network-specific TAO inference microservice ({network_arch}-inference-microservice) by delegating container execution to the appropriate platform skill. Handles container imag
OfficialSkillApache-2.0★ 3.6k in collectionNo key
NVDINOv2 for self-supervised visual representation learning. Trains vision transformers via self-distillation (teacher-student) without labels and produces general-purpose visual features. Use when tr
in the skill textand produces general-purpose visual features. Use when training, exporting, or running inference for a TAO NVDINOv2 backbone. Trigger phrases include "train NVDINOv2", "self-supervised ViT
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Run container-backed AutoML / hyperparameter optimization (HPO) for NVIDIA TAO networks using AutoMLRunner. Handles algorithm selection (bayesian, hyperband, asha, bohb, llm, hybrid, autoresearch), Wa
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Connects to and performs inference with Google Cloud Agent Platform GenAI models, including First-Party Gemini models and Third-Party OpenMaaS models (Llama, DeepSeek, Qwen, etc.). Use when asked to p
OfficialSkillApache-2.0★ 21k in collectionNo key
StatsPAI is the first Agent-native Python library for causal inference and applied econometrics — unified API, broad cross-method coverage, structured result objects, machine-readable schemas, Skills,
PythonMIT★ 341No key
Guides the migration of existing AI workloads (Cloud Run, Gemini API, Gemini Enterprise Agent Platform) to self-hosted GKE inference using gcloud and kubectl. Use when the user has an existing AI infe
OfficialSkillApache-2.0★ 21k in collectionNo key
Model Context Protocol (MCP) server for Inference Labs - adds vendor-neutral LLM routing, model comparison, and live LLM pricing to Claude Desktop, Cursor, Windsurf, and any MCP client.
MCPLink onlyFew stars
Co-DETR (CoDINO) for object detection. A DETR-family detector with collaborative hybrid assignment — auxiliary one-to-many heads supervise the encoder during training, giving strong closed-set accurac
in the skill textsupervise the encoder during training, giving strong closed-set accuracy at high inference cost. Use when training, evaluating, or running inference for a TAO Co-DETR
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Comprehensive, scalable ML inference architecture using Amazon EKS, leveraging Graviton processors for cost-effective CPU-based inference and GPU instances for accelerated inference. Guidance provides
SkillMIT-0★ 19No key
Create a SageMaker endpoint (real-time, real-time scale-to-zero, or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endp
in the skill texttracking on invocations per instance 5. **CloudWatch alarms** — latency, errors, platform overhead An inference-component deployment (`deploy_ic.py`) creates the same set with two changes: the endpoint
OfficialSkillApache-2.0★ 11k in collectionNo key
Bayesian MCTS Model Context Protocol Server allowing Claude to control Ollama local models for Advanced MCTS and analysis.
PythonMIT★ 5No key
Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be c
in the skill textthumb: if the vLLM tag you picked contains `cu130` or later, pass `--inference-ami-version al2-ami-sagemaker-inference-gpu-3-1` to `deploy.py
OfficialSkillApache-2.0★ 11k in collectionNo key
OneFormer for universal image segmentation. Unifies panoptic, instance, and semantic segmentation with a single architecture using task-conditioned queries. Use when training, evaluating, exporting, q
in the skill textusing task-conditioned queries. Use when training, evaluating, exporting, quantizing, or running inference for a TAO OneFormer model. Trigger phrases include "train OneFormer", "universal segmentation", "task
OfficialSkillApache-2.0★ 3.6k in collectionNo key
Memory for AI agents that never leaves your device. Local-first, end-to-end-encrypted, zero-telemetry memory engine (Rust, MCP) — gives Claude & any MCP client persistent cross-session memory.
in the readmememory, not a text file** — 4 tiers, multi-signal retrieval, self-correcting Bayesian beliefs, a cross-channel people graph. - ⚡ **Sub-millisecond** — 156µs ingest, 568µs search
SkillMIT★ 35No key
MCP server: pay-per-token Claude and Grok inference, settled in BSV, via the hosted inference.bsvkey.com gateway.
Node.jsMITFew starsNo key
Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and search per-sample (guidance, crop_ratio) parameters. Thre
in the skill textfinetune then generate), finetune_only (Phase 0→1: train only), inference_only (Phase 0, 2→7: generate from an existing checkpoint). Use when the user asks
OfficialSkillApache-2.0★ 3.6k in collectionNo key
MCPLink onlyFew stars
Who stands behind it
