MCP servers and skills: search, filter by where they run, and compare.
Use Transformers.js to run state-of-the-art machine learning models directly in JavaScript/TypeScript. Supports NLP (text classification, translation, summarization), computer vision (image classifica
OfficialSkillApache-2.0★ 11k in collectionNo key
Simplified, standalone Python scripts for transformer models, LLMs, TTS, STT, and Image Generation. Educational and lightweight AI. AI is Good.
SkillMIT★ 1Few starsNo key
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers class
OfficialSkillApache-2.0★ 11k in collectionNo 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
OfficialSkillApache-2.0★ 11k in collectionNo key
Open-source speech recognition toolkit for training, inference, streaming ASR, VAD, punctuation, speaker diarization pipelines, and OpenAI-compatible/MCP serving.
SkillMIT★ 21kNo key
Run NV-Reason-CT inference on user-provided 3D NIfTI chest or abdominal CT volumes for engineering and research workflows. Not for diagnosis, treatment, or clinical reporting.
OfficialSkillApache-2.0★ 3.6k in collectionNo key
🪈 Intelligent orchestration system that coordinates multiple AI coding assistants (Claude, Codex, Gemini CLI, Copilot CLI) to collaborate on complex software development tasks via REPL or a Vue/Nuxt
PythonMIT★ 97No key
Preview, clean up, vectorize & export your logo — 100% in your browser. No uploads, no sign-up.
Node.jsMIT★ 2Few starsNo key
Nexus Prime fuses multimodal AI (text, vision, audio, real-time data) for zero-shot learning, ethical reasoning, and simulations in climate and medicine. Quantum-inspired algorithms enable exponential
SkillMIT★ 5No key
Claude Code skill: turn a research paper or project into a 3Blue1Brown-style explainer video with Remotion (script, narration, real-data animation, captions, covers, YouTube/Bilibili copy)
SkillMIT★ 6No key
Turn a 2D reference into pixel-art spritesheets via Blender, Dead Cells style, driven by Claude Code
SkillMIT★ 4Few starsNo key
Distill a Douyin video link into timestamped knowledge cards: watermark-free download, native video understanding, evidence-backed Markdown/Wiki output.
SkillMIT★ 3Few starsNo key
MCP server for Microsoft OmniParser: turn screenshots into structured UI elements for GUI agents (such as Claude Desktop / Cursor / Cline)
SkillCC-BY-4.0Few starsNo key
Sync Canvas courses into a local Obsidian vault — transcribed lecture notes, a cross-lecture concept graph, homework and deadlines — then study it with Claude or Gemini over MCP.
SkillMIT★ 6No key
Agent Skill and toolkit for generating publication-ready, editable ML architecture diagrams from model code.
SkillMIT★ 5No key
Design compiler for antenna and phased-array PCBs: YAML spec in, synthesized layout, KiCad DRC, and openEMS full-wave verification out. Deterministic Python core, agent-ready via MCP.
PythonMIT★ 3Few starsNo key
Add audio, speech, or vision modalities to an existing LLM. Three approaches — LLaVA-style adapter, REAP + expert replacement, EvoMoE-style specialization — with training pipelines and GPU feasibility
SkillMIT★ 4Few starsNo key
252 free sound effects for your app or video, rendered from code: whooshes, clicks, pops, dings. No samples, no torch.
SkillMITFew starsNo key
Free browser tools that run on your device: PDF, image, video, audio and AI tools with no uploads, sign-ups or watermarks. roundertools.com
Node.jsAGPL-3.0Few starsNo key
Local, on-device audio toolbox for AI agents: voice-clone TTS, instrumental music, and audio verification — three installable Agent Skills.
SkillMITFew starsNo key
SkillMITFew starsNo key
Multimodal video dossiers for agents: transcripts, frames, OCR, evidence, and RAG-ready knowledge.
SkillMIT★ 8No key
DiffusionGemma node pack for ComfyUI, built on MCP backbone for fully-agentic consumption — discrete diffusion text generation with per-step canvas snapshots, commit heatmaps, and structured trace dat
SkillGPL-3.0★ 2Few starsNo key
Who stands behind it
