Data and AI

13,567 mods in this category, of every kind an agent can take. Each one carries what it costs per session, what the scan found, and whether it is the original.

openrouter-multimodal

289

stabgan/openrouter-mcp-multimodal

MCP server Claude CodeCodexCursor +2

Chat with 300+ LLMs via OpenRouter. Analyze and generate images, audio, and video from MCP. Runs locally from the @stabgan/openrouter-mcp-multimodal npm package. Needs 13 environment variables to run.

not rated 85 yesterday A tokens not measured original Apache-2.0

backlot

290

brekkylab/backlot

Plugin Claude Code

Bundles 1 skill · 192 tokens together

Emulate an enterprise SaaS knowledge source over a corpus you supply, then wire a real client to it.

not rated 85 +25 yesterday A tokens not measured original MIT

pdfmux

292

NameetP/pdfmux

MCP server Claude CodeCodexCursor +2

Self-healing PDF extraction for RAG — #2 of 8 engines on opendataloader-bench (0.903). Flags pages it can't read instead of dropping them, and certifies any extractor's output for silent drops. Verify signed manifests offline, free. Per-page confidence, 7-tool MCP server, LangChain/LlamaIndex loaders. LlamaParse…

not rated 82 +1 4d ago A Socket: warn tokens not measured original MIT

token-router

293

sleeplesshan/token-router

Skill Claude CodeCodex

Route oversized logs, source files, and long routeable agent-context reference files through a local Ollama model to identify relevant line ranges before analysis. Use when Codex needs to analyze massive error logs, stack traces, source files over roughly 300 lines, or long…

not rated 82 2mo ago A 145 tokens original MIT

NVIDIA-AI-IOT/DeepStream_Coding_Agent

Skill Claude CodeCodex

Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.

not rated 81 3mo ago A 68 tokens

ai-ready-data

295

Snowflake-Labs/ai-ready-data

Skill Claude CodeCodex

Assess and optimize data for AI workloads across platforms. Scan estates for prioritization, assess assets against profiles, and guide remediation.

not rated 81 3mo ago A 29 tokens original Apache-2.0

knowledge_sources

296

elizaOS/knowledge

Cursor rule Cursor

This repository aggregates knowledge from various sources for RAG systems. See the main README.md for a full overview.

not rated 81 2d ago A 0 tokens

cocoindex

297

cocoindex-io/cocoindex-claude

Skill Claude CodeCodex

Comprehensive toolkit for developing with the CocoIndex library. Use when users need to create data transformation pipelines (flows), write custom functions, or operate flows via CLI or API. Covers building ETL workflows for AI data processing, including embedding documents into vector databases, building knowledge…

not rated 79 3mo ago A 72 tokens original Apache-2.0

lance-mcp

298

adiom-data/lance-mcp

MCP server Claude CodeCodexCursor +2

MCP server for interacting with LanceDB database. Runs locally from the lance-mcp npm package.

not rated 78 1y ago A tokens not measured original MIT

meta-harness

299

001TMF/harness-forge

Skill Claude CodeCodex

Run a Meta-Harness-style optimization loop NATIVELY — automatically search over the scaffolding around a FIXED base model (memory, retrieval, context construction, prompt templates, summarization, tool-selection logic) by proposing candidate variants, scoring each on a cheap deterministic eval, and keeping a Pareto…

not rated 77 +1 2mo ago A 217 tokens original MIT

prompt-refine

300

Apeironics/prompt-refine-skill

Skill Claude CodeCodex

Silently restructures the user's natural-language prompt into the format the model CURRENTLY running this skill handles best, then answers. On activation it identifies which model family is executing it (Claude, GPT, Gemini, Llama, DeepSeek, Mistral, Qwen, Grok, Perplexity, Kimi, GLM, Command, Nova, or Phi) and loads…

not rated 76 1mo ago A 118 tokens original MIT

AMD-AGI/Apex

Skill Claude CodeCodex

This skill should be used when writing or tuning Triton GPU kernels, including autotuning block sizes, coalesced accesses, tiled matmul, fused ops, reductions, flash-attention style kernels, quantization, custom gradients, and profiling.

not rated 76 4d ago A 56 tokens original MIT

ollama-mcp

302

NightTrek/Ollama-mcp

MCP server Claude CodeCodexCursor +2

MCP server for Ollama - exposes all Ollama SDK functionality through MCP tools. Runs locally from the ollama-mcp npm package.

not rated 76 1y ago A tokens not measured

ai-model-wechat

303

TencentCloudBase/skills

Skill Claude CodeCodex

A guide to adding AI features to WeChat Mini Programs, including enterprise Mini Programs, through CloudBase. It covers text generation and streamed responses, where text arrives while it is being produced.

not rated 75 changed 2d ago A Socket: passSnyk: warn 144 tokens

mcp-rag-server

304

karaage0703/mcp-rag-server

MCP server Claude CodeCodexCursor +2

MCP server "mcp-rag-server" as configured in karaage0703/mcp-rag-server. Runs locally from the mcp-rag-server Python package.

not rated 71 10mo ago A tokens not measured original MIT

mykg

305

SenolIsci/mykg

Skill Claude CodeCodex needs its repo

Run mykg knowledge-graph commands inside Claude Code from one slash command /mykg. The user describes intent in natural language (extract, append, sync, resume, approve, walkthrough, parse-docs, fetch-web, query); the skill parses intent, builds the right mykg CLI command from the live --help output, confirms, runs…

not rated 69 changed 3d ago A 175 tokens original MIT

okfy

306

0dust/OKFy

Skill Codex

Use when a user wants an agent to use docs through OKFy, set up or verify an OKFy MCP docs source, convert docs websites or local Markdown into OKF bundles, generate activation proof, or answer from an existing OKFy bundle/workspace.

not rated 69 +1 20d ago A 54 tokens original MIT

pinecone

307

pinecone-io/pinecone-claude-code-plugin

Plugin Claude Code

Bundles 9 skills, 1 command, 1 hook, 1 MCP server · 747 tokens together

Pinecone vector database integration. Streamline your Pinecone development with powerful tools for managing vector indexes, querying data, and rapid prototyping. Use slash commands like /quickstart to generate AGENTS.md files and initialize Python projects and /query to quickly explore indexes. Access the Pinecone MCP.

not rated 68 changed 3d ago A tokens not measured original MIT

wandb-primary

308

wandb/skills

Skill Claude CodeCodex

Primary W&B skill for broad or mixed Weights & Biases work: project overviews, W&B runs and artifacts, Weave traces and evaluations, Reports, and Launch workflows. Use when the task spans multiple W&B surfaces or the user asks generally what is happening in a W&B project.

not rated 67 1mo ago A Socket: passSnyk: warn 64 tokens original Apache-2.0

skills

309

runwayml/skills

Plugin Claude Code

Bundles 11 skills · 542 tokens together

Build Runway models, Model Routers, Characters, recipes, and workflows into applications with Dev MCP and the official SDK, or generate media directly.

not rated 67 +2 9d ago A tokens not measured original MIT

minirag-mcp

310

sfrangulov/minirag-mcp

MCP server Claude CodeCodexCursor +2

Local-first RAG MCP server: hybrid search over your documents, fully local. Runs locally from the minirag-mcp Python package. Needs 13 environment variables to run.

not rated 65 27d ago A Socket: warn tokens not measured original MIT

landing-ai/ade-document-processing-skills

Plugin Claude Code

Bundles 1 skill · 169 tokens together

Agent skill for LandingAI's Agentic Document Extraction (ADE): production-ready document AI with 99%+ accuracy. Parse, extract, and classify documents through the ADE REST APIs or the Python and TypeScript libraries, with full auditability and traceability.

not rated 64 changed 2d ago A tokens not measured original MIT

Tapestry

312

NatsuFox/Tapestry

Plugin Claude Code

Bundles 9 skills · 446 tokens together

Bundle-first Tapestry skill pack for crawling, organizing, and synthesizing web content into reusable feed and knowledge-base artifacts.

not rated 64 4mo ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: