Browse the metahub catalog

Generate a professional, client-facing GEO report combining all audit results into a single deliverable with scores, findings, and prioritized actions

Generate a professional PDF report from a GEO audit using pandoc + Chrome headless. Converts GEO-AUDIT-REPORT.md into a styled, client-ready PDF with a cover page, color-coded score tables, severity-tagged findings, and a 90-day roadmap.

CoCounsel Legal delivers comprehensive Westlaw Deep Research reports with inline, linked citations to Westlaw and Practical Law sources.

GEO-first SEO skill for Claude Code.

GEO-first SEO skill for Claude Code.

Runs first-pass trademark clearance and freedom-to-operate triage, screens invention disclosures for initial patentability, drafts and triages cease-and-desist letters and DMCA takedowns (send and respond), checks open source compliance, reviews IP clauses, and tracks registrations and renewal deadlines.

Platform-specific AI search optimization — audit and optimize for Google AI Overviews, ChatGPT, Perplexity, Gemini, and Bing Copilot individually

Analyzes and generates llms.txt files -- the emerging standard for helping AI systems understand website structure and content. Can validate existing llms.txt files or generate new ones from scratch by crawling the site.

Reviews hires and terminations for jurisdiction-specific risk flags, classifies workers against the controlling state test, tracks leave deadlines before they're missed, runs internal investigations, and drafts policies with state supplements where the law differs.

AI crawler access analysis. Checks robots.txt, meta tags, and HTTP headers to determine which AI crawlers can access the site. Provides a complete access map and recommendations for maximizing AI visibility while maintaining appropriate control.

Content quality and E-E-A-T assessment for AI citability — evaluate experience, expertise, authoritativeness, trustworthiness, and content structure

Runs M&A diligence at scale with cited tabular review, builds disclosure schedules and closing checklists, drafts board consents and minutes in house format, and tracks entity compliance deadlines across jurisdictions.

GEO-first SEO skill for Claude Code.

AI citability scoring and optimization. Analyzes web page content to determine how likely AI systems (ChatGPT, Claude, Perplexity, Gemini) are to cite or quote passages from the page. Provides a citability score (0-100) with specific rewrite suggestions.

Reviews vendor agreements, NDAs, and SaaS subscriptions against your sales-side or purchasing-side playbook, tracks renewals and cancel-by deadlines before they're missed, routes escalations to the right approver, and translates reviews into summaries business stakeholders will actually read.

Brand mention and authority scanner for AI visibility. Analyzes brand presence across platforms that AI models rely on for entity recognition and citation decisions. Produces a Brand Authority Score (0-100) with platform-specific recommendations.

Full website GEO+SEO audit with parallel subagent delegation. Orchestrates a comprehensive Generative Engine Optimization audit across AI citability, platform analysis, technical infrastructure, content quality, and schema markup. Produces a composite GEO Score (0-100) with prioritized action plan.

Triages proposed AI use cases against your registry, runs impact assessments across the regimes in scope, reviews vendor AI terms for training-on-data and liability gaps, and keeps your AI policy current with practice.

GEO-first SEO skill for Claude Code.

AI-powered reverse engineering assistant that bridges IDA Pro with language models through MCP.

Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers.

Provides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan.

VoltAgent docs-mcp - MCP Docs

Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.

Simple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO.

voltagent-example-with-cerbos MCP server

High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing.

Provides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput.

An AWS Labs Model Context Protocol (MCP) server for AWS Serverless

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training

Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines.

GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

Provides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

Provides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior.

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture.

Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.

Expert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support

Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support

Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.

Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.

Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.

RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.

Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).

State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design. Mamba-1 (dstate=16) and Mamba-2 (dstate=128, multi-head). Models 130M-2.8B on HuggingFace.

Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.

Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.