5,245,230 AI resources indexedWorking toward the world’s largest AI resource index.
Reusable instructions for compatible AI agents.
Field counts come from the latest full-catalog snapshot. A resource can belong to several fields and platforms.
Build Manhattan, Miami, QQ, and locuszoom-style regional plots from GWAS, TWAS, PWAS, and QTL summary statistics with correct genomic-inflation diagnostics, multi-trait overlays, lead-SNP labeling, and LD-aware regional rendering. Use when visualizing association results across the genome, compar...
Single-variant common-variant GWAS with plink2 --glm (linear/logistic, Firth) and the linear mixed models GEMMA, BOLT-LMM, SAIGE, regenie (SPA). A GWAS statistic is valid only when genotype is independent of unmodeled phenotype drivers after the chosen covariates and random effects, so the engine...
OBLITERATUS: abliterate LLM refusals (diff-in-means).
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
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 abstractio...
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLS...
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.
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 abstractio...
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLS...
Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training
Kaggle API integration with managed authentication. Access datasets, models, competitions, and kernels.\n Use this skill when users want to search, download, or interact with Kaggle resources.\n For other third party apps, use the api-gateway skill (https://clawhub.ai/byungkyu/api-gateway).
Try a broader search or clear some filters.
Platform labels describe intended use. Read each resource's author credits, requirements and available access methods.