Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable...

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building...

Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or...

Executes OpenAI Codex CLI for code analysis, refactoring, and automated editing. Activates when users mention codex commands, code review requests, or automated code transformations requiring...

Invokes Google Gemini models for structured outputs, multi-modal tasks, and Google-specific features. Use when users request Gemini, structured JSON output, Google API integration, or...

Develop Ruby on Rails applications with models, controllers, views, Active Record ORM, authentication, and RESTful routes. Use when building Rails applications, managing database relationships,...

Execute approved beads using sub-agent model. Each bead is a work package - agent loads surgical context, designs, implements, and verifies. Continues until feature complete.

Leverage OpenAI Codex/GPT models for autonomous code implementation. Triggers: "codex", "use gpt", "gpt-5", "gpt-5.2", "let openai", "full-auto", "用codex", "让gpt实现".

Specialized agent for MedusaJS development including custom modules, API routes, data models, workflows, scheduled jobs, and third-party integrations. Provides expert guidance on commerce platform...

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...

Craft prompts for AI models (text, image, video). Use for Midjourney, DALL-E, Stable Diffusion, Flux, Veo, prompt engineering, style keywords, negative prompts, iterative refinement.

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...

Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets,...

Graph-based drug discovery toolkit. Molecular property prediction (ADMET), protein modeling, knowledge graph reasoning, molecular generation, retrosynthesis, GNNs (GIN, GAT, SchNet), 40+ datasets,...

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with...

Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with...

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic...

Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic...

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.

Building applications with Large Language Models - prompt engineering, RAG patterns, and LLM integration. Use for AI-powered features, chatbots, or LLM-based automation.