AI/ML

A comprehensive memory management system for AI agents offering persistent storage, pattern learning, and reasoning capabilities with impressive performance claims and multiple integration options.

A comprehensive reference guide for orchestrating multi-model AI workflows through PROXY_MODE directive, enabling seamless integration of external AI models within Claude's agent system.

A comprehensive Skill for distributed neural network training and deployment in E2B sandboxes, offering advanced architectures, template marketplace, and cluster management with innovative features like divergent patterns and decentralized consensus.

Comprehensive guide to LangChain4j tool and function calling patterns with excellent practical examples, covering basic to advanced implementations for Java-based AI agents.

A comprehensive integration guide for LangChain4j with Spring Boot, offering practical patterns for AI-powered Java applications with good security practices and production readiness.

A comprehensive reinforcement learning toolkit for AI agents offering 9 algorithms with WASM acceleration, practical CLI/API interfaces, and clear training workflows for building self-improving autonomous systems.

Provides structured templates and best practices for PyTorch Lightning development. Covers LightningModule organization, Trainer configuration, distributed training strategies, and common debugging patterns. Includes ready-to-use code snippets for data pipelines, logging, and multi-GPU setups.

A Python script that generates multiple images using OpenAI's image models with configurable parameters. It creates random structured prompts, supports batch generation, and outputs an HTML gallery for easy viewing. Handles different models (GPT image, DALL-E 2/3) with appropriate defaults and limitations.

A comprehensive RAG implementation guide with practical Java examples, covering core components, patterns, and best practices for building knowledge-grounded AI systems.

Provides a systematic approach to evaluating AI agents using binary criteria instead of subjective scales. Focuses on error analysis, trace examination, and creating component-level tests. Includes practical templates for graders and workflows to identify failure patterns in agent reasoning.

This skill integrates AgentDB's high-performance vector database with ReasoningBank patterns for adaptive agent learning. It provides trajectory tracking, verdict judgment, memory distillation, and pattern recognition with 150x faster retrieval. Includes CLI tools, TypeScript API, and 100% backward compatibility with legacy ReasoningBank systems.

Provides a structured guide to implement document chunking for RAG systems, covering five strategies from basic fixed-size to advanced semantic methods. Includes concrete Python examples, performance metrics, and implementation steps for different document types.