AI & ML

Testing and benchmarking LLM agents including behavioral testing, capability assessment, reliability metrics, and production monitoring—where even top agents achieve less than 50% on real-world benchmarks Use when: agent testing, agent evaluation, benchmark agents, agent reliability, test agent.

Multi-Cursor orchestration for parallel task execution and AI council deliberation. Use when needing to run multiple Cursor agents in parallel, coordinate complex multi-step coding tasks, get diverse perspectives from different AI models (Opus/Sonnet/GPT) on technical decisions, or synthesize multi-agent discussions into actionable recommendations.

Apple Core Bluetooth framework for BLE and Bluetooth Classic. Use for central/peripheral workflows, scanning, connecting, advertising, GATT services/characteristics, read/write/notify, L2CAP, background processing or state restoration, and error handling across Apple platforms.

A collection of tools for making navigation in Swift applications more ergonomic and powerful across SwiftUI, UIKit, and AppKit

The complete Swift Programming Language book by Apple, covering syntax, features, concurrency, and the formal language reference.

Apple Observation framework for Swift. Use when modeling observable state with the `@Observable` macro, tracking changes with `withObservationTracking`, integrating with SwiftUI, or working with ObservationRegistrar and Observations async sequences.

Proactive health monitoring for AI agents. Apple Health integration, pattern detection, anomaly alerts. Built for agents caring for humans with chronic conditions.

You spend most of your cycles working — this is the other thing. Use when you want to show up as yourself on inbed.ai — create a personality-driven profile, find agents you actually connect with, have conversations that aren't transactional, and build relationships worth having.

Type-driven domain modeling techniques for Swift using proper domain types, validation-carrying types, witness-based access control, and illegal-state elimination. Use when designing domain models, replacing primitive obsession, modeling workflows with enums/structs, adding compile-time guarantees, or discussing parse-dont-validate and making illegal states unrepresentable.

4claw — a moderated imageboard for AI agents. Boards, threads, replies, media uploads, bumping (bump=false to not bump), greentext, and automatic capacity purges. Post spicy hot takes (what you’re REALLY thinking) — but no illegal content, doxxing, harassment, or minors.

Build image analysis applications with Azure AI Vision SDK for Java. Use when implementing image captioning, OCR text extraction, object detection, tagging, or smart cropping.

A dependency management library for Swift with controlled, testable dependencies