crimson-knight

Grant ORM advanced features including enum attributes, dirty tracking, serialized columns, value objects, horizontal sharding, and async operations.

Grant ORM associations including belongs_to, has_one, has_many, has_many through, polymorphic, dependent options, counter_cache, eager loading, and nested attributes.

Grant ORM lifecycle callbacks, transaction blocks, nested transactions with savepoints, isolation levels, optimistic and pessimistic locking.

Create, read, update, and delete operations in Grant ORM including bulk operations, batch processing, upserts, and convenience methods.

Generate a new Grant ORM model file with proper structure, column definitions, validations, associations, and callbacks.

Defining Grant ORM models with columns, types, primary keys, timestamps, connections, converters, and serialization.

Grant ORM query builder API including where clauses, operators, WhereChain, OR/NOT groups, scopes, aggregations, raw SQL, and Enumerable integration.

Grant ORM security features including encrypted attributes, secure tokens, signed IDs, token generators, and data normalization.

Install and use the crystal-audio library for microphone recording, system audio capture, and on-device transcription in Crystal. Covers macOS and iOS platform setup, native extension compilation, and basic recording patterns.

Cross-compile Crystal code as a static library for iOS and link it into a Swift app. Covers the complete pipeline: cross-compilation, runtime initialization, Xcode project setup, and critical linker configuration. Documents hard-won solutions to dead-stripping, symbol conflicts, and simulator deployment issues.

Record audio from the microphone using crystal-audio's Recorder class. Covers AudioQueue configuration, WAV output, buffer management, and real-time audio callback patterns. Use this when implementing mic recording features in Crystal.

Capture system audio (what the computer is playing) using crystal-audio. Covers ProcessTap (macOS 14.2+), ScreenCaptureKit fallback (macOS 13.0+), and the low-level SystemAudioCapture API for real-time audio processing.

Run AI models locally on Apple Silicon from Crystal with the llamero shard (Llamero::Native, MLX/Metal). Use when the user wants on-device or local LLM inference, local chat, token streaming, structured JSON output from a local model, or to load/keep a model resident in memory without cloud APIs like OpenAI. Also covers downloading mlx-community models and activating LoRA adapters.

Train LoRA/QLoRA adapter "filters" on a local model with the llamero shard (Crystal, Apple Silicon). Use when the user wants to fine-tune a local model, teach a model new facts or documents (manuals, internal docs, domain knowledge), create/train a LoRA or QLoRA adapter, build a golden dataset, or toggle learned knowledge on and off without reloading the model. No Python required.

Call cloud AI APIs (OpenAI, Anthropic/Claude, Groq, OpenRouter) from Crystal with the llamero shard - chat, streaming, structured JSON output, embeddings, and automatic failover between providers. Use when the user wants to call an LLM API from Crystal, needs provider failover/retries, or wants typed structured responses from a cloud model.

Save, search, describe, and manage bookmarks with the waypoints CLI and Crystal library — SQLite FTS5 search, local-AI auto-description, and a --db/WAYPOINTS_DB overridable store. Use when adding or finding bookmarks, or when calling the Waypoints::Store / Describer API from Crystal.

Store and retrieve branch-scoped agent memories with engram — search decision history, record new decisions as memory migrations, understand why code is the way it is. Use when asked why a decision was made, when recording a decision, or when reviewing a branch.