The library

langchain · When using langchain is more effective than generic alternatives.

formax-skill-capture · When using formax-skill-capture is more effective than generic alternatives.

apprenticeship-pedagogy · When using apprenticeship-pedagogy is more effective than generic alternatives.

llamaindex · When using llamaindex is more effective than generic alternatives.

vue · When using vue is more effective than generic alternatives.

craft-methodology · When using craft-methodology is more effective than generic alternatives.

chroma · Open-source RAG prototyping where self-hosted storage is preferred over managed cloud.

gemini-deep-research · Multi-source synthesis tasks where systematic web search + AI analysis beats single-prompt research.

materials-and-fit · Trades specification when wide panels, metal beams, or humidity-sensitive assemblies are involved.

faiss · High-throughput vector search where metadata filtering is not required and GPU acceleration helps.

measurement-and-tolerance · Specification work when parts must interface precisely and function depends on dimensional stability.

pinecone · Production RAG where managed infrastructure and low latency (<100ms) are non-negotiable requirements.

tool-and-machine · Tool justification and apprenticeship teaching where understanding the tool-machine spectrum matters.

qdrant-vector-search · Production RAG requiring on-premise control, Rust performance, or complex payload filtering during search.

workshop-practice · Workshop setup when efficiency over sustained periods depends on physical layout and tool discipline.

sentence-transformers · Text embedding when you need semantic vectors that are domain-tuned or when you want pure open-source.

context-handoff · Multi-agent orchestration where agents must hand off work and restore full execution context.

dspy · Complex prompt pipelines where you want automatic optimization and compositional abstraction.

ecosystem-alignment · Agent design review when the agent lives in a multi-stakeholder ecosystem with competing interests.

guidance · Structured extraction when you need 100% format compliance and can define the grammar precisely.

issue-triage-pr-review · High-volume repositories where initial triage and pattern detection beats manual read.

instructor · Extraction tasks where you want automatic validation and retry without building your own harness.

refinery-merge · Data programming when multiple weak sources must be reconciled into clean training sets.

outlines · Batch generation where you need guaranteed valid JSON/SQL/code and sampling speed is critical.

security-hygiene · Production agent deployment where adversarial input and prompt injection are realistic threats.

langsmith-observability · Multi-step agent debugging when you need visibility into every LLM/tool call and latency bottleneck.

session-awareness · Resuming work after interruption when project state matters more than fresh context.

phoenix-observability · Production LLM systems needing detailed observability without vendor lock-in or cost overhead.

audiocraft-audio-generation · Applications requiring controllable, variable-length music generation without licensing constraints.

expository-writing · Academic papers, op-eds, and reports where logical rigor and audience trust depend on visible reasoning.

blip-2-vision-language · Zero-shot image understanding tasks where training data is unavailable and frozen backbones reduce compute.

narrative-craft · Fiction and story-driven nonfiction where emotional truth and structural integrity matter equally.

clip · Quick zero-shot image classification and semantic search when training data unavailable and model is open-source.

poetry-form · Poets seeking formal discipline and readers wanting to understand how sound and structure create meaning.

evaluating-cosmos-policy · Evaluating vision-language-action models on sim-to-real robotics tasks with detailed latency profiling.

research-writing · writing research papers, evaluating sources, constructing academic arguments, or teaching research methodology

llava · Large Language and Vision Assistant

revision-editing · Use when revising drafts, editing for clarity, running workshops, or teaching the revision process.

fine-tuning-serving-openpi · Use when adapting pi0 models to custom datasets, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.

voice-style · Use when developing voice, analyzing style, adapting register, or teaching style awareness.

fine-tuning-openvla-oft · Use when reproducing OpenVLA-OFT paper results, training custom VLA action heads (L1 or diffusion), deploying server-client inference for ALOHA, or debugging normalization, LoRA merge, and cross-GPU issues.

aminet-browser · Use when searching, browsing, or managing package collections.

segment-anything-model · Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.

aminet-emulator · Use when configuring emulation, managing ROMs, or launching Amiga software.

stable-diffusion-image-generation · Use when generating images from text prompts, performing image-to-image translation, inpainting, or building custom diffusion pipelines.

toss-push · Use for toss-push tasks and operations.

aminet-index · Managing complete Aminet package database lifecycle with incremental RECENT-based updates.

whisper · Robust multilingual ASR on noisy audio; 72.9k GitHub stars, MIT licensed, 680k training hours.

aminet-installer · Safe Amiga package installation with atomic tracking, dependency detection, and enforced scan gates.

knowledge-distillation · Retaining 90%+ of large-model performance in smaller deployable student (70B→7B).