The library

evolving-ai-agents · When optimizing agent performance through iterative evolution cycles that automatically mutate prompts, skills, and memory.

autogpt-agents · When building persistent autonomous agents with visual workflows and external triggers without code.

crewai-multi-agent · When using crewai-multi-agent is more effective than generic alternatives.

sql-patterns · When using sql-patterns is more effective than generic alternatives.

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

formax-skill-capture · When using formax-skill-capture 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.

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

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.

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

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

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

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.

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

llava · Large Language and Vision Assistant

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.

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.

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

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).

aminet-mirror · Bulk downloading packages with fallback mirrors, atomic state persistence, and resume-from-interruption.

long-context · Processing long documents (32k-128k+ tokens) by extending pre-trained models with RoPE/YaRN interpolation.

aminet-scanner · Enforcing security gates on Amiga package installation via 3-layer scanning (signature + heuristic + emulated).

model-merging · Creating specialized models by blending domain expertise (math+coding+chat) in minutes without retraining.

model-pruning · Achieving 50% sparsity with minimal accuracy loss via one-shot pruning without retraining.

kp-content-authoring · Generating consistent, scaffolded educational content across 4 tiers with prerequisite chains.

moe-training · Scaling model capacity without proportional compute via conditional expert routing.

kp-content-validation · Ensuring all tier packs meet quality bars before publishing.

speculative-decoding · 2-8x inference speedup with small draft model validated by large verifier.

academic-plotting · Creating journal-ready plots with minimal code (IEEE/Nature style templates included).

ml-paper-writing · Rapidly drafting ML papers with automatic figure integration and citation formatting.

systems-paper-writing · Structure a 10-12 page OSDI/SOSP/ASPLOS/NSDI/EuroSys paper with authoritatively grounded paragraph blueprints.

brainstorming-research-ideas · Move from vague curiosity to concrete, defensible research direction via problem-first vs. solution-first analysis and abstraction-ladder exploration.

adversarial-pr-review · Verify PR claims match actual implementation against approved spec before merge, detecting scope creep and divergences.

creative-thinking-for-research · Escape local-optimum thinking via bisociation, problem reformulation, and tension-resolution frameworks grounded in decades of creativity research.