Machine learning

Route DeblurGAN users to data preparation, training, and single-image inference workflows.

Routes Distil-Whisper inference, PyTorch distillation training, and Flax reproduction workflows.

Use FlagEmbedding for embedding, reranking, retrieval evaluation, and fine-tuning workflows.

Guide FunClip ASR video/audio clipping, LLM-assisted clipping providers, and release packaging workflows.

Route GeoAI geospatial data, inference, training, foundation-model, and integration workflows.

Observe the user's screen via screenpipe, detect repeated research workflows, match them against existing scientific-agent-skills, and draft new skills (or…

LM Studio のローカル LLM に調査・修正を委任（Codex CLI 経由） (user)

LM Studio のローカル LLM でブランチ差分をレビュー (user)

Search and structurally lint this LLM wiki vault (wiki/, raw/).

Route Auto-PyTorch tabular and forecasting workflows.

Validate local single-cell raw-count matrices and propose researcher-approved Scanpy QC, embedding, clustering, and marker exploration.

Studio-quality music production with multi-pass K3 inference pipeline.

TypeDB-backed ontological memory with schema-driven retrieval.

Build, validate, and package reusable evaluation datasets for agent and LLM systems from prompts, traces, tool-call logs, metadata, and expected outcomes.

Web search, online search, real-time search, internet search, Google alternative, Bing alternative, DuckDuckGo alternative, search the web, lookup online…

Reference for the Claude API / Anthropic SDK - model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration.

Analyze PyTorch CUDA memory snapshots from torch.cuda.memory._dump_snapshot(), torch.cuda.memory._snapshot(), or memory_viz artifacts.

Nightly memory consolidation across the Weblyfe agent fleet (Appie-1/2/5 OpenClaw + Appie-3/4 Hermes).

Build unified multi-level category taxonomy from hierarchical product category paths from any e-commerce companies using embedding-based recursive clustering…

Humanize AI-generated text by detecting and removing patterns typical of LLM output.

Extract and generate structured Learning Objectives (ULO, CIO, SIO) from raw syllabus and context text using LLM scripts.

LLM-as-a-judge evaluations over OpenAI-compatible APIs (including NVIDIA Nemotron & LM Studio).

Use when preparing photos or images for a news wire, publication, photo CMS, or archive — embedding caption, byline, credit, alt text, keywords, copyright or…

Evolution of Heuristics (EoH) — arxiv 2401.02051.