Machine learning

Strip LLM writing tics from prose so it reads like a person wrote it.

Delegate edit/implementation work to a local LLM (Ollama-backed) running as a separate claude or opencode CLI process, while this session stays the…

给 agent 会话配「观察者」：读完整会话历史（Codex rollout JSONL、Claude Code transcript、 Kimi wire、DeepSeek Harness / dsh 的 zstd 会话，含 subagent/team 日志）， 用「物证流 vs 叙事流」对质，找出执行…

Infer gene regulatory networks (GRNs) from expression matrices using arboreto's scalable GRNBoost2 and GENIE3 tree-ensemble algorithms with Dask-distributed…

Runs molecular machine learning with DeepChem — diverse featurizers, pre-built MoleculeNet benchmark datasets, and pre-trained models (ChemBERTa, GROVER) for…

Build phylogenetic trees end-to-end from raw sequences — MAFFT multiple sequence alignment, optional TrimAl trimming, IQ-TREE 3 maximum-likelihood inference…

Loads Therapeutics Data Commons (TDC, PyTDC) AI-ready drug-discovery datasets and benchmarks — ADME, toxicity, drug-target interaction (DTI), scaffold splits…

Provides the RDKit cheminformatics toolkit for low-level, fine-grained molecular primitives — SMILES/SDF parsing, descriptors (MW, LogP, TPSA), fingerprints…

Evaluate an agent skill against a golden dataset with fact-level LLM verdicts and deterministic Python gates.

Use when working with a trading-card sales tape — any sale-level dataset of collectible card transactions across multiple venues (Pokémon TCG, sports cards…

Use when evaluating MCP-enabled agents, tool-using LLM systems, multi-server workflows, tool-selection quality, trajectory quality, task completion, or MCP…

Automatiza a criação de frameworks de Machine Learning (Perceptron/Softmax) para Geociências com rigor acadêmico Qualis A1.

分析 Android 项目源码，用 LLM 从多维度生成 AI 自动化测试所需的先验知识文档，打包上报测试平台。核心价值：让 AI 测试 Agent 在运行前就知道「测什么、怎么断言、有哪些陷阱」。触发词：「分析我的 Android 项目」「生成测试画像」「理解这个 App 的业务」「提取测试先验知识」「帮我分析…

High-performance numerical computing and machine learning workflows using JAX.

Bayesian modeling with PyMC.

Detect and escape collective homogeneity by querying multiple LLM architectures, then separating modal convergence (what every AI says) from…

Run GPT Researcher as a self-hosted open-source deep research framework using an LLM plus a search provider.

Builds Python-based Databricks applications using Dash, Streamlit, Gradio, Flask, FastAPI, or Reflex.

Generate video from a photo (or two) using self-hosted LTX-2.3 on Modal GPU.

基于Sorftime MCP的深度选品调研。通过LLM Agent执行多维度分析：数据采集→属性标注→交叉分析→竞品VOC→壁垒评估→选品决策评估。交互式执行，输出Markdown报告和Dashboard看板。

Numeric-aware prompt compression for long ENGLISH prose you're about to feed another LLM — meeting transcripts, paper intros/discussion, web-article bodies…

Give any repository a code-derived LLM wiki — cited claims, blob-SHA drift checking, coverage auditing, a generated index.

Security testing for Large Language Models (Prompt Injection, Jailbreaking).

Build identity-preserving character generation workflows and pipelines in ComfyUI.