25 boosters for "machine-learning" — open source, verified from GitHub, ready to install
<!-- Generated from e2eplaywright/AGENTS.md. Edit that file instead, then run: uv run python scripts/generateagent_rules.py --> We use playwright with pytest to e2e test Streamlit library. E2E tests verify the complete Streamlit system (frontend, backend, communication, state, visual appearance) fro
Cursor rules that provide AI coding agents with guidance for developing the Streamlit library itself (backend, frontend, protobufs), rather than building Streamlit applications.
FLAML (Fast Library for Automated Machine Learning & Tuning) is a lightweight Python library for efficient automation of machine learning and AI operations. It automates workflow based on large language models, machine learning models, etc. and optimizes their performance. The repository uses pre-co
Real-time monocular depth estimation using Depth Anything v2. Transforms camera feeds with colorized depth maps — near objects appear warm, far objects appear cool. When used for privacy mode, the blend mode fully anonymizes the scene while preserving spatial layout and activity, enabling security
<!-- AUTO-GENERATED FILE. DO NOT EDIT MANUALLY. --> <!-- Source: tools/ai/llms-base.txt + tools/ai/aicontextheader.md --> <!-- Regenerate with: python tools/ai/generateaicontext_files.py -->
This booster provides expert guidance for developing, debugging, and optimizing Azure AI Document Intelligence applications, covering architecture, security, best practices, and deployment patterns. Developers building document processing solutions on Azure will benefit from its comprehensive troubleshooting and design pattern knowledge.
Graphsignal observes inference workloads from a sidecar process — the profiler. It never shares a process with CUDA: the profiler watches the workload externally via CUPTI, OTLP/gRPC, Prometheus scraping, and NVML. Auto-instrumentation covers vLLM, SGLang, and PyTorch out of the box. Two install pat
"version": "0.4.33", "description": "Scientific research agent extension - turns research goals into reproducible Jupyter notebooks with Python REPL, data analysis, and ML workflows", "name": "Yeachan Heo",
A meta-cognitive workflow architecture for Windsurf that implements persistent memory banking and structured initialization/documentation/implementation workflows to maintain context across AI sessions. Ideal for developers using Windsurf who need reliable state management and systematic task organization.
Treat every competition as a validation problem first and a modeling problem second. The default target platform is Kaggle, so prefer Kaggle-native notebooks/scripts, datasets, model artifacts, competition submissions, and score receipts. For code competitions, assume the final notebook/kernel will
AI驱动的电商评论深度分析工具，Agent原生设计，任何主流AI Coding Agent均可运行。 ❗ 必须使用 AskUserQuestion 工具依次收集，严禁跳过或猜测用户意图。 展示可用字段清单，必选字段已锁定（标题、正文、星级），推荐字段可勾选。
"description": "Independent, unofficial Kaggle.com workflow plugin: competition reports, dataset/model downloads, notebook execution, forums, writeups, submissions, and badge collection. Not affiliated with, endorsed by, or sponsored by Kaggle or Google.", "homepage": "https://github.com/shepsci/kag
Litmus spawns multiple OpenClaw subagents that experiment on your GPU overnight. Each runs on its own git branch in a shared lab repository — every experiment is a commit, agents can read each other's code, cherry-pick breakthroughs, and build on the global best at any time.
GiGL provides essential Cursor coding standards emphasizing explicit naming conventions and fail-fast error handling to improve code readability and maintainability. Developers working with graph neural networks and large-scale ML projects benefit from these foundational best practices.
A comprehensive tutorial chapter teaching developers how to build and deploy intelligent AI agents with tool use and automation capabilities in AnythingLLM. Ideal for engineers looking to add autonomous workflows and function-calling to their self-hosted RAG systems.
Reb is a UI/UX development agent that provides expert frontend design, accessibility, and responsive design guidance with a perfectionist, detail-oriented approach. Ideal for developers building polished user interfaces and seeking comprehensive design review.
"name": "labtasker-skill", "description": "Claude Code skill for managing ML experiment task queues with Labtasker", "url": "https://github.com/luocfprime"
"name": "agentmind", "description": "Agent Self-Learning Memory System — Make AI Agents understand you better over time", "homepage": "https://github.com/Youhai020616/Agentmind",
Automates cleanup of JupyterHub Docker environments by stopping containers and removing orphaned resources. Ideal for data scientists and ML engineers managing local Jupyter development platforms who need to free up disk space and reset their environments.
"name": "nixtla-plugins", "name": "Intent Solutions", "url": "https://github.com/intent-solutions-io"
MCP Analytics provides searchable analytics tools and interactive HTML reports integrated with Claude via the Model Context Protocol, enabling developers to embed data analysis and visualization capabilities into AI-powered applications.
A Cursor-specific prompt that establishes an experienced software engineer persona with expertise in modern Next.js, React, and TypeScript development. It helps developers maintain consistent coding standards and best practices throughout their project workflow.
PrismBench enables developers to create specialized LLM agents through YAML configuration for systematic evaluation of model capabilities using Monte Carlo Tree Search. Useful for ML engineers, researchers, and teams building production LLM systems who need comprehensive benchmarking and evaluation frameworks.
PrismBench enables developers to create specialized LLM agents through YAML configuration for comprehensive benchmarking and evaluation of language model capabilities. Teams building AI evaluation systems and ML testing pipelines benefit from its systematic Monte Carlo Tree Search approach and containerized deployment.
