ml-experiments

2 Lines of code to track ML experiments + EDA + check into Github

ML Experimentation Platform

lightweight MCP server for ClearML

Unsorted Playground for Machine Learning, Reinforcement Learning and other AI Experiments

AI Agent plugin for Autoresearch with AI (Claude, OpenClaw, etc) to improve anything!

Research-first machine learning experiment tracker for comparing model metrics, scalar curves, artifacts, and experiment lineage.

A self-improving ML agent that compounds capability across projects through knowledge crystallization, reusable skills and shared ML/MLOps infrastructure.

Paper-to-code replication workspace with Jupyter notebooks and Python implementations of ML and deep learning research ideas.

A hands-on collection of machine learning concepts, algorithms, and practical implementations. Designed to help learners and practitioners apply ML techniques with clarity and efficiency. 🚀

A lightweight Python library for reproducible computational experiments with an ultra-simple, smart API. From idea to insight in under 5 minutes, with zero configuration.

Nighttime ML experiment workflow with Claude Code multi-agent orchestration (Planner / Executor / Reviewer / Auditor)

Contains code and slides for our talk at Cloud Next 2022: Better Hardware Provisioning for ML Experiments on GCP.

A desktop workbench for AI research: questions, frozen experiments, runs, samples and findings kept as plain files in your project, with a research assistant on API models, local models (LM Studio, MLX), Claude Code or Codex that does only what you allow. Runs on your computer or your own SSH host.

Turn research ideas into reproducible, auditable experiments: frozen specs, sandboxed runs and evidence-gated VERIFIED results. 把研究想法变成可复现实验

An application of the WhizML codebase for an analysis of cardiovascular disease risk.

A multi-agent research design council that uses Flask and Backboard AI to critique, refine, and evaluate experimental ideas.

MediaPipe face landmarker, detector, and recognition experiments.

Autonomous experiment loops for Claude Code. Let AI run 100 experiments while you sleep. Works on any codebase.

A reusable codebase for fast data science and machine learning experimentation, integrating various open-source tools to support automatic EDA, ML models experimentation and tracking, model inference, model explainability, bias, and data drift analysis.

An application of the WhizML codebase for an analysis of Walmart weekly sales.