Skip to main content
plugin

experiment-tracker · rohitg00 — Claude Code plugin: what it does, how to install

experiment-tracker logs metrics for ML training runs and compares runs side by side inside Claude Code. Useful once you have more than one run to judge.

Apache-2.0 ★ 2,858 updated 2026-05-12

Install into Claude Code · Plugin marketplace All methods and platforms ↓
/plugin marketplace add rohitg00/awesome-claude-code-toolkit
/plugin install experiment-tracker@claude-code-toolkit
Open on GitHub

What experiment-tracker does

experiment-tracker is a Claude Code plugin for keeping track of ML experiments. It logs metrics for each run and compares runs against each other, so results from different training attempts sit in one place.

It comes from rohitg00's rohitg00/awesome-claude-code-toolkit repository and is licensed Apache-2.0. Installation goes through that repository's marketplace: /plugin marketplace add first, then /plugin install. Skip the first command and the second has no marketplace to resolve experiment-tracker@claude-code-toolkit from.

What it helps with

  • log metrics after each model training run
  • compare two runs side by side
  • keep a record of ML experiments without leaving Claude Code
  • collect results from several attempts into one comparison

Example prompts for the agent

  • Log the metrics from this run with experiment-tracker
  • Use experiment-tracker to compare my last two training runs
  • Track experiments for this model with experiment-tracker

How to install experiment-tracker

Plugin marketplace

/plugin marketplace add rohitg00/awesome-claude-code-toolkit
/plugin install experiment-tracker@claude-code-toolkit

Step by step, with commands for each platform: Claude Code plugins: marketplaces, installing, and building your own

Questions about experiment-tracker

How do I install experiment-tracker in Claude Code?

Run /plugin marketplace add rohitg00/awesome-claude-code-toolkit first, then /plugin install experiment-tracker@claude-code-toolkit.

What does experiment-tracker do?

It tracks ML experiments: it logs metrics for runs and compares runs with each other.

Who made experiment-tracker and what is the license?

rohitg00 wrote it, and it lives in the rohitg00/awesome-claude-code-toolkit repository under Apache-2.0. The platform is Claude Code.

Source text

experiment-tracker · Apache-2.0
ML experiment tracking with metrics logging and run comparison

© rohitg00 · Apache-2.0 · rohitg00/awesome-claude-code-toolkit

Similar plugins

All plugins for AI and ML →

experiment-tracker by other authors comes first.

experiment-tracker Michael Galpert experiment-tracker is a Claude Code plugin for tracking A/B tests and feature experiments, documenting changes, and reviewing results before a launch decision. ★ 1,013repo stars experiment-tracking-swanlab Orchestra Research experiment-tracking-swanlab — a skill that shows your agent how to track ML runs in SwanLab: metrics, configs, media logging and a local dashboard. CX Codex +1 1,000installs monitor-experiment allenai The monitor-experiment skill tracks Beaker experiments until all jobs finish, displaying each job's status and failure logs. Follow progress without manually checking status. CX Codex +1 1installs ai-research-explore lllllllama ai-research-explore governs deep learning research exploration on top of an existing baseline. It isolates candidate experiments and generates structured comparison reports. CX Codex +1 363,600installs explore-run lllllllama explore-run plans bounded exploratory machine learning runs with comparability caveats and saves summaries to explore_outputs. CX Codex +1 362,600installs nemo-rl-auto-research NVIDIA nemo-rl-auto-research automates hypothesis testing and training loops in NeMo-RL and NeMo-gym. Keeps experiments tracked through dedicated git branches and TSV logs. CX Codex +1 1,900installs mlflow-onboarding mlflow The mlflow-onboarding skill figures out whether your project is GenAI or classic ML and walks you through the matching MLflow quickstart. Handy when you need tracking or tracing but don't know where to begin. CX Codex +1 1,300installs

From the same set178

The whole set →

Project sponsors

Companies that keep this analytics open