Lab Rat
Lab Rat teaches your AI coding agent to work like a careful ML researcher: reproduce papers, launch and compare runs at the same epoch, and check every claim before it costs you weeks of compute.
Built by Fatih Cagatay Akyon (2000+ citations, 5 patents) from 2200+ Claude Code and Codex sessions. Every guardrail traces to a real mistake.
Install
Claude Code
claude plugin marketplace add fcakyon/labrat
claude plugin install labrat@labrat
Update with claude plugin update labrat@labrat.
Coming from phd-skills? Remove it first with claude plugin uninstall phd-skills@phd-skills and claude plugin marketplace remove phd-skills.
Claude.ai and Claude Desktop
Open Customize, then Plugins. Select Add, then Add marketplace, choose Add from a repository and enter fcakyon/labrat. Install Lab Rat from the Discover tab.
Needs a paid plan. Chat runs the skills. The plugin also syncs to Claude Code when you sign in there with the same account.
Codex
codex plugin marketplace add fcakyon/labrat
codex plugin add labrat@labrat
Update with codex plugin marketplace upgrade labrat.
Cursor
cursor-agent plugin marketplace add https://github.com/fcakyon/labrat
Then start cursor-agent, enter /plugin and install Lab Rat. To update, run cursor-agent plugin marketplace remove labrat, add it again and reinstall.
Gemini CLI
git clone https://github.com/fcakyon/labrat ~/.labrat
gemini extensions link ~/.labrat/plugin
Update with git -C ~/.labrat pull.
Every tool gets the same 11 skills. The research peer review and notifications run in Claude Code only. Paper search needs Paper Search CLI (uv, Python 3.10+, setup), nothing else does. Optional: /labrat:setup shows what it detected and turns on extras like notifications to ntfy, Slack or email, the command allowlist and LaTeX.
Why
AI agents make research mistakes that cost weeks of compute. Real ones from my sessions:
- It read "done?" as "dont?" and started uploading thousands of files.
- It restarted a 50-hour training job without diffing the config against the reference run. Three days lost.
- It killed an experiment over a proxy metric that had not converged, before the downstream eval could show the real result.
- It ran
rm -rfon a path it remembered wrong and deleted local checkpoints.
The skills teach the method, not a script, so the agent writes code for your setup (wandb, neptune, local files) and stops to check the evidence before it claims a result.
Skills
A skill starts when you describe its task, or run it as /labrat:<skill>.
| Say | Skill |
|---|---|
| "find related papers on X", "find gaps in the literature on X" | literature-research |
/labrat:reproduce arxiv 2508.12345 |
reproduce, from the paper to replication runs |
| "design an ablation study" | experiment-design |
| "launch the new training run" | launch, with a pre-flight checklist |
| "why is my loss diverging?" | debug, evidence before fixes |
| "compare run alpha to baseline" | compare, at the same epoch |
| "analyze dataset bias" | dataset-curation |
| "check my numbers match the code", "verify my BibTeX", "prepare code for release" | paper-check |
| "review my methods section", "set up LaTeX for CVPR" | paper-write |
| "what will reviewers ask?", "pick my strongest ablations" | rebuttal |
/labrat:setup |
setup |
In Claude Code, a fresh-context research peer hook checks each conclusion against the actual artifacts and sends you to the matching skill, like the launch checklist before a run.
For long runs, pair it with /loop 30m check experiment logs, notify me if metrics beat the baseline or if loss starts to diverge.
Star history
Contributors
MIT license.