ClawsGO ScienceReview: a literature review that runs its own analysis
ClawsGO Science is a research agent with its own cloud computer. Give it a task in plain English, such as "pull the 2020–2026 trials comparing two treatments, run a meta-analysis, and draft the results section," and it searches the literature, screens papers, extracts the data into CSV tables, runs the statistics in Python, draws the forest plot, and writes the draft with citations. LaTeX manuscripts compile straight to PDF.
Every search, command, and file edit is logged and replayable, so you can check the work instead of trusting it. You can point it at your own files with @, switch the underlying model per task, or connect a lab GPU over SSH for heavy jobs. It's aimed at researchers, but also at consultants, policy analysts, and due-diligence teams. The cloud machine isn't billed separately; you pay for model use in credits, and plan prices sit inside the app.
Keywords
research agent, literature review, meta-analysis, data analysis, latex
- End-to-end tasks: Search, screening, extraction, analysis, and a written draft.
- Real outputs: CSV evidence tables, Python scripts, figures, and LaTeX PDFs.
- A replayable log: Every search, command, and edit recorded.
- Bring your own compute: Connect a lab GPU over SSH.
- Model choice: Switch the underlying model per task.
TMRW VERDICT
Deep research that shows its working
by TMRW Team·Nov 2, 2026
The deep research modes in ChatGPT and Gemini hand you a tidy report and no way to see how it got there. ClawsGO goes further: it runs the analysis, keeps the data tables and the code, and logs every step. For a literature review or a market scan where someone will ask "where did that number come from," that log is the product.
This is a specialist tool. Researchers, analysts, and consultants who write evidence reviews will get the most from it, and it finished second on Product Hunt on November 1. Everyone else should stick with the deep research mode they already pay for.
The site itself warns that it can make mistakes, and a meta-analysis is exactly where one bad screening call skews the result. Treat the first draft as a junior analyst's work and check the included studies. Credit-only pricing with no plan prices up front also makes a 38-page review hard to budget.
