Primus
Give it a research question and get back a coded experiment, run results, and a finished paper, roughly 30x faster than doing it yourself.
Primus — the verdict: ML researchers and R&D teams who want a full hypothesis-to-paper research loop automated What separates Primus from most autonomous research demos is that it shipped receipts: 30 completed papers in 30 days, with at least one citation from a major lab, not just a benchmark screenshot. Pricing: Free during waitlisted rollout, GPU-limited. Last reviewed: August 2026.
Best For
ML researchers and R&D teams who want a full hypothesis-to-paper research loop automated
Standout Feature
Output has already been cited in published research from Google DeepMind, not just a demo claim
Verdict
The most credible autonomous research tool available right now, if you can get off the waitlist.
Alternatives
Overview
Primus, built by Transformer Lab, is an autonomous AI researcher that runs the entire scientific research loop on its own: it forms a hypothesis, reads millions of relevant papers, writes and runs the experiment code on real compute, iterates on the results, and writes up a finished paper, roughly 30 times faster than a human research team working the same problem. It went live August 10, 2026 with gradual onboarding from a waitlist due to limited GPU capacity, and it's free to use during this rollout. In a 30-day internal test, Primus produced more than 30 complete papers on previously unanswered questions spanning machine learning, seismology, physics, crystallography, and biology, and findings it helped produce have already been cited in published research from labs including Google DeepMind.
It isn't limited to a narrow problem type: you can ask it to fine-tune a model, write and benchmark a custom GPU kernel, explore open questions left in a paper you supply, or test a new forecasting approach against your own sensor data. The output is a real deliverable, code, benchmarks, and a written paper, though it's still built for people who can evaluate research output, not a black box for non-researchers.
Our Take
What separates Primus from most autonomous research demos is that it shipped receipts: 30 completed papers in 30 days, with at least one citation from a major lab, not just a benchmark screenshot. That's a meaningfully higher bar of proof than most agentic tools clear at launch. The honest limitation is that this is built for people who can already evaluate research quality, an ML engineer or R&D lead gets real leverage here, someone without domain expertise will struggle to know if the output is actually sound. The waitlist and GPU constraints mean you can't just sign up and start today, but it's worth getting in line if research throughput is a real bottleneck for your team.
Key Features
- End-to-end autonomous research loop
- Reads millions of papers to ground hypotheses
- Writes and runs real experiment code
- Domain-flexible (ML, physics, biology, and more)
- Produces code, benchmarks, and a written paper
- Self-improving with more experiments run
- • Output independently cited in published research
- • Genuinely broad domain coverage, not narrowly scoped
- • Free to access during the current rollout
- • Waitlisted with limited GPU capacity
- • Requires domain expertise to validate output before real use
- • Mostly proven on ML problems so far despite broader claims
People Also Use
Other Research tools builders reach for alongside Primus.
WolframAlpha
Get exact computed answers to math, science, and data questions instead of a list of links to sift through.
Gemini
Google's flagship model handles research, coding, long-document analysis, and multimodal tasks, and it's woven into every corner of Google Workspace.
ChatPDF
Drop in a PDF and immediately chat with it, getting cited, page-referenced answers instead of manually searching the document.
Google NotebookLM
Turn a pile of uploaded documents into a source-grounded research partner that answers questions, drafts reports, and generates audio/video overviews. Built on Gemini 3.
SciSpace
Search, summarize, and extract data from academic papers using specialized AI agents, spanning workflows from quick reading to full systematic reviews.
Readwise Reader
Pull articles, PDFs, tweets, and newsletters into one inbox, with AI summarizing and surfacing highlights — bundled with Readwise Highlights as a single subscription.