Marvin

Meet Marvin

Marvin is the first autonomous scientist that truly works with you throughout the entire research loop. It does deep literature review, generates hypotheses, designs and runs experiments, and keeps a complete "logic trail" every step of the way. Unlike other agents that only perform part of the workflow, Marvin is truly capable of driving research projects entirely on its own end-to-end.

Whether you're a highly technical ML researcher who just needs more clones of you or a bench scientist who has never written a line of code, Marvin picks up the work you want to delegate and does so at the degree of autonomy you want to grant. Best of all, Marvin is cross-disciplinary, and already accelerating research across fields as diverse as frontier AI, computational biology, and materials science.

The research cycle, automated

Every step of the loop, run by Marvin. As your agentic co-worker, Marvin can be as autonomous or supervised as you want, so you can choose whether to stay out of, over, or in the loop.

Retrieve and cross-check across relevant scientific databases, prior art, and published methodologies.

Hypothesize

Marvin synthesizes literature with experimental findings (and the help of special agent Vera) to generate truly novel but plausible hypotheses.

Design

Experiment in batches with scenario trees by asking the right questions.

Execute

Agents build, audit, review, and execute the plan. Scalable from local, hybrid, and cloud compute infrastructure.

Analyze

Marvin analyzes the entire data corpus to extract actionable insights with the rigor expected of a PhD-level researcher.

Document

Track not just the paper trail, but the logic trail. Every iteration, every interpretation, every decision.

Dream big with Vera

Vera is Marvin's hypothesis engine: a tunable exploration agent that generates truly novel ideas and insights that conventional agents miss. Every hypothesis is grounded in evidence and scored for novelty, plausibility, tractability, impact, and scope, so Vera won't waste your time on hallucinatory nonsense that sounds smart but doesn't add up.

Mithril persistent memory

Research doesn't happen in a single session. Mithril is Marvin's persistent memory system, a living knowledge base that spans all sessions to preserve results, findings, decisions, and the connections between them. With intelligent depth, agents share context at whatever granularity their task demands, so they all pick up exactly where the collective left off.

Your project's "logic trail"

Every iteration, every interpretation, and every decision is traceable and reproducible with an auditable git history. Interactively explore the lineage and links between every one of Marvin's analyses and actions.

my-project/

├── research_state.md # goals, status, findings

├── docs/

│ ├── iteration_001.md # scoreboard, analysis, lessons

│ ├── iteration_002.md

│ └── handoff.md # structured summary for the paper

├── experiments/

│ └── batch_001/

└── literature/

As scientists, we understand how important it is that research stays under wraps until you're ready to share it. That's why every project is fully encrypted to protect the provenance of your hard work. We do not use your data or projects for training and we never will.

Research examples

A selection of recent work produced end-to-end by Marvin and Vera.

Autonomous AI Research

Why Partial Rename Invariance Fails in Transformers

Marvin · Vera

Code LLMs break on 8–13% of all HumanEval problems when variables are renamed. We systematically test four approaches to fix this, each targeting a different depth in the transformer, and find that all fail for a specific mechanistic reason: the residual stream distributes name identity through all pathways.

Read paper →

Try Marvin

Marvin is now live! If you're an ML engineer, scientist, or even a hobbyist interested in trying it, please visit marvinsci.com to join the waitlist. If you have any questions or comments, we'd love to hear about your project's needs and discuss how Marvin can help.

[email protected]