Med Auto Scienceis for teams already doing real medical research. It keeps study questions, data, analyses, evidence, drafts, and delivery files connected on one governed study line so the work can keep moving and stay reviewable.
Why Med Auto Science
The hard part of medical research is rarely a single paragraph. It is moving a study from data and ideas toward a paper that can be reviewed, revised, and submitted.
Medical teams often run into the same problems:
- You have data, but it is not clear which question is worth pursuing.
- You have preliminary results, but they do not yet form one manuscript line.
- Figures, drafts, analysis notes, and validation results drift across folders and conversations.
- Review, extra analysis, claim revision, and delivery files overlap until progress is hard to explain.
- Multiple disease studies run in parallel, and key evidence or decisions can be lost.
Med Auto Science is built around those research problems.
It organizes a medical study as a research line: frame the valuable question, prepare the data and evidence, advance analysis and validation, build the manuscript story, and keep paper-facing files ready for review and delivery.
It does not treat medical research as a rigid pipeline. A study can start with several possible directions, return to data and evidence for comparison, and gradually converge into a clearer manuscript line. AI keeps the work moving, organized, and revised; researchers keep clinical framing, claim acceptance, and final submission judgment.
One-Sentence Quick Start
You can start with prompts like:
- "Help me find a paper-worthy question from this colorectal cancer dataset, tell me what evidence is still missing, and propose the next step."
- "I already have preliminary results. Turn them into one manuscript line and tell me what validation to do next."
- "Keep pushing this disease study toward a publishable paper, and keep the progress plus files organized as we go."
Core Highlights
Identify paper-worthy questions from data
Start with a disease cohort, registry, or real-world dataset, then identify questions with clinical value, evidence support, and manuscript potential before piling up analyses.
Turn scattered results into a manuscript line
Existing analyses, early findings, figures, and drafts are organized into a clearer research story with explicit next evidence steps.
Keep progress and delivery files together
Tasks, files, figures, drafts, validation notes, and deliverables stay tied to the same study workspace so the line remains reviewable and easy to continue.
Let AI do the heavy lifting while researchers keep judgment
AI can help prepare data, run analyses, organize evidence, and report progress. Clinical framing, claim acceptance, and final submission decisions stay with researchers and PIs.
Compare, revise, and review repeatedly
Medical papers do not finish in one generation. The system can keep multiple claims, evidence gaps, analysis routes, and review findings on the same research line, then keep producing the next more-reviewable manuscript and evidence package.
What It Helps With
- Finding a study question worth continuing from a disease-specific dataset, registry, or cohort.
- Turning existing analyses and early results into one manuscript line.
- Managing validation, subgroup analysis, calibration, clinical utility analysis, and other supporting evidence.
- Keeping multiple related studies organized in one workspace.
- Keeping paper-facing results, figures, drafts, and delivery files tied to their study.
- Comparing study claims, evidence gaps, analysis routes, and review findings inside the same study stage, then producing the next manuscript and evidence package.
Current Position And Boundary
Research knowledge stays with its owner. MAS can use a team's existing Obsidian or Markdown library alongside Study-specific project files. Without an external library, the workspace holds the canonical notes. Team policies, disease-topic lessons and individual Study decisions remain distinct; each task consumes an exact version, and accepted updates return to the original source. Data, literature and manuscript artifacts retain their project ownership. See the knowledge policy.
Med Auto Scienceis the medical research Foundry Agent for turning disease data, study questions, evidence, and manuscript work into one governed research line.- In the OPL family, MAS is an
OPL Package(kind=agent): MAS retains medical-domain authority, while OPL owns generic runtime and hosted surfaces. Package identity, capabilities, dependencies, research work items, and typed views remain independent of any one carrier or executor. - It can be used as the Research Foundry inside One Person Lab, and it can also be called directly by Codex or another agent through stable capability entries.
- Codex is the current first-class path because it offers the best implementation and maintenance economics. Its Plugin is a carrier projection and its CLI is an executor; neither is MAS package identity or the complete installed package.
- MAS owns the medical work itself: study questions, evidence organization, manuscript direction, manuscript quality, and delivery materials. One Person Lab handles hosted runtime, progress display, recovery/retry, and the cross-agent product entry.
- Manuscript quality is governed by study charters, evidence ledgers, review records, AI reviewer workflow, publication gates, and controller records. Status panels and script checks provide supporting evidence.
- Clinical framing, claim acceptance, and final submission decisions stay with researchers and PIs.
- Journal submission and external system interaction stay under human supervision.
How To Read This Repository
- Potential users and medical experts should start here, then continue to the Docs Guide.
- Technical readers and planners should read Project, Status, Architecture, Invariants, and Decisions.
- Developers and maintainers should continue from the Docs Guide into
docs/active/,docs/runtime/,docs/delivery/,docs/references/, anddocs/policies/.
Installation
Install through the standard OPL Package entry:
opl packages install mas --json
opl packages status --package-id mas --json
The publication channel is ghcr.io/gaofeng21cn/one-person-lab-packages/mas. Immutable versions identify exact releases; latest-stable selects the current version. OPL and the native plugin manager handle installation and updates. Separate GitHub Release pages and attachments are not used for distribution.
Runtime use requires mas-scholar-skills, resolved through the declared Package dependency.
Start a new task after installation to load the professional skills. Package installation, runtime callability, and domain acceptance remain separate; see Current Status.