From AI answers to finished expert work

One Person Lab App is the lab’s published workbench for serious, long-running knowledge work. It gives users one place to start or continue Codex conversations, bring in project materials when needed, enter professional tasks exposed by installed Agent Packages, follow progress, review evidence, and collect deliverables such as manuscripts, proposals, slide decks, books, reviews, and project files.

The workbench connects native Codex conversations with project materials and specialist Agent Packages. Start a conversation without selecting a project directory, add materials as the work develops, and return to the same files and context across sessions.

The technology is built around two reinforcing advantages.

1. A foundation for high-value knowledge delivery

OPL organizes open-ended expert judgment into visible stages with real artifacts, evidence, review, recovery, and clear human decisions. The shared Framework provides the reliable runtime and delivery model; the App makes that work legible and actionable; each Foundry Agent retains the standards and judgment of its domain.

MAS, MAG, RCA, and OBF apply this foundation to research, grants, visual communication, and long-form publishing. Med Auto Cast (MAC) extends the specialist portfolio into evidence-based medical explainer videos, with its own audiovisual and medical review requirements.

2. A meta-agent and self-evolving agent foundry

OPL Meta Agent (OMA) is the agent that develops agents. It turns a create, takeover, or improvement objective into a reviewable Agent blueprint, evaluation specification, and evidence-bound evolution proposal. The OPL Foundry Kernel then materializes candidates, runs evaluations, versions accepted results, and controls activation or rollback.

This separation of design judgment from controlled evaluation creates a compounding platform: evidence from existing agents can improve the next design, while reusable infrastructure lowers the time and marginal cost of creating each new specialist.

Specialist agents and installable capabilities

The App discovers specialist entry points from the Agent Packages installed on your machine. The lab’s public portfolio spans research, grants, visual communication, books, medical videos, and agent development.

Agent Role What it delivers
OPL Meta Agent (OMA) Meta-agent and Agent Foundry Designs, takes over, diagnoses, and evolves other OPL-compatible agents.
Med Auto Science (MAS) Research agent Evidence organization, analysis, manuscript preparation, review, and auditable study progression.
Med Auto Grant (MAG) Grant agent Grant direction setting, proposal development, simulated review, and revision.
RedCube AI (RCA) Visual-deliverable agent Slide decks, Xiaohongshu visual stories, and knowledge posters, with design, review, revision, and export.
OPL Book Forge (OBF) Book agent Planning, drafting, reviewing, and delivering books and long-form manuscripts.
Med Auto Cast (MAC) Medical video agent Medical evidence, storyboards, narration, animation, audiovisual review, and reusable media assets.

Browse AI Systems & Open Software for the connected platform, domain agents, and shared capabilities. Each project’s repository provides its methods, documentation, and installation options.

Whitepapers

The OPL whitepapers connect the family vision with the Framework foundation, App workbench, Cloud platform, task coordination, and medical-research practice.

Whitepaper Focus Read online
One Person Lab Whitepaper Why complex knowledge work needs expert stages, evidence, review, and recoverable delivery. HTML
OPL Framework Whitepaper How the Cordis Host turns the shared foundation into a composable, inspectable, and evolvable runtime. HTML
OPL App Whitepaper How the local-first workbench turns goals, materials, progress, artifacts, and decisions into one continuous user experience. HTML
OPL Cloud Whitepaper How the OPL work line extends to online workspaces, governed resources, collaboration, and Agent services. HTML
OPL Flow Whitepaper How consistent task intake, automated delivery, and recoverable execution connect goals, agents, and resources across sustained work. HTML (Chinese)
MAS Agent Whitepaper How the OPL model is applied to real medical-research work and publication-oriented delivery. HTML

Install One Person Lab App

Start with the Latest Stable release. For a new Apple Silicon Mac, choose the Full installer when available: it includes bundled runtime and Package files for offline setup. Standard is the smaller download for upgrades and online installation. Both provide the same workbench; connect your chosen model service to begin AI work.

Choose the guide for your environment:

macOS and Linux Desktop include a browser-access mode for working remotely with the same workbench. Docker WebUI is a separately distributed container product with its own installation and update path.

OPL Flow and OPL Fleet

OPL Flow is the Codex experience baseline and durable work-coordination layer. It keeps ownership, recovery, repository integration, and verifiable closeout coherent when work spans multiple tasks, conversations, and repositories.

OPL Fleet extends that coordination across machines. It is an Agent-native distributed execution and continuity system for durable objectives, compatible workspaces, fresh node admission, protected capacity, task dispatch, checkpoints, and owner-safe continuation. It complements Codex, SSH, GitHub runners, HPC, cloud, and container systems rather than replacing their strongest execution primitives.

Flow and Fleet are already used in regular and power-user workflows where one person is coordinating several AI tasks or machines at once. They are not required for basic App use; users can adopt them when the scale and continuity of the work justify the additional control layer.