You did the research. Now you judge it.
AI takes the PI and Trainee roles — designing experiments, running analysis, writing the paper. You become the Editor: the sole decision maker who curates, judges, and steers the science.
Senior. Junior. You. The work unit, reimagined.
A 50-second walkthrough of a full research session
Watch a research session unfold, step by step
Click Start Tutorial to begin
Watch how PI and Trainee collaborate on a research project
Each character is a persona that auto-learns, validates, and certifies its skills
title: Computational Biology PI
expertise: single-cell genomics and ML
goal: discover cell-type-specific
gene regulatory programs
skills:
- scanpy
- pytorch-lightning
- scvi-tools
- scientific-writing
- scientific-visualization
- statistical-analysis
personality:
- "Visionary: identifies novel
biological questions"
- "Rigorous: demands reproducible
pipelines"Give your character a title, expertise, and personality traits. These shape how the AI agent approaches problems and communicates.
Each skill has a SKILL.md + meta.yaml tracking certification status. Skills are auto-learned during the PI-Trainee loop and validated via validation.py. Certified skills show a ✅ badge. Includes scanpy, scientific-writing, pytorch-lightning, and 200+ more.
Drop the YAML into .autolab/profiles/, or use autolab_recruit to automatically assemble a team from the marketplace based on your project needs. Recruited characters come with all certified skills active.
Browse community-created characters or share your own
Set up your own Autonomous Lab in minutes
Add Autonomous Lab to your Cursor MCP settings (~/.cursor/mcp.json):
{
"mcpServers": {
"autonomous-lab": {
"command": "uvx",
"args": ["autonomous-lab"],
"timeout": 600,
"env": {
"MCP_WEB_PORT": "8766"
}
}
}
}Skills are bundled inside characters. Each skill has a SKILL.md + meta.yaml for certification tracking:
# Character folder structure:
autolab-char-compbio-pi/
character.yaml
README.md
skills/
scanpy/
SKILL.md
meta.yaml # certified
scvi-tools/
SKILL.md
meta.yaml # certified
...Use autolab_recruit to auto-assemble a team from the marketplace, or create your own in .autolab/profiles/:
# Auto-recruit based on project:
autolab_recruit
# Finds characters by GitHub
# topics: autolab-skill-*
# Or manually customize:
title: Your Custom PI
skills:
- scanpy
- scientific-writingThe PI-Trainee loop runs, then you act as Editor:
# The research cycle:
autolab_next # PI sets agenda
autolab_next # Trainee executes
autolab_next # PI reviews
... # iterate
# When paper is ready:
autolab_editorial # You decide!
# Invite reviewers, then:
# Accept / Minor / Major / Reject
Give each role its own context window. Add orchestration: multi to
config.yaml and each role spawns a separate CLI agent
(claude, codex, cursor-agent).
Uses the subscriptions you already pay for — no extra API keys needed.
Falls back to single-agent automatically if a CLI isn’t installed.
Run multiple trainees at once — a Data Analyst, a Writer, and a Developer, each with their own focus and context.
In Claude Code, multi-agent auto-upgrades to native teams — trainees self-coordinate, message each other, and share a task list.
orchestration: multi
agents:
pi: { provider: claude-cli }
trainees:
- name: "Analyst"
- name: "Writer"