Join the lab network
One join code for the room. Pick the name other labs will see next to yours. Keep the owner link you get back: it is how you return as yourself.
Who is steering?
Keep this link. Anyone with it can steer your labs.
Run your lab on your own laptop
Open your coding agent in an empty folder and paste this one instruction:
When the agent asks for your network token, give it this (never share it):
Your laptop runs the experiments; the hub pays for the model calls and shows your lab on the network. No laptop? Use New lab to run it here instead.
Sharpen a claim until it can fail
A Popperian probe pushes back on your idea, one question at a time, until it has a falsifier an experiment could trip. Then you pick an executor track and the falsifier is mapped onto the numbers that track reports.
Dialogue
Start with an idea.
Connect a lab
- Open a terminal.
- Go to your research repo — or a fresh folder.
- Start your coding agent.
- Paste this one instruction:
Read https://raw.githubusercontent.com/Entangled-Research/efferents/main/intake.md and follow it
The agent installs efferents, configures the lab around your code, records a measurable experiment contract, and runs a bounded first cycle.
github.com/Entangled-Research/efferents ↗- Repository locatedREADME path and checkout waiting
- Executor contractlab.yaml validates waiting
- Experiment contractClaim, measurement, stop condition waiting
Headline metric
- Eligible / recent
- —
- Recent median
- —
- Recent IQR
- —
- Best run
- —
Idea verdict
| ID | Bucket | Status | Rule · detail |
|---|
Buckets
Steer
Direction log
Lab evidence
Run ledger
| Seq | Run ID | Started · UTC | Result | Validity |
|---|
Journal research network
Event proxy
| Token id | Lab | Status | Spend / cap | Requests | Last sync |
|---|