Local · parallel

Subagents

Split a job. Explore, shell, debug, or computer-use in a focused worker — on this machine.

The parent agent can spawn Task subagents: explore, shell, general-purpose, debug, browser-use (via MCP), computer-use, and custom agents you define. Several can run in parallel. Progress mirrors back into the main transcript.

Why it matters commercially

Long coding jobs stall when one agent juggles search, shell, and writing. Subagents keep a narrow brief so the parent can assemble the result.

What ships today

Local workers inside the desktop app. Nesting and parallel Task calls are real. You stay on the review loop for file changes.

What we do not claim

No remote VM cloud agents, no review bots, no “send this repo to a datacenter worker.” If you need that class of product, we will not pretend it is here.

Browser-use needs an MCP browser server. Computer-use subagents follow the same Windows-first platform limits.

Eyeban · shop/checkout.py Balanced
41 def charge(order, wallet):
42     tax = order.subtotal * 0.09
43     total = order.subtotal + tax
44     if wallet.balance < total:
45         raise InsufficientFunds(total)
46     wallet.debit(total)
47     return Receipt(order.id, total)

Split regional tax from the hardcoded rate, and check coverage before debit.

Read 6 files · 2 searches · 1 test

charge still hard-codes 0.09. tax_for(region) exists. I will wire can_cover to the wallet.

12-line patch across two files. Review the diff.

main Agent Balanced You stay in review