12vectors
/
bench
docs for $version
Documentation
Put the agents
on the bench.
Task files in stage directories are the only source of
truth. A stdlib-only board narrates what happens to them — agents
working in git worktrees, PRs opening on review, CI on the cards —
and never merges anything itself.
no account, no service, no database. it is
python 3 on your own machine.
~/your-repo
first run · abridged
$install_block
No .task-manager/manager/local/.env yet — a few questions and bench writes one.
Enter takes the default in [brackets]; Ctrl-D skips the rest.
solo or team? [solo]:
which agent adapter? [claude]:
what command runs this project's tests? [python3 -m unittest]:
Wrote .task-manager/manager/local/.env — every other setting is in there, commented; edit it any time.
…
Task board for ~/your-repo/.task-manager/tasks
http://127.0.0.1:26071/
Ctrl-C to stop
01
Install and first run
Untar it into .task-manager/,
run start.sh, answer three questions.
Port 26071, pinned.
02
The five stages
backlog → to-do → in-progress → review → done.
The directory a file sits in is its status.
03
Agents on the board
▸ start work makes a worktree and a branch, runs
the agent headless, and moves the card when it exits.
04
PRs & review
A card entering review gets a PR opened for it.
Then ◔ review PR, ⚑ copilot, ↻ act on PR — until it settles.
05
Team mode
BOARD_SYNC=1 makes
origin/main the truth. Moves commit and push themselves; boards pull
on a beat.
06
The three-layer law
Core knows tasks, worktrees, PRs and events.
Drivers know apps, adapters know vendors, local/ knows your
project.
Version
$version
read from manager/core/VERSION
when this page was built. update.sh replaces an
install with the latest release; BENCH_REF=v2
pins an exact one.
Releases ↗