Ordewell for the terminal · TUI and CLI

The same plan, in your terminal. Over SSH, too.

Conversation on the left, live plan on the right. Single keys drive the plan: no menus, no mouse. One binary, and no API key if you already have a coding agent.

macOS, Linux and Windows · uses the coding agents you already have, signed in · git optional

Ordewell's terminal UI: the conversation on the left lists the planner's reads and a question about reusing a shared Redis client, and the plan on the right lists seven tasks, six with their runner and model and their effort where the model offers one, and one manual rollout task; two are done and one is running. The footer reads Planner ctx 38k (19%), Claude 5h 23% used, Weekly 41% used, and the status bar reads Guarded · supervisor Watch.
The planner conversation and the live plan, side by side.

Get started

One line, then one goal.

Install

macOS and Linux · one binary
curl -fsSL https://ordewell.ai/install.sh | sh
Homebrew
brew install ordewell/tap/ordewell
npm · Windows, or anywhere with Node.js
npm install -g ordewell

The binary needs no Node.js. The npm package needs Node.js 20.3 or newer; mouse and paste on Windows need 22.17.

First run

  1. Open a project directory in a terminal.
  2. Run ordewell. The opening screen names the planner and the runners it found.
  3. Type a goal, then approve the plan, or let autorun start it.

An installed coding agent plans by default, with no API key. Change it in place with /planner and /runners.

Keys

Single keys drive the plan.

Select a task and change it where it stands: its runner, its model, how it runs. Then start one task, or the whole plan.

  • tab swap chat and plan
  • f start selected task
  • E run the whole plan
  • R change runner
  • o change model
  • M execution mode

Watch

A real run, start to finish.

A real run on a small Express API, 48 seconds, sped up where marked. Recorded with Ordewell 0.6, so its panes look older than the still above.

CLI

For a pipeline instead of a person.

The same plan from a script: plan a goal, change a task, run it, and read the diff before it merges.

bash
# plan on an agent you already have, no API key
export AI_PROVIDER="claude-code"        # or codex, opencode and five more

ordewell plan --goal "Add rate limiting to the public API"
ordewell task-model 3 sonnet            # change a task before it runs
ordewell run
ordewell handoff review                 # read the diff first
ordewell handoff merge                  # then bring it onto your branch

Go further

Set the goal. Let the graph run.

Step in whenever you want, or not at all.

Free and open source. You need one coding agent, installed and signed in: Claude Code, Codex or one of the others.