Comparison

Ordewell vs Herdr

Checked on , against Herdr's README, documentation and website. Every statement about Herdr links to its source.

Herdr keeps your coding agents running in real terminals and shows which one needs you. Ordewell turns a goal into a plan and hands each task to an agent. They sit at different layers: Herdr is where agents run, and Ordewell is what gives them the work.

Disclosure: the people who build Ordewell wrote this page. Where a difference could not be sourced from Herdr's own pages, it is left out.

What each one is for

Herdr is "the runtime your coding agents live on". It runs Claude Code, Codex, Cursor, OpenCode and others, and "doesn't wrap or replace them; it owns their terminals" (README). "Herdr is a terminal workspace manager. It keeps real terminal processes running and adds structure around them" (concepts).

Ordewell's README puts it this way: "One goal becomes a plan graph you can edit, and each task gets its own agent, model and effort." Independent tasks run in parallel on their own branches, pass only on evidence, then merge (README).

How they differ

On the things Ordewell is built around. Each cell about Herdr links to its source.

OrdewellHerdr
Who plans A planner reads your repository without changing it, asks what is vague and writes tasks with dependencies. It can be a coding agent you are signed in to, or an API provider (README). You, or your agents: they drive Herdr through its CLI and socket API, spawn panes, prompt each other and wait until another agent is blocked (README).
Plan editable before anything runs Yes. Change any prompt, dependency, agent, model, effort or mode, then approve it; the desktop app shows the plan as a list or a graph. Build tasks wait for that approval unless you turn on autorun (README). Work is arranged as workspaces, tabs and panes, each pane a real terminal. "Use one workspace per repo, task, or investigation" (concepts).
Agent and model per task Each task names its own agent, model and effort. Claude Code, Codex, OpenCode, Pi, GitHub Copilot CLI, Qwen Code, Cline, Gemini CLI and Cursor mix in one plan (README). Any agent that runs in a terminal, each in its own pane. Herdr recognises Claude Code, Codex, GitHub Copilot CLI, Cursor, OpenCode, Pi and more (agents).
How a task counts as done The agent reports through task_complete, or a script task exits cleanly. A clean exit with no report is a failure, and no second model decides (README). Herdr marks each agent working, blocked, done or idle, from what it draws on screen or what it reports itself (concepts, agents).
Isolation and merging With git, each task runs on its own branch in its own worktree. You review the diff and merge, or turn on automatic merging. Without git, tasks share your folder (README). Herdr "owns their terminals" (README). The pages linked here do not cover branches or merging.
Surfaces Desktop app, terminal UI, VS Code extension, CLI and a local API, on macOS, Linux and Windows (README). Herdr TUI, "one rust binary" in the terminal you already use (README); a native app on herdr-core for macOS, Linux and Windows; iPhone, iPad and Android apps; other machines over SSH (herdr.dev).
License Apache-2.0 (LICENSE). Apache 2.0, for the app, herdr-core and Herdr TUI (LICENSE, herdr.dev).

When Herdr is the better choice

When Ordewell is

Try Ordewell

Ordewell is open source under Apache-2.0 and runs on macOS, Linux and Windows. Get the desktop app from the download page, or install the terminal app:

bash
# macOS and Linux: a standalone binary, no Node.js
curl -fsSL https://ordewell.ai/install.sh | sh

# Homebrew
brew install ordewell/tap/ordewell

# npm, Node 20.3+: the way to install on Windows
npm install -g ordewell

On Windows the terminal UI runs natively; its mouse and paste need Node 22.17+. git is optional, 2.38+ recommended: with it, tasks run in their own worktrees. You also need a supported coding agent, installed and signed in, or a provider API key. Then run ordewell in your project and type a goal. The docs cover the rest.

Sources

Every page below was read on 21 November 2026.

All comparisons