Ordewell

Multi-agent task orchestration for coding agents: turn one goal into an editable plan of tasks, run them in parallel on isolated runners, models and branches, and verify the results.

Stars
★ 211
Last updated
today
License
Apache-2.0
Primary language
TypeScript

At a glance

How it runs
CLIIDE extension
Works with
Universal · cross-platformCodex · Claude Code · OpenAI API · Claude API
Cost
Free software; you pay for model usage
Setup effort
Low · running in minutes
You'll need
Node.js 20 or newergittmux (terminal UI)Claude Code, Codex or OpenCodeShell / CLINetwork accessLocal filesystem
Typical use
A solo developer adding a cross-cutting feature (e.g. rate limiting a public API) to a large existing repo who wants to read and change the task plan before anything runs.
Not a fit if
  • Developers without Claude Code, Codex or OpenCode installed
  • Projects not managed with git
  • Windows users unwilling to use WSL for the terminal UI
Website
ordewell.ai ↗ set on GitHub
Maintenance
Commits in the last 30 dayslast commit 2026-11-20latest release v0.14.4 (2026-11-19)
Source review
87/100 · Good

What does this agent do, and when should you use it?

Ordewell is an open-source (Apache-2.0) task orchestration tool for coding agents that turns a single goal into an ordered, editable plan of tasks. Its planner is read-only: it researches your repository, asks about anything you left vague, and returns a dependency graph of tasks, each naming the coding agent, model and thinking effort it will use. At execution time each task starts a fresh agent session inside its own git worktree branch, with independent tasks running three at a time by default. A task counts as done only when a unique completion marker appears in the runner's output, not on a model's opinion of its own work; passing tasks land on an integration branch in plan order, and you decide when to merge. It supports Claude Code, Codex and OpenCode out of the box, freely mixable within one plan, and ships four entry points: a terminal UI, a VS Code extension, a CLI, and a local API.

Ordewell's workflow has five stages. 1) Plan: run ordewell plan --goal "..."; the planner explores your workspace without modifying it, asks clarifying questions, and produces an ordered list of tasks with dependencies. 2) Edit: use commands like ordewell task-runner, task-model and task-deps to change any task's runner, model or dependencies without another round trip to the model. 3) Run: ordewell run starts a fresh coding agent session per task in its own worktree, fed the results of its dependencies; independent tasks run concurrently (three at a time by default). 4) Verify: a task passes only when its unique completion marker appears in the agent's output, with the exit code kept as supporting evidence; passing tasks merge onto an integration branch in plan order, with a chance to self-resolve conflicts before waiting for you. 5) Hand off: ordewell handoff review shows the diff, ordewell handoff merge lands or discards it. Folders containing several repositories are treated as one workspace, with a worktree of every repository per task. Pick planner and runners with /planner and /runners; the planner can be a coding agent you already pay for, or any of 25 API providers.

  1. A solo developer adding a cross-cutting feature (e.g. rate limiting a public API) to a large existing repo who wants to read and change the task plan before anything runs.
  2. Teams using Claude Code, Codex and OpenCode together who want a security refactor on a stronger model and a README update on a cheaper one, mixed in one plan.
  3. Engineers who want independent subtasks executed in parallel without agents interfering with each other, relying on git worktree isolation and ordered merges to an integration branch.
  4. Cautious reviewers who distrust model self-assessment and want completion decided by an evidence marker plus exit code.
  5. Automation-minded users who prefer scripts: the CLI subcommands and local API fit existing pipelines, with the terminal UI for interactive work.

Key setup facts

Pulled from the install and usage notes below. The project README has the current values.

Install / run
  • npm install -g ordewell
Runtime
Node.js 20
Install notes cover
Windows · WSL

How do you install or deploy this agent?

Install the CLI globally:

bash

npm install -g ordewell

For VS Code, install Ordewell from the Marketplace, or run:

bash

code --install-extension ordewell.ordewell

Requirements: Node.js 20 or newer, at least one of Claude Code, Codex or OpenCode, and git for task isolation. The terminal UI also needs tmux; on Windows, run it under WSL. The VS Code extension bundles its own core and needs nothing from npm.

How do you use this agent?

Run ordewell in your project to open the terminal UI and type a goal; on first run pick a planner and runners with /planner and /runners. The same workflow is available from the command line:

bash

export AI_PROVIDER=claude-code      # plan with Claude Code, Codex or OpenCode
ordewell plan --goal "Add rate limiting to the public API"
ordewell run
ordewell handoff review             # read the diff
ordewell handoff merge              # bring it onto your branch

Between plan and run, edit the plan:

bash

ordewell task-runner 2 opencode     # move a task to another agent
ordewell task-model 3 sonnet        # or just change its model
ordewell task-deps 3 1,2            # make it wait for tasks 1 and 2

What are this agent's strengths and limitations?

Pros
  • The plan is fully editable before execution: change any task's prompt, runner, model, effort or mode, add or remove tasks, and rewire dependencies without another model round trip.
  • Per-task model assignment, with every assignment visible before a token is spent.
  • Completion verdicts come from evidence — a unique marker in the runner's output plus the exit code — never a model's opinion of its own work.
  • The planner is read-only and refuses commands that would change your repository; every task runs isolated on its own worktree branch, landing in plan order on one integration branch.
  • No extra API key required: a coding agent you already pay for can act as planner, or any of 25 providers' keys.
Limitations
  • Task isolation depends on git worktrees, so non-git projects cannot use it.
  • Requires an installed, paid coding agent — Claude Code, Codex or OpenCode — to run at all.
  • The terminal UI needs tmux and is not supported natively on Windows; WSL is required.
  • The Ordewell name and logos are excluded from the Apache-2.0 license (see NOTICE), limiting brand reuse.
  • Default concurrency is three, and tasks that fail to self-resolve merge conflicts still require manual intervention.

How does this agent compare with similar options?

Key facts side by side with the most closely related agents.

Agent Source review Form / cost Stars Updated Language Full support on
Ordewell This agent 87 · Good CLIFree + model costs ★ 211 today TypeScript Codex · Claude Code · OpenAI API · Claude API
Plannotator 80 · Good CLIFreemium ★ 14k today TypeScript Codex · Claude Code
Codex Dynamic Workflows (Claude Code skill) 70 · Some gaps — ★ 330 4mo ago JavaScript Codex · Claude Code
MyClaude Multi-Agent Workflow 45 · Major gaps CLIFree + model costs ★ 2.8k 6mo ago Go Codex · Claude Code

How does FollowAgents rate this agent?

FollowAgents source review · FARS-2.1
Good
87/ 100 5-point scale 4.4 / 5
This review covers the source as of Nov 08, 2026. The project has shipped 8 stable release(s) since, which have not been re-reviewed. The score and verdict describe the reviewed version only. Recent releases ↓
Trust 23/29
Reliability 11/14
Adaptability 18/18
Convention 16/18
Effectiveness 12/13
Verifiability 7/8
Why each dimension lost points
Trust23 / 29 · 4.0/5

The README says the planner is read-only by default, submitted build plans wait for approval, and autorun and automatic merging are off by default. SECURITY.md and troubleshooting further describe command classification, sandboxing, credential boundaries, known macOS residual risks, and the version check's data and opt-outs. This supports strong scores for permission controls, confirmation, data-flow transparency, and external effects. Deductions: tasks run as the user in the plan's assigned mode, and may share a workspace without isolation or Git; sandboxing has environment-specific gaps and documented residual risks; the packet is insufficient to fully assess dependency security and recovery behavior. The repository gives a security reporting path, but publisher identity is unverified and does not earn attribution credit.

Reliability11 / 14 · 3.9/5

The README, AGENTS.md, and CI configuration describe planning, task dependencies, verification, version requirements, build order, test layers, and CI scope. Troubleshooting provides concrete checks and explanations for sandbox, Git-version, and platform failures. Deductions: the packet does not expose enough implementation or dependency evidence to verify every behavior, and static review cannot establish that the mechanisms work correctly in execution.

Adaptability18 / 18 · 5.0/5

The documentation covers research, coding, operations, and consented script tasks; per-task runner, model, and mode selection; and terminal, VS Code, CLI, and local API interfaces. Sample skills define boundaries for diagnosing failures, exploring open questions, and design review. Installation notes address Linux, macOS, Windows, Homebrew, npm, and editor environments. Full marks reflect the breadth and specificity of the scenarios, boundaries, triggers, and environments shown by this static evidence.

Convention16 / 18 · 4.4/5

The README organizes features, installation, quick start, workflow, and security information, with separate troubleshooting, contribution, security, architecture, and agent-instruction materials. It identifies the license, pre-1.0 compatibility expectations, changelog, supported-version policy, and concrete limitations. Deductions: repository naming and a listed author do not establish verified publisher or maintainer identity; release and maintenance paths are described, but the responsible publisher remains unverified.

Effectiveness12 / 13 · 4.6/5

The product turns a goal into dependency-ordered tasks with selectable runners and modes, supports parallel execution, and provides diff review, verification, and optional merging. The README describes approval defaults, and the sample skills give structured task workflows. Deduction: coordinating multiple runners adds installation, configuration, and orchestration costs, and the supplied static material does not quantify the resulting everyday benefit or overhead.

Verifiability7 / 8 · 4.4/5

Major workflow and security claims in the README are traceable to SECURITY.md, troubleshooting, CI configuration, and source entry points. AGENTS.md lists verification commands, while CI describes automated checks; the documentation distinguishes defaults, platform conditions, and known limitations. Deductions: the packet is a sample and omits implementations and tests needed for full cross-source corroboration; references to tests are not evidence that they were executed for this review.

Risks and how to mitigate them
  • Tasks run as the user. Review each task's runner, mode, and scope before approving a plan, then inspect changes before merging.
  • Tasks may share a workspace when isolation is unavailable or disabled; Codex or planner sandboxing may also be unavailable on some hosts. Read SECURITY.md and troubleshooting first, including the documented macOS residual risks.
  • Publisher identity is unverified. This assessment uses the supplied static sample and did not execute code or independently verify claims.
Evidence confidence: Low Reviewed Nov 08, 2026 Reviewed revision 061fce8fe651 New commits since this review; the score may not cover them
See the full review method →
Maintain this project? Add the FARS badge to your README

The badge shows the current review score and verdict and links back to this page. It refreshes about once an hour after a re-review.

FARS

[![FARS review](https://followagents.com/badge/ordewell.svg)](https://followagents.com/en/agents/ordewell)
<a href="https://followagents.com/en/agents/ordewell"><img src="https://followagents.com/badge/ordewell.svg" alt="FARS review"></a>

Recent releases

Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.

  1. v0.14.4
    Release notes excerpt
    v0.14.4 — Ordewell Desktop Ordewell Desktop: your planner, editable plan graph, files, diffs, git and terminal in one window for macOS, Windows and Linux. 0.14.4 tells a running change where a sibling's work lands and how to take it in, reads which tasks open, fan out and close a wide one-shot plan, and narrows a task that failed part-way before retrying it; OpenRouter calls prefer the upstream that served the last one, and the built-in runner continues a turn whose reply writes its tool call as text. | Platform | Installer | | --- | --- | …
    View on GitHub ↗
  2. v0.14.3
    Release notes excerpt
    v0.14.3 — Ordewell Desktop Ordewell Desktop: your planner, editable plan graph, files, diffs, git and terminal in one window for macOS, Windows and Linux. 0.14.3 reviews a plan whose dependencies run in one long chain once by its planner, keeps a copy of a plan saved by an earlier version from removing its original's worktrees, and reads a saved session without opening every other session. | Platform | Installer | | --- | --- | | macOS · Apple silicon | [Download DMG](https://github.com/ordewell/ordewell/releases/download/v0.14.3/Ordewell-0.14.3-mac-arm64.dmg) | …
    View on GitHub ↗
  3. v0.14.2
    Release notes excerpt
    v0.14.2 — Ordewell Desktop Ordewell Desktop: your planner, editable plan graph, files, diffs, git and terminal in one window for macOS, Windows and Linux. 0.14.2 keeps long sessions responsive, lets a retry carry a note for the new attempt, and fixes a supervisor that was not woken again for a failure it left standing, a session that could remove another session's worktrees, and an empty chat after a stream gap. | Platform | Installer | | --- | --- | | macOS · Apple silicon | [Download DMG](https://github.com/ordewell/ordewell/releases/download/v0.14.2/Ordewell-0.14.2-mac-arm64.dmg) | …
    View on GitHub ↗

FAQ

Do I pay for Ordewell itself?
No. Ordewell is Apache-2.0 licensed and free; you pay for the coding agents (Claude Code, Codex, OpenCode) or planner API keys you run it with.
Which coding agents does it support?
Claude Code, Codex and OpenCode are supported out of the box and can be mixed freely within one plan.
How does it decide a task is done?
Only when the task's unique completion marker appears in the agent's output, with the exit code kept as supporting evidence — never a model's self-assessment.
What happens on failure or merge conflicts?
Passing tasks merge onto the integration branch in plan order. On conflict the task gets a chance to resolve it; if that fails it waits for you with the conflicting files named.
Does it work on Windows?
The CLI does, but the terminal UI requires tmux and must run under WSL; the VS Code extension, which bundles its own core, is an alternative.
Is Ordewell open source?
Yes. The source code is on GitHub (ordewell/ordewell) under the Apache-2.0 licence.
Is Ordewell safe to use?
FollowAgents' FARS review (Nov 08, 2026) scored Ordewell 23/29 on trust and safety. None of the eight safety controls the review checks for was missing outright. The repository has changed since that review.
Is Ordewell still maintained?
Yes. The latest commit on GitHub is from 2026-11-20, within the last 30 days. The latest release is v0.14.4 (2026-11-19).
Who makes Ordewell?
Ordewell is published on GitHub by the account ordewell. FollowAgents has not verified which person or company is behind that account.
What is Ordewell's official website?
The project's GitHub repository lists https://ordewell.ai as its website. That link is set by the repository owner; the source code itself is on GitHub (ordewell/ordewell).
Was this page helpful?
View on GitHub ↗ Install ↓

Host ecosystems

Compare agents like this one

The same FARS review applied across the shortlist this agent qualifies for.

Related concepts