ordewell
One goal becomes a plan graph you can edit; each task runs on its own agent (Claude Code, Codex, OpenCode, GitHub Copilot CLI and more), in parallel on its own branch with git, and passes only on evidence. Desktop app, terminal UI, VS Code and CLI.
Runs with mockssource: GitHubTypeScriptApache-2.0commit 551f05ac8154
TypeScript, Apache-2.0 licensed. The project labels itself: agent orchestration, agent orchestrator, agentic, agentic coding, ai agents, claude code, cli and codex.
ordewell runs, with stand-ins for the services it depends on. An Argusic agent installed it in 3 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Ordewell 0.14.5 installs and builds from source on Node 22; the core test suite passes 6692/6694 tests (2 pre-existing failures require Docker); the CLI reports version 0.14.5; the offline planner loop with mock provider passes all scenarios; bench data-dir tests pass 6/6; Node 18 is insufficient and must be upgraded to >=20.3 for engine requirements, import.meta.dirname support, and typecheck memory budget.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 92 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page. Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Node.js v18.19.1 bundled, project requires >=20.3 (package.json engines). Caused all workspace engine warnings, broke bench/lib/data-dir.mjs (import.meta.dirname undefined before Node 22), caused tsc --noEmit OOM (heap exhausted at default 4GB), and vitest suite ran against a mismatched runtime.8 minutes
- No Docker engine in container. Two SettingsService tests fail: 'changes from what the file holds, and comes off it whole when the change answers nothing' and 'is read, as written whatever it holds, where ORDEWELL_CONTAINERS=1 is set…'. Both expect docker binary/containers setting to work.
- TypeScript typecheck (npx tsc --noEmit) OOM on Node 18 with default 4GB heap limit at ~86s. Compiled ~2700+ test files.
- Install time
- 3 minutes
- Cold machine to finish
- 74 minutes
- Errors hit and fixed
- 3 hit, 3 fixed with no human help
- How the result was proved
- node packages/cli/dist/main.js --version returned '0.14.5'; npm run build:core exited 0 with DTS output; npm run build exited 0 producing all package artifacts; vitest suite on packages/core (excl e2e) reported 6692 pass / 2 fail; SettingsService container tests run in isolation under Node 22 pass 4/4; bench/live/drive-conversation.mjs with mock-provider.mjs passed all scenarios; bench/lib/data-dir.test.mjs passed 6/6 under Node 22
- Model tokens used
- 298,984
- Exact commit tested
- 551f05ac8154
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
- Behaviour against real services
- this run was verified against stand-in services only
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
=== Timestamps ===
1795342185
=== Node versions ===
v22.23.5
=== vitest pass/fail counts ===
Node 18 run (completed): 6692 passed, 2 failed
=== Offline planner ===
see above output
## ARGUSIC_RESULT: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 3, "err…
tokens used
298,984
## ARGUSIC_RESULT: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 3, "err…Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Installed in 3 minutes, faster than the median of the 21 comparable projects Argusic has measured.
- Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 22 agent-orchestration projects Argusic has installed and timed, ordewell was the 5th fastest to reach a running state, and 15 of 22 reached one at all.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.30 |
Topics (from GitHub)
agent-orchestrationagent-orchestratoragenticagentic-codingai-agentsclaude-codeclicodexcoding-agentsdesktop-appdeveloper-toolsgit-worktreesmulti-agentopen-sourceopencodeorchestrationparallelparallel-agentstask-orchestrationtui
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ordewell)Questions
- Does ordewell run?
- ordewell runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 3 minutes, hitting 3 errors on the way, and recorded the session.
- How did Argusic test ordewell?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 551f05ac8154. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test ordewell?
- The run that produced this verdict cost $0.30: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ordewell take to install?
- 3 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does ordewell need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ordewell?
- 3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does ordewell compare with the alternatives?
- Of the 22 agent-orchestration projects Argusic has installed and timed, ordewell was the 5th fastest to reach a running state, and 15 of 22 reached one at all.
- Where is the evidence for ordewell?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.