cli-agent-orchestrator
Multi-agent orchestration for AI coding CLIs, Claude Code, Kiro, Codex, and more, coordinated in isolated tmux sessions
Runssource: GitHubhomepagePythonApache-2.0commit dc5efb317974
Python, Apache-2.0 licensed. The project labels itself: agent orchestration, ai agents, ai coding assistant, antigravity, claude code, codex, copilot cli and cursor cli.
cli-agent-orchestrator runs. An Argusic agent installed it in 5 minutes and hit 5 errors on a clean machine with no GPU, and the whole session was recorded.
CAO server starts, responds 200 on /health and /docs, and passes all unit tests (2986+ passed) except for 4 pre-existing test-isolation wiki_lint failures and Node version-gated web UI build.
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 96 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . 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.
- tmux not on PATH2 minutes
- uv not installed1 minute
- ag-ui-protocol missing (optional dep [agui])1 minute
- Node.js 18.19 too old for Vite (needs 20.19+)1 minute
- 4 wiki_lint test failures (test-isolation bugs, not env)1 minute
- Install time
- 5 minutes
- Cold machine to finish
- 43 minutes
- Errors hit and fixed
- 5 hit, 4 fixed with no human help
- How the result was proved
- curl -s http://localhost:19890/health returned 200 with JSON body '{"status":"ok","service":"cli-agent-orchestrator","terminal_backend":"tmux","components":{"cao":"ok","herdr":"unavailable","claude":"unavailable"}}'; server /docs returned 200; 2986+ unit tests passed
- Model tokens used
- 216,325
- Exact commit tested
- dc5efb317974
- 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
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
2. **uv missing** — installed via the astral.sh script 3. **`ag-ui-protocol` not installed** — 15 API tests returned 501; added the `[agui]` optional depe… 4. **Node.js version too old (18.19)** for Vite (needs 20.19+) — web UI bundle cannot be built in t… 5. **4 wiki_lint test failures** — pre-existing test-isolation bugs (pass individually, fail in sui… 6. **Argusic Agent CLI provider tests timeout** — test against a real Argusic Agent binary; the bin… **Verified test counts:** - models + utils: 660 passed - cli + api: 1583 passed, 1 skipped (was 1065+15=1080 after ag-ui-protocol fix ) - clients + backends + mcp_server: 789 passed, 6 skipped - services/agui/: 376 passed - wiki_lint: 62 passed, 4 failed (pre-existing isolation bugs) - kiro_cli_unit: 124 passed
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
- Reached a running state on a clean machine, with the session recorded.
- Installed in 5 minutes.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Hit 5 errors during setup, 1 of which were not solved.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
- A quick evaluation: it was running 5 minutes after the clone.
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 | 2/3 | Runs | 96.00 | 0.17 | |
| Argusic Runner | 1/3 | Ran out of time | 0.00 | 0.54 |
Topics (from GitHub)
agent-orchestrationai-agentsai-coding-assistantantigravityclaude-codecodexcopilot-clicursor-clideveloper-toolshermeskimi-clikiromcpmodel-context-protocolmulti-agent-systemsopencodeorchestrationpythontmux
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/cli-agent-orchestrator)Questions
- Does cli-agent-orchestrator run?
- Yes. cli-agent-orchestrator runs. Argusic installed and launched it on a clean machine in 5 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test cli-agent-orchestrator?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit dc5efb317974. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test cli-agent-orchestrator?
- The run that produced this verdict cost $0.17: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does cli-agent-orchestrator take to install?
- 5 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 cli-agent-orchestrator need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing cli-agent-orchestrator?
- 5 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
- Where is the evidence for cli-agent-orchestrator?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.