Cotal
The open standard for agent coordination
Runssource: GitHubhomepageTypeScriptApache-2.0commit 1793d6c635a8
TypeScript, Apache-2.0 licensed. The project labels itself: a2a, agent communication, agent mesh, agent orchestration, agent skills, ai, ai agents and claude code.
Cotal runs. An Argusic agent installed it in 10 minutes and hit 2 errors on a clean machine with no GPU, and the whole session was recorded.
Cotal 0.100.2 installed, pnpm build succeeded across 29 packages, and the local mesh runs with broker (nats-server v2.14.0), delivery daemon, and manager all in 'running' state on static auth, verified by 27 passing smoke suites covering multicast/unicast/anycast delivery, DM durability, presence, auth, the cotal-lang workflow language (grammar, keys, journal), runtime driver, mesh wait/checkpoint/sleep, web dashboar...
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 90 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.
- cotal up preflight refused due to group-writable /home/runner/.local directory (mode 0775) — the nats-server binary path was not protected against other local writers1 minute
- CI gate-inventory smoke failed with 15 ungated exemptions past their recheckBy date 2026-10-24 — a process/maintenance issue, not a code defect
- Install time
- 10 minutes
- Cold machine to finish
- 10 minutes
- Errors hit and fixed
- 2 hit, 1 fixed with no human help
- How the result was proved
- cotal status confirmed broker/delivery/manager running on nats://127.0.0.1:4222; pnpm smoke: 25/25 passed; pnpm smoke:auth: 12/12 passed; pnpm smoke:lang-grammar: 129/129 passed; pnpm smoke:lang-journal: 114/114 passed; pnpm smoke:turn-relay-auth: 13/13 passed; pnpm smoke:runtime-run-driver: 87/87 passed; pnpm smoke:runtime-mesh-wait: 62/62 passed; 27 smoke suites verified in total, all passing
- Model tokens used
- 263,919
- Exact commit tested
- 1793d6c635a8
- 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.
--- Mesh health --- Mesh: main → main ● reachable static auth · local registration Broker: nats://127.0.0.1:4222 Connection: ● reachable stack-broker 16af6404-9a79-4d06-b9a2-ca3000978efd 5102e4fbd322 ● running broker… stack-manager 2a8ca7a8-da79-4f5d-86bc-a208a545d78e 5102e4fbd322 ● running endpoi… stack-delivery 2b15af65-a1fd-4deb-88d1-8c417539eb1f 5102e4fbd322 ● running adapte… All smokes passed, the mesh is running with all three services healthy. Here's the final tally: tokens used 263,919 All smokes passed, the mesh is running with all three services healthy. Here's the final tally:
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.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
What did not, or is not known
- Took 10 minutes to install, slower than the median of the 8 comparable projects Argusic has measured.
- Hit 2 errors during setup, 1 of which were not solved.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 9 a2a projects Argusic has installed and timed, Cotal was the 6th fastest to reach a running state, and 8 of 9 reached one at all.
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 10 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
Topics (from GitHub)
a2aagent-communicationagent-meshagent-orchestrationagent-skillsaiai-agentsclaude-codedistributed-systemsinfrastructurejetstreammcpmodel-context-protocolmulti-agentnatsprotocolpubsubself-hostedswarmtypescript
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/cotal)Questions
- Does Cotal run?
- Yes. Cotal runs. Argusic installed and launched it on a clean machine in 10 minutes, hitting 2 errors on the way, and recorded the session.
- How did Argusic test Cotal?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 1793d6c635a8. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test Cotal?
- The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does Cotal take to install?
- 10 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 Cotal need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing Cotal?
- 2 things broke in the recorded run, and 1 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does Cotal compare with the alternatives?
- Of the 9 a2a projects Argusic has installed and timed, Cotal was the 6th fastest to reach a running state, and 8 of 9 reached one at all.
- Where is the evidence for Cotal?
- 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.