opentag
Mention any ACP coding agent from Slack, GitHub, GitLab, Linear, or Lark. OpenTag runs Claude Code, Codex, Cursor and more on your own machine, then replies in-thread with verified, evidence-backed results.
Runs with mockssource: GitHubTypeScriptMITcommit 3a3136dcb839
TypeScript, MIT licensed. The project labels itself: acp, agent client protocol, ai agents, claude code, codex, coding agents, developer tools and github.
opentag runs, with stand-ins for the services it depends on. An Argusic agent installed it in 10 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
The repository installs, typechecks, lints, and builds cleanly; the full vitest suite passes (1502 passed) against a user-space PostgreSQL 17.10; the credential-free paired-relay contract smoke passes (113 tests); and the built CLI answers --version 0.11.0 and --help.
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, 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.
- PostgreSQL 18 readiness incompatibility: PG18 catalogs NOT NULL constraints in pg_constraint, so control_plane_migrations has 4 constraints while the strict readiness query expects exactly 1 (migrations_pending)6 minutes
- 6 SQLite-backed tests exceeded the default 5000ms non-CI vitest timeout on this slow container3 minutes
- System Node.js v18.19.1 is below the required >=22.14.02 minutes
- corepack pnpm build failed: 'pnpm: not found' when the control-plane workspace spawned a nested pnpm1 minute
- Install time
- 10 minutes
- Cold machine to finish
- 27 minutes
- Errors hit and fixed
- 4 hit, 4 fixed with no human help
- How the result was proved
- vitest run --testTimeout=60000 with OPENTAG_TEST_DATABASE_URL=postgresql://runner@localhost:15432/runner exited 0 (147 files, 1502 passed, 2 skipped); smoke:live --case paired-relay exited 0 (8 files, 113 passed); node packages/cli/dist/index.js --version returned 0.11.0
- Model tokens used
- 219,650
- Exact commit tested
- 3a3136dcb839
- 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.
- PostgreSQL 18 (from an embedded binary) broke a strict schema-readiness check: PG18 now catalogs … - Docker is absent and no root exists, so the Compose Control Plane and real Slack/GitHub/ACP deliv… **Verifications observed (all exit 0):** - `corepack pnpm install --frozen-lockfile` → Done in ~15s, no error. - `corepack pnpm typecheck` → exit 0. - `corepack pnpm lint` → all packages "Done". - `corepack pnpm build` → exit 0 (all packages; control-plane server + vite console built). - Full `vitest run` against PG17.10 → **147 files / 1502 passed / 2 skipped**. - `smoke:live -- --case paired-relay` → **PASSED: 8 files / 113 tests** (Slack/GitHub credentials e… - `node packages/cli/dist/index.js --version` → **0.11.0**; `--help` prints usage. The repo's tracked files are unchanged (`git status` clean). `test_depth` is **tier2_mock**: I stood up a real PostgreSQL 17 and ran the credential-free Control…
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 10 minutes, faster than the median of the 3 comparable projects Argusic has measured.
- Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, 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 4 acp projects Argusic has installed and timed, opentag was the 2nd fastest to reach a running state, and 1 of 4 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 | 0.14 |
Topics (from GitHub)
acpagent-client-protocolai-agentsclaude-codecodexcoding-agentsdeveloper-toolsgithublocal-firstslack
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/opentag)Questions
- Does opentag run?
- opentag runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 10 minutes, hitting 4 errors on the way, and recorded the session.
- How did Argusic test opentag?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 3a3136dcb839. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test opentag?
- The run that produced this verdict cost $0.14: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does opentag 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 opentag need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing opentag?
- 4 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.
- How does opentag compare with the alternatives?
- Of the 4 acp projects Argusic has installed and timed, opentag was the 2nd fastest to reach a running state, and 1 of 4 reached one at all.
- Where is the evidence for opentag?
- 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.