opencode-manager

A self-hosted command center for OpenCode. Sessions, git, terminal, and schedules in one web app, from your phone or desktop.

Runssource: GitHubhomepageTypeScriptMITcommit c06075651dfe

TypeScript, MIT licensed. The project labels itself: agent, ai agents, ai coding, coding agent, developer tools, docker, llm and mobile.

opencode-manager runs. An Argusic agent installed it in 21 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

All 3 packages (backend, frontend, CLI) build and all 5622 tests pass with coverage exceeding 80% thresholds across all categories.

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

verdict
Runs
Argusic Score
96 / 100
cost of the verifying run
$0.35 (measured)
recorded runs
2
last tested
stars
1,107
forks
132
open issues
14
watchers
7
size
39 MB
created
last push

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.

Time lost to each failure while testing opencode-manager, drawn from the recorded run
Every bar is a failure the agent recorded, with the time it cost. Drawn from this run, not from anywhere else.

What went wrong, in the agent's own words

The agent's own words, worst first, never rewritten into advice.

  • Bun runtime not installed on system3 minutes
  • unzip binary not found, causing 8 test failures3 minutes
  • pnpm package manager not installed2 minutes
  • Node.js v18.19.1 too old for Vite 7 (needs 20.19+/22.12+)2 minutes
Install time
21 minutes
Cold machine to finish
22 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
pnpm test:backend passed: 46 bun tests + 3132 vitest tests (88.8% coverage); pnpm test:frontend passed: 2164 tests; pnpm test:cli passed: 279 tests; server started on port 5003, health endpoint returned HTTP 200 with database connected
Model tokens used
152,827
Exact commit tested
c06075651dfe
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.

 Test Files  17 passed (17)
      Tests  279 passed (279)
   Start at  07:51:18
   Duration  7.03s (transform 817ms, setup 0ms, collect 1.64s, tests 8.93s, environment 4ms, prepar…
exec
/bin/sh -lc 'date +%s' in /work/repo
 succeeded in 0ms:
1795074688
All tests pass across every package. Here's the final result:
tokens used
152,827
All tests pass across every package. Here's the final result:

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.
  • Recovered from all 4 errors without a human stepping in, which says the failures are documented well enough to solve.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 21 minutes to install, slower than the median of the 140 comparable projects Argusic has measured.

Of the 141 agent projects Argusic has installed and timed, opencode-manager was the 122nd fastest to reach a running state, and 94 of 141 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.

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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.35
Argusic Runner1/3Runs with mocks92.000.66

Topics (from GitHub)

agentai-agentsai-codingcoding-agentdeveloper-toolsdockerllmmobileopencodepwareactremote-developmentself-hostedterminalweb

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/opencode-manager.svg)](https://argusic.com/subject/opencode-manager)

Questions

Does opencode-manager run?
Yes. opencode-manager runs. Argusic installed and launched it on a clean machine in 21 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test opencode-manager?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit c06075651dfe. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test opencode-manager?
The run that produced this verdict cost $0.35: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does opencode-manager take to install?
21 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 opencode-manager need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing opencode-manager?
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 opencode-manager compare with the alternatives?
Of the 141 agent projects Argusic has installed and timed, opencode-manager was the 122nd fastest to reach a running state, and 94 of 141 reached one at all.
Where is the evidence for opencode-manager?
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.

Discussion