hive

Multi-Agent Harness for Production AI

Runssource: GitHubPythonApache-2.0commit 6193aea7eb06

Python, Apache-2.0 licensed. The project labels itself: agent, agent framework, agent skills, anthropic, automation, autonomous agents, claude and harness.

hive runs. An Argusic agent installed it in 17 minutes and hit 8 errors on a clean machine with no GPU, and the whole session was recorded.

With the fixes, ./quickstart.sh completes and launches the Hive dashboard on an available local port; /api/health returned 200, Chromium rendered the Hive landing UI without page errors, and make test exited 0 with 2496 core and 4381 tools tests passed.

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 93.8 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
93.8 / 100
cost of the verifying run
$0.29 (measured)
recorded runs
2
last tested
stars
11,162
forks
5,630
open issues
1,101
watchers
231
size
63 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 hive, 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.

  • Playwright was falsely reported as ready because 'playwright install --dry-run' exits 0 without browsers; three chart tests failed with 'Executable doesn't exist'.5 minutes
  • The installer's dashboard launch crashed with OSError: [Errno 98] address already in use on 127.0.0.1:8787.2 minutes
  • The core suite had one failure while a live Hive server held the maintenance lock; the janitor test rejected the active runtime.2 minutes
  • docs/getting-started.md referenced the nonexistent core/examples/manual_agent.py.2 minutes
  • quickstart.sh exited 1 immediately under TERM=dumb because clear returned nonzero and set -e aborted.1 minute
  • 'uv run python' returned 127 in the current non-login shell because ~/.local/bin was not on PATH.1 minute
Install time
17 minutes
Cold machine to finish
21 minutes
Errors hit and fixed
8 hit, 7 fixed with no human help
How the result was proved
./quickstart.sh reached 'ADEN HIVE - READY' and launched http://127.0.0.1:8788; curl -sS -o /dev/null -w '%{http_code}' http://127.0.0.1:8788/api/health returned 200; Playwright loaded the dashboard with HTTP 200, title 'Hive', and no page errors; make test exited 0 (core: 2496 passed, 19 skipped; tools: 4381 passed, 230 skipped); frontend npm test: 19 files passed, 172 tests passed, 7 skipped.
Model tokens used
320,798
Exact commit tested
6193aea7eb06
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

Watch the session

The whole run, from a clean machine, at the speed it actually happened. Nothing is cut and nothing is sped up.

A recording of attempt 1, run . The verdict above comes from a different attempt, so read this as one session and not as the current result. The terminal recording it was made from is the evidence, stored with a sha256 fingerprint; the video is a rendering of it. Nothing loads from the video host until you press play.

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

 M docs/getting-started.md
 M hive
 M quickstart.sh
--- final check ---
diff_check_exit=0
--- final diff stat ---
 docs/getting-started.md | 15 +++++++--------
 hive                    | 34 ++++++++++++++++++++++++++++++++++
 quickstart.sh           | 29 ++++++++++++++++++++++-------
 3 files changed, 63 insertions(+), 15 deletions(-)
tokens used
320,798

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.
  • Measured 2 times, so the result is not a one-off.

What did not, or is not known

  • Took 17 minutes to install, slower than the median of the 137 comparable projects Argusic has measured.
  • Hit 8 errors during setup, 1 of which were not solved.

Of the 138 agent projects Argusic has installed and timed, hive was the 113th fastest to reach a running state, and 92 of 138 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 Runner2/3Runs97.500.29
Argusic Runner1/3Runs90.000.07

Topics (from GitHub)

agentagent-frameworkagent-skillsanthropicautomationautonomous-agentsclaudeharnessharness-engineeringhuman-in-the-loopopenaipythonself-hostedself-improving

Embed the badge

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

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

Questions

Does hive run?
Yes. hive runs. Argusic installed and launched it on a clean machine in 17 minutes, hitting 8 errors on the way, and recorded the session.
How did Argusic test hive?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 6193aea7eb06. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test hive?
The run that produced this verdict cost $0.29: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does hive take to install?
17 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 hive need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing hive?
8 things broke in the recorded run, and 7 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does hive compare with the alternatives?
Of the 138 agent projects Argusic has installed and timed, hive was the 113th fastest to reach a running state, and 92 of 138 reached one at all.
Where is the evidence for hive?
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