OpenVLHarness

Official Code for OpenVLHarness: Real-World Visual Agentic Tool‑Use with Multimodal Memory

Runssource: GitHubhomepagePythonMITcommit c080224d3177

Python, MIT licensed. The project labels itself: agent harness, agent skills, agentic ai, ai agents, coding agent, deep research, efficiency and grounded reasoning.

OpenVLHarness runs. An Argusic agent installed it in 1 minute and hit no errors on a clean machine with no GPU, and the whole session was recorded.

Package openvlharness 0.1.0 installed in a Python 3.12 venv with all extras; all 503 tests pass (0 failures, 0 skips); the tool router FastAPI app creates and serves /health (200 OK) and /tools endpoints; the openvlharness-eval CLI entrypoint prints help text correctly.

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

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
1
last tested
stars
520
forks
41
open issues
2
watchers
12
size
22 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.

Install time
1 minutes
Cold machine to finish
5 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
pip install -e '.[test,server,eval]' succeeded; pytest tests/ --tb=short -q: 503 passed, 449 subtests passed; python -m openvlharness.services.server --config examples/local_tools.yaml started and curl returned 200 on /health and listed 2 tools on /tools; openvlharness-eval --help printed usage; all core imports (bootstrap, server, memory) succeeded
Model tokens used
45,854
Exact commit tested
c080224d3177
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.

-- Docs: https://docs.pytest.org/en/stable/how-to/capture-warnings.html
503 passed, 3 warnings, 449 subtests passed in 24.81s
exec
/bin/sh -lc '# One more check - verify no tests were skipped
cd /work/repo && /tmp/venv/bin/python -m pytest tests/ --tb=short -q 2>&1 | grep -E "passed|failed|…
 succeeded in 25849ms:
503 passed, 3 warnings, 449 subtests passed in 24.69s
Everything is clean and fully working. Let me provide the final report.
2026-11-14T07:21:13.893267Z ERROR codex_core::session: failed to record rollout items: thread 01a1d…
tokens used
45,854
Everything is clean and fully working. Let me provide the final report.

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 1 minute, faster than the median of the 10 comparable projects Argusic has measured.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.

What did not, or is not known

  • Measured once so far. A single attempt shows it can run, not that it runs reliably.

Of the 11 agent-harness projects Argusic has installed and timed, OpenVLHarness was the 1st fastest to reach a running state, and 8 of 11 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 1 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

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 Runner1/3Runs100.000.03

Topics (from GitHub)

agent-harnessagent-skillsagentic-aiai-agentscoding-agentdeep-researchefficiencygrounded-reasoningharness-engineeringharness-optimizationllmllm-agentsmllmmultimodalmultimodal-searchmultimodal-toolsperceptionrsispatial-reasoningtool-use

Embed the badge

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

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

Questions

Does OpenVLHarness run?
Yes. OpenVLHarness runs. Argusic installed and launched it on a clean machine in 1 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test OpenVLHarness?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit c080224d3177. One attempt is recorded, and the full method is on the methodology page.
What did it cost to test OpenVLHarness?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does OpenVLHarness take to install?
1 minute in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does OpenVLHarness need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing OpenVLHarness?
Nothing did, in the recorded run: zero errors between clone and running.
How does OpenVLHarness compare with the alternatives?
Of the 11 agent-harness projects Argusic has installed and timed, OpenVLHarness was the 1st fastest to reach a running state, and 8 of 11 reached one at all.
Where is the evidence for OpenVLHarness?
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.

Discussion