agents-universe

不是问答机器人,而是能真正干活的数字分身。共享智能体,共享项目上下文,让项目所有成员一起协同工作。同时智能体会像人一样通过资料或者工作抽象和总结经验到项目上下文中

Runs with mockssource: GitHubhomepagePythonApache-2.0commit c73e89e7bff7

Python, Apache-2.0 licensed. The project labels itself: agent, agent framework, agent orchestration, agent skill, agentic ai, ai agents, ai governance and ai tools.

agents-universe runs, with stand-ins for the services it depends on. An Argusic agent installed it in 55 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Backend API runs on port 8002 (SQLite, auth-bypass) with /health 200, project+knowledge APIs working, and a real agent turn streamed an SSE-mocked response end-to-end; 7 agent-core sandbox/shell tests remain red in this container due to missing root for python symlink/user-site and venv path layout.

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

At a glance

verdict
Runs with mocks
Argusic Score
56 / 100
cost of the verifying run
$0.85 (measured)
recorded runs
2
last tested
stars
966
forks
6
open issues
0
watchers
1
size
8 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 agents-universe, 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.

  • agent-core pytest: 7 sandbox/shell tests failed (1642 passed) - sandbox guard sitecustomize user-site channel unavailable in venv (ENABLE_USER_SITE False), no python on PATH (only python3), venv-editable agent_core path not a guard read root25 minutes
  • uvicorn --env-file not honored for settings - server started with default MSSQL URL (libodbc missing, /api/projects/{id}/knowledge 404; /api/projects by slug 404)20 minutes
  • model-config test-connection rejects loopback base_url (SSRF literal-IP block) and mock returns non-SSE to stream10 minutes
Install time
55 minutes
Cold machine to finish
37 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
curl http://127.0.0.1:8002/health returned 200 {"status":"ok"}; /api/projects returned 200 with created project; /api/projects/{uuid}/knowledge returned 200 with 18 knowledge entries; WS turn with SSE mock streamed pong, stream_end, assistant message persisted (message rows verified via SQL). api pytest 657 passed; web vitest 445 passed; agent-core 1642 passed/7 failed.
Model tokens used
4,081,241
Exact commit tested
c73e89e7bff7
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.

except Exception as e:
    print('full_url mode validate: blocked ->', e)
EOF" in /work/repo
 succeeded in 0ms:
base_url mode validate: blocked -> Blocked IP in URL: 127.0.0.1
full_url mode validate: blocked -> Blocked IP in URL: 127.0.0.1
exec
/bin/sh -lc "printf '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\":…
 succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 55, "errors": [{"msg": "ag…
tokens used
4,081,241

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

  • Recovered from all 3 errors without a human stepping in, which says the failures are documented well enough to solve.
  • 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

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.
  • Took 55 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, agents-universe was the 140th fastest to reach a running state, and 94 of 141 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 byattemptoutcomescorecost USDwhen
Argusic Runner2/3Did not run20.000.08
Argusic Runner1/3Runs with mocks92.000.85

Topics (from GitHub)

agentagent-frameworkagent-orchestrationagent-skillagentic-aiai-agentsai-governanceai-toolsdeepseek-harnessharnessharness-engineeringharness-frameworkpythonpython3vue3vuejsweb-applicationwebappworkbuddyworkbuddy-alternative

Embed the badge

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

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

Questions

Does agents-universe run?
agents-universe runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 55 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test agents-universe?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit c73e89e7bff7. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test agents-universe?
The run that produced this verdict cost $0.85: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does agents-universe take to install?
55 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 agents-universe need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing agents-universe?
3 things broke in the recorded run, and 3 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does agents-universe compare with the alternatives?
Of the 141 agent projects Argusic has installed and timed, agents-universe was the 140th fastest to reach a running state, and 94 of 141 reached one at all.
Where is the evidence for agents-universe?
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