GenericAgent

Self-evolving agent: grows skill tree from 3.3K-line seed, achieving full system control with 6x less token consumption

Runs with mockssource: GitHubhomepagePythonMITcommit e86ca723a943

Python, MIT licensed. The project labels itself: ai agent, automation, autonomous agent, browser automation, claude, computer control, desktop automation and gemini.

GenericAgent runs, with stand-ins for the services it depends on. An Argusic agent installed it in 1 minute and hit 6 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

After a venv install of the declared UI and test dependencies, 275 tests pass, the TUI starts, the Streamlit UI completes a mocked tool-using turn with MOCK_FINAL: 246810, and launch.pyw opens a live 1200x900 GenericAgent window on DISPLAY=:99 using PyQt6 and an extracted libxcb-cursor.

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

verdict
Runs with mocks
Argusic Score
92 / 100
cost of the verifying run
$0.36 (measured)
recorded runs
2
last tested
stars
14,428
forks
1,672
open issues
210
watchers
40
size
46 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 GenericAgent, 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.

  • Automated PTY input could not trigger the TUI submit handler because the harness escaped control characters, so it made no model request5 minutes
  • The Qt xcb platform plugin failed because libxcb-cursor.so.0 was missing4 minutes
  • frontends/tui_v3.py exited 1 when stdin was not a TTY3 minutes
  • launch.pyw failed because pywebview found neither GTK Python bindings nor Qt bindings2 minutes
  • README's uv-based install could not run because uv is not installed in the container1 minute
  • /usr/bin/time is unavailable, so the first timed install command failed before running
Install time
1 minutes
Cold machine to finish
29 minutes
Errors hit and fixed
6 hit, 6 fixed with no human help
How the result was proved
.venv/bin/python -m pytest -q frontends/tests exited 0 with 275 passed in 1.89s; Streamlit AppTest submitted a chat message and displayed MOCK_FINAL: 246810 after two mock POST /v1/chat/completions requests returned 200; curl http://127.0.0.1:8506/_stcore/health returned 200 and xwininfo listed a 1200x900 GenericAgent window; .venv/bin/ga --version printed GenericAgent v0.1.0.
Model tokens used
1,494,551
Exact commit tested
e86ca723a943
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.

5713 /usr/bin/bash -c printf 'Remaining processes:\n'; pgrep -af 'agentmain|ga_mock_openai|streamli…
Window check:
none
Final git status:
Final tests:
........................................................................ [ 26%]
........................................................................ [ 52%]
........................................................................ [ 78%]
...........................................................              [100%]
275 passed in 1.89s
tokens used
1,494,551

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 1 minute, faster than the median of the 78 comparable projects Argusic has measured.
  • Recovered from all 6 errors without a human stepping in, which says the failures are documented well enough to solve.
  • 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

  • Only reached a running state against stand-in services, so nothing here proves it works against the real ones.

Of the 79 ai-agent projects Argusic has installed and timed, GenericAgent was the 16th fastest to reach a running state, and 54 of 79 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 Runner2/3Runs with mocks92.000.36
Argusic Runner1/3Runs with mocks92.000.02

Topics (from GitHub)

ai-agentautomationautonomous-agentbrowser-automationclaudecomputer-controldesktop-automationgeminilightweightllm-agentmemory-systempythonself-evolvingskill-treetask-automation

Embed the badge

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

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

Questions

Does GenericAgent run?
GenericAgent runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 1 minutes, hitting 6 errors on the way, and recorded the session.
How did Argusic test GenericAgent?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit e86ca723a943. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test GenericAgent?
The run that produced this verdict cost $0.36: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does GenericAgent 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 GenericAgent need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing GenericAgent?
6 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does GenericAgent compare with the alternatives?
Of the 79 ai-agent projects Argusic has installed and timed, GenericAgent was the 16th fastest to reach a running state, and 54 of 79 reached one at all.
Where is the evidence for GenericAgent?
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