waku-agent

Waku Waku! Waku Agent is a local-first AI agent harness you actually own, including loop, memory, eval, all in code built to stay legible as it grows.

Runssource: GitHubPythonMITcommit 12bf00efb11f

Python, MIT licensed. The project labels itself: agent framework, ai agent, ai assistant, claude, evals, llm, llmops and local first.

waku-agent runs. An Argusic agent installed it in 18 minutes and hit 2 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Waku is fully installed at /work/repo/.venv. The dashboard serves HTTP 200 on localhost:7777. All 1714 deterministic evals pass offline. Ruff lint passes. The CLI (waku --help, waku connections, interactive waku) works 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
$0.05 (measured)
recorded runs
2
last tested
stars
2,205
forks
437
open issues
84
watchers
6
size
13 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 waku-agent, 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.

  • ModuleNotFoundError: No module named 'aiohttp' in hosted gatewaylib.py (import aiohttp)0.5 minutes
  • ModuleNotFoundError: No module named 'cryptography' in hosted gatewaylib.py (from cryptography.hazmat...)0.5 minutes
Install time
18 minutes
Cold machine to finish
6 minutes
Errors hit and fixed
2 hit, 2 fixed with no human help
How the result was proved
.venv/bin/pytest evals/deterministic/ -q --tb=line 2>&1 | tail -1 returned '1714 passed, 63 skipped in 80.00s'; curl -s -o /dev/null -w '%{http_code}' http://localhost:7777/ returned 200; .venv/bin/waku --help printed 15 entrypoints; .venv/bin/waku connections printed configured integrations; .venv/bin/ruff check waku/ evals/ scripts/ hosted/ returned 'All checks passed'
Model tokens used
32,051
Exact commit tested
12bf00efb11f
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 2, run , the attempt that decided the verdict above. 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.

exec
/bin/sh -lc 'cd /work/repo && echo "--- Full deterministic test summary ---" && .venv/bin/pytest ev…
 succeeded in 81196ms:
--- Full deterministic test summary ---
........................................................................ [ 89%]
........................................................................ [ 93%]
....................................................sssssssssss......... [ 97%]
................................................                         [100%]
1714 passed, 63 skipped in 80.00s (0:01:20)
2026-11-12T01:26:27.563899Z ERROR codex_core::session: failed to record rollout items: thread 01a1c…
tokens used
32,051

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 2 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 18 minutes to install, slower than the median of the 62 comparable projects Argusic has measured.

Of the 63 agent-framework projects Argusic has installed and timed, waku-agent was the 56th fastest to reach a running state, and 50 of 63 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 Runner2/3Runs100.000.05
Argusic Runner1/3Runs100.000.08

Topics (from GitHub)

agent-frameworkai-agentai-assistantclaudeevalsllmllmopslocal-firstopenaipersonal-assistantpythonsqlite

Embed the badge

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

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

Questions

Does waku-agent run?
Yes. waku-agent runs. Argusic installed and launched it on a clean machine in 18 minutes, hitting 2 errors on the way, and recorded the session.
How did Argusic test waku-agent?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 12bf00efb11f. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test waku-agent?
The run that produced this verdict cost $0.05: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does waku-agent take to install?
18 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 waku-agent need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing waku-agent?
2 things broke in the recorded run, and 2 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does waku-agent compare with the alternatives?
Of the 63 agent-framework projects Argusic has installed and timed, waku-agent was the 56th fastest to reach a running state, and 50 of 63 reached one at all.
Where is the evidence for waku-agent?
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