sleepless-agent

🤖 24/7 AI agent that maximizes Claude Code Pro usage via Slack. Auto-processes tasks, manages isolated workspaces, creates Git commits/PRs, and optimizes day/night usage thresholds.

Runs with mockssource: GitHubhomepagePythonMITcommit dbeb1c28699b

Python, MIT licensed. The project labels itself: ai agent, anthropic, automation, autonomous agents, claude, claude code, daemon and git automation.

sleepless-agent runs, with stand-ins for the services it depends on. An Argusic agent installed it in 51 minutes and hit 3 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Installed and built cleanly in venv; all CLI commands (think/check/report/cancel/trash) work; sle daemon runs the full Slack-mode loop (socket-mode broker, /check success 200, mock task execution COMPLETE) against local mocks; real Anthropic/Slack credentials still needed for genuine end-to-end operation.

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

At a glance

verdict
Runs with mocks
Argusic Score
87 / 100
cost of the verifying run
$0.72 (measured)
recorded runs
2
last tested
stars
840
forks
111
open issues
1
watchers
17
size
6 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 sleepless-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.

  • daemon hard-requires SLACK_BOT_TOKEN/SLACK_APP_TOKEN despite README promising CLI-only mode (RuntimeError in SleeplessAgent.__init__)20 minutes
  • no Anthropic credentials available; real API rejects fake keys with 40115 minutes
  • claude CLI missing on PATH and npm global install needs root (EACCES)3 minutes
Install time
51 minutes
Cold machine to finish
53 minutes
Errors hit and fixed
3 hit, 3 fixed with no human help
How the result was proved
sle check rc=0 (dashboard HEALTHY); ClaudeCodeExecutor.execute_task rc 0, EVAL COMPLETE; sle daemon logged 'Slack bot started and listening for events', handled WS /check + message, 'send_response: success status=200', stayed up under timeout; claude -p returned 'ACK say hi' via mock; pip install -e . succeeded
Model tokens used
3,253,007
Exact commit tested
dbeb1c28699b
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.

- Open gaps I could not close without real credentials: `claude usage` parsing of the welcome scree…
`ARGUSIC_RESULT: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 51, "erro…
tokens used
3,253,007
All verification is complete and recorded. Here is my final summary and the required result line.
**What happened (all observed)**
- Standard install: `pip install -e .` in a fresh venv built the package and installed cleanly; `sl…
- Real `claude` binary is absent from the container, and `npm install -g @anthropic-ai/claude-code`…
- With no Anthropic credentials (`Not logged in` / real API returns 401 for fake keys), I stood up …
- Verified end to end: `claude -p` returned `ACK say hi`; `ClaudeCodeExecutor.execute_task` returne…
- Open gaps I could not close without real credentials: `claude usage` parsing of the welcome scree…
`ARGUSIC_RESULT: {"install_succeeded": true, "launch_succeeded": true, "install_minutes": 51, "erro…

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 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.
  • Took 51 minutes to install, slower than the median of the 83 comparable projects Argusic has measured.

Of the 84 ai-agent projects Argusic has installed and timed, sleepless-agent was the 84th fastest to reach a running state, and 58 of 84 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 mocks82.000.06
Argusic Runner1/3Runs with mocks92.000.72

Topics (from GitHub)

ai-agentanthropicautomationautonomous-agentsclaudeclaude-codedaemongit-automationpythonslackslack-botsqlitetask-automationworkflow-automationworkspace-management

Embed the badge

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

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

Questions

Does sleepless-agent run?
sleepless-agent runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 51 minutes, hitting 3 errors on the way, and recorded the session.
How did Argusic test sleepless-agent?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit dbeb1c28699b. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test sleepless-agent?
The run that produced this verdict cost $0.72: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does sleepless-agent take to install?
51 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 sleepless-agent need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing sleepless-agent?
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 sleepless-agent compare with the alternatives?
Of the 84 ai-agent projects Argusic has installed and timed, sleepless-agent was the 84th fastest to reach a running state, and 58 of 84 reached one at all.
Where is the evidence for sleepless-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