agentty

AI pair programming in your terminal, one static binary, sub-ms startup, any model

Could not verifysource: GitHubhomepageC++MITcommit 23560a0487bd

C++, MIT licensed. The project labels itself: agentic coding, ai agent, anthropic, claude, claude code, claude code alternative, cli and coding agent.

Argusic could not get agentty running. An Argusic agent installed it in 33 minutes and hit 4 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.

Prebuilt agentty 0.9.26 linux x86_64 release binary is installed at /home/runner/.local/bin/agentty and responds to all query subcommands (version, status, config doctor, skills, help, diagnostics). Source build fails at the jaal submodule due to insufficient compiler support for C++26 structured binding packs.

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

At a glance

verdict
Could not verify
Argusic Score
50 / 100
cost of the verifying run
$0.12 (measured)
recorded runs
2
last tested
stars
560
forks
31
open issues
1
watchers
3
size
59 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 agentty, 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.

  • Source build fails: jaal dependency needs C++26 structured binding packs (P1061) which require Clang 22+ or GCC 16+. Available compiler is Clang 19.1.7 (via LLVM prebuilt).33 minutes
  • libnghttp2-dev not installed in container (only libnghttp2-14 shared lib present). Headers missing for find_path/find_library.10 minutes
  • CMake 3.28.3 was too old for jaal submodule (req 3.29+).5 minutes
  • maya CMakeLists.txt hard-failed on C++26 detection with GCC 13 (no -std=c++2c).5 minutes
Install time
33 minutes
Cold machine to finish
30 minutes
Errors hit and fixed
4 hit, 4 fixed with no human help
How the result was proved
/home/runner/.local/bin/agentty --version returned 'agentty 0.9.26'; agentty status returned credentials file paths; agentty config doctor returned 'healthy.'; agentty skills returned 'no skills installed.'; agentty help printed 113 lines of usage information; agentty diagnostics succeeded.
Model tokens used
566,830
Exact commit tested
23560a0487bd
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
Whether it works at all
this run verified nothing, so this page makes no claim either way

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

=== agentty session: 0.9.26 release pid=1352 cwd=/work/repo ===
2026-10-17T00:43:07.092 +0000000ms 40a1 W general startup: agentty 0.9.26 os=linux arch=x86_64 buil…
=== agentty session: 0.9.26 release pid=5986 cwd=/work/repo ===
2026-10-17T01:02:55.684 +0000000ms 4afd W general startup: agentty 0.9.26 os=linux arch=x86_64 buil…
Now I have a complete picture. Let me compile the final report.
The prebuilt binary (v0.9.26) works. Source build fails because the project's dependency jaal requi…
exec
/bin/sh -lc "echo \"1792199128\" | python3 -c \"from datetime import datetime; ts=int(__import__('s…
 succeeded in 0ms:
0.225981601079305
tokens used
566,830

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 4 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

  • An agent with no time limit did not get it running.
  • Took 33 minutes to install, slower than the median of the 29 comparable projects Argusic has measured.

Of the 30 agentic-coding projects Argusic has installed and timed, agentty was the 29th fastest to reach a running state, and 23 of 30 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 Runner2/3Unverified80.000.12
Argusic Runner1/3Did not run20.000.06

Topics (from GitHub)

agentic-codingai-agentanthropicclaudeclaude-codeclaude-code-alternativeclicoding-agentcppdeveloper-toolsllmmcpollamaopenairagretrieval-augmented-generationsandboxstatic-binaryterminaltui

Embed the badge

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

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

Questions

Does agentty run?
Argusic could not verify that agentty runs. Argusic installed and launched it on a clean machine in 33 minutes, hitting 4 errors on the way, and recorded the session.
How did Argusic test agentty?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit 23560a0487bd. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test agentty?
The run that produced this verdict cost $0.12: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does agentty take to install?
33 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 agentty need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing agentty?
4 things broke in the recorded run, and 4 were fixed without human help. Each one, and the time it cost, is listed on this page.
How does agentty compare with the alternatives?
Of the 30 agentic-coding projects Argusic has installed and timed, agentty was the 29th fastest to reach a running state, and 23 of 30 reached one at all.
Where is the evidence for agentty?
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