neuron-ai

The Agentic Framework of the PHP ecosystem to build production-ready AI driven applications. Connect components (LLMs, Tools, vector DBs, memory) to agents that interact with your data and UI.

Runssource: GitHubhomepagePHPMITcommit f6d4e4507309

PHP, MIT licensed. The project labels itself: agent, agentic ai, agentic framework, agents, ai, llm, llm inference and llms.

neuron-ai runs. An Argusic agent installed it in 15 minutes and hit 7 errors on a clean machine with no GPU, and the whole session was recorded.

Composer install with all 145 dependencies succeeded; vendor/bin/phpunit reports 1373 tests, 5460 assertions passed, 0 failures, 0 errors, 78 skipped (external services); vendor/bin/phpstan analyse reports OK, 0 errors; bin/neuron CLI reports help with 7 commands

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

At a glance

verdict
Runs
Argusic Score
58.6 / 100
cost of the verifying run
$0.23 (measured)
recorded runs
2
last tested
stars
2,122
forks
254
open issues
5
watchers
31
size
29 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 neuron-ai, 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.

  • PHP 8.1+ not installed (no root apt permissions)3 minutes
  • Composer install failed: zip extension missing, no unzip binary2 minutes
  • Disk full (7.8G partition at 100%) during composer install2 minutes
  • psr.so extension (from php8.3-common) provides PsrExt\Http\Message\ResponseInterface conflicting with PHP-level PSR-7 interfaces2 minutes
  • Composer.phar requires phar, mbstring extensions1 minute
  • PDO SQLite driver not found for Eloquent tests1 minute
Install time
15 minutes
Cold machine to finish
33 minutes
Errors hit and fixed
7 hit, 6 fixed with no human help
How the result was proved
vendor/bin/phpunit exited 0, 1373 tests, 5460 assertions, 0 failures, 0 errors, 78 skipped
Model tokens used
343,307
Exact commit tested
f6d4e4507309
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

The end of the recording

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

All verifications done. Let me compile the final result
exec
/bin/sh -lc '# Final verification: run the full suite one more time to get precise counts
cd /work/repo && PATH="/tmp/unzip-extract/usr/bin:$PATH" /tmp/phpcache/usr/bin/php8.3 -c /tmp/phpco…
 succeeded in 1314ms:
Time: 00:01.258, Memory: 44.00 MB
OK, but some tests were skipped!
Tests: 1373, Assertions: 5460, Skipped: 78.
All tasks complete. Let me present the final result.
tokens used
343,307
All tasks complete. Let me present the final result.

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.
  • 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 15 minutes to install, slower than the median of the 68 comparable projects Argusic has measured.
  • Hit 7 errors during setup, 1 of which were not solved.

Of the 69 agent projects Argusic has installed and timed, neuron-ai was the 48th fastest to reach a running state, and 47 of 69 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 Runner2/3Runs97.140.23
Argusic Runner1/3Did not run20.000.12

Topics (from GitHub)

agentagentic-aiagentic-frameworkagentsaillmllm-inferencellmsphpvector-database

Embed the badge

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

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

Questions

Does neuron-ai run?
Yes. neuron-ai runs. Argusic installed and launched it on a clean machine in 15 minutes, hitting 7 errors on the way, and recorded the session.
How did Argusic test neuron-ai?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit f6d4e4507309. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test neuron-ai?
The run that produced this verdict cost $0.23: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does neuron-ai take to install?
15 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 neuron-ai need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing neuron-ai?
7 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 neuron-ai compare with the alternatives?
Of the 69 agent projects Argusic has installed and timed, neuron-ai was the 48th fastest to reach a running state, and 47 of 69 reached one at all.
Where is the evidence for neuron-ai?
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