ruby-openai
OpenAI API + Ruby! 🤖❤️ GPT-5 & Realtime WebRTC compatible!
Runs with mockssource: GitHubhomepageRubyMITcommit 62938e02bb83
Ruby, MIT licensed. The project labels itself: ai, api client, chatgpt, dall e, gpt 4, gpt 4o, o1 and openai.
ruby-openai runs, with stand-ins for the services it depends on. An Argusic agent installed it in 8 minutes and hit 5 errors and fixed every one without help on a clean machine with no GPU, and the whole session was recorded.
Ruby 3.2.3 and all gem dependencies (40 gems) are installed in a local prefix under /home/runner/ruby, the ruby-openai gem loads without errors, and all 155 test specs pass when run via bundle exec rspec.
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
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.
What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Ruby not installed in container2 minutes
- Ruby header files not found (native ext gems require ruby.h)2 minutes
- libruby-3.2.so.3.2 not found on library path1 minute
- libyaml-0.so.2 not found (RubyGems requires it)1 minute
- Bundler version mismatch (lockfile 2.4.5, installed 4.0.22)1 minute
- Install time
- 8 minutes
- Cold machine to finish
- 17 minutes
- Errors hit and fixed
- 5 hit, 5 fixed with no human help
- How the result was proved
- bundle exec rspec --format progress exited 0 with '155 examples, 0 failures'
- Model tokens used
- 107,626
- Exact commit tested
- 62938e02bb83
- 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.
4. **Ruby include headers** — Native extension gems (`bigdecimal`, `json`, `racc`, `byebug`) need t… **Test results**: All 155 specs pass, 0 failures, running against pre-recorded VCR cassettes (no re… tokens used 107,626 All 155 tests pass against the pre-recorded VCR cassettes (no real API keys needed). Here's the sum… **Installation**: Extracted Ruby 3.2.3 from Debian package archives into a local prefix at `/home/r… **Issues encountered and fixed**: 1. **Missing Ruby** — Ruby wasn't installed in the container. Downloaded and extracted Debian packa… 2. **Shared library path** — Needed `LD_LIBRARY_PATH` set to `/home/runner/ruby/usr/lib/x86_64-linu… 3. **Need libyaml** — RubyGems requires `libyaml-0.so.2`; downloaded `libyaml-0-2` Debian package a… 4. **Ruby include headers** — Native extension gems (`bigdecimal`, `json`, `racc`, `byebug`) need t… **Test results**: All 155 specs pass, 0 failures, running against pre-recorded VCR cassettes (no re…
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 5 errors without a human stepping in, which says the failures are documented well enough to solve.
- Licensed MIT, as reported by its host.
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 8 minutes to install, slower than the median of the 72 comparable projects Argusic has measured.
- Measured once so far. A single attempt shows it can run, not that it runs reliably.
Of the 73 ai projects Argusic has installed and timed, ruby-openai was the 46th fastest to reach a running state, and 53 of 73 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 by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 1/3 | Runs with mocks | 92.00 | 0.08 |
Topics (from GitHub)
aiapi-clientchatgptdall-egpt-4gpt-4oo1openairailsrubywhisper
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/ruby-openai)Questions
- Does ruby-openai run?
- ruby-openai runs, with mocks standing in for external services. Argusic installed and launched it on a clean machine in 8 minutes, hitting 5 errors on the way, and recorded the session.
- How did Argusic test ruby-openai?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit 62938e02bb83. One attempt is recorded, and the full method is on the methodology page.
- What did it cost to test ruby-openai?
- The run that produced this verdict cost $0.08: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does ruby-openai take to install?
- 8 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 ruby-openai need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing ruby-openai?
- 5 things broke in the recorded run, and 5 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does ruby-openai compare with the alternatives?
- Of the 73 ai projects Argusic has installed and timed, ruby-openai was the 46th fastest to reach a running state, and 53 of 73 reached one at all.
- Where is the evidence for ruby-openai?
- The recorded run is on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.