repository · survival report #5 · 2026-10-12 · method v4 · unranked

openai/openai-agents-python

In Survival Report #5 (2026-10-12, method v4): 97,002 of 97,483 lines introduced by 6 AI-tagged commits are still at HEAD, 99.5 %. These are counts, not grades. No rank, no colour, no verdict, and no comparison with any other repository on this page. Every number links to the audit bytes behind it and the method and its limits are public.

GitHub · latest.json · badge.svg · Survival Report #5 · all repositories · Atom feed

6AI-tagged commits · of 2,368 97,483lines introduced by them 97,002still attributed to them at HEAD 99.5 %line-weighted 89.4 %median per commit 97 %of introduced lines in the largest commit

Baseline: this repository's untagged lines

Commits with no machine-readable AI signal, human-written, inline-completed or untagged-agent code alike: 2,362 commits, 726,331 lines introduced, 486,431 still at HEAD (67.0 % line-weighted, 77.8 % median per commit). Age is the time from a commit to HEAD. The baseline was added in method v3 and is unchanged later; definition at causari.dev/method.

No age window holds at least 5 commits of both kinds, so there is no age-matched figure.

Line ageAI-taggedcommitsUntaggedcommits
0–30 d86.2 %487.1 %237
30–90 d—077.7 %550
90–180 d100.0 %153.9 %375
180–365 d42.9 %157.8 %534
365–730 d—056.9 %666

By agent, in Survival Report #5

Alphabetical. A commit is attributed to the agent its metadata names; one agent per commit. VERIFIED commits only.

AgentCommitsLines introducedStill at HEADLine-weightedCapped
claude-code43,3072,85086.2 %86.2 %
openai-codex294,17694,152100.0 %99.8 %

History across reports

One row per report this repository was measured in, oldest first; each report measured HEAD as of its own date. The line is the line-weighted ratio on a fixed 0 – 100 % axis; each point is one report.

Line-weighted ratio across reports, 0 to 100 %: #3 99.8 %; #4 99.5 %; #5 99.5 %
ReportDateAI-tagged commitsLines introducedStill at HEADLine-weighted
Survival Report #22026-09-23294,17694,152n < 5
Survival Report #32026-09-28595,77395,59399.8 %
Survival Report #42026-10-05697,48397,00299.5 %
Survival Report #52026-10-12697,48397,00299.5 %

Reproduce

One command, any machine, no account: the same bytes the report was built from. The exact bytes behind this page are repos/openai__openai-agents-python.json of Survival Report #5. Open an issue with your JSON if it differs.

re audit openai/openai-agents-python --json   # method v4, full clone

Badge

Text only, one colour, no red and no green. It follows the latest report and is cached for one hour. badge-dark.svg is the same badge as paper on ink.

AI code survival 99.5 % · causari · #5 AI code survival 99.5 % · causari · #5, paper on ink

README · Markdown
[![AI code survival](https://causari.dev/r/openai/openai-agents-python/badge.svg)](https://causari.dev/r/openai/openai-agents-python/)

Coverage

  • Method v4, causari 0.4.1. Detection from commit metadata only; survival from git blame -w -M -C at HEAD.
  • Full clone: yes. Method v4 refuses shallow clones; this row comes from a complete history.
  • Sample: 6 AI-tagged commits; the sample floor is 5. At or above the floor, so the ratio is aggregated into the report.
  • PROBABLE: No PROBABLE commits: every counted commit carries machine-readable AI authorship metadata.
  • Cap: 10,000 lines per commit in this repository; the capped ratio is 96.4 %.
  • .git-blame-ignore-revs: not present in this repository.