repository · survival report #6 · 2026-10-19 · method v4 · unranked

BerriAI/litellm

In Survival Report #6 (2026-10-19, method v4): 1,669,345 of 2,536,387 lines introduced by 5,914 AI-tagged commits are still at HEAD, 65.8 %. 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 #6 · all repositories · Atom feed

5,914AI-tagged commits · of 45,139 2,536,387lines introduced by them 1,669,345still attributed to them at HEAD 65.8 %line-weighted 68.9 %median per commit 3 %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: 39,225 commits, 6,604,890 lines introduced, 3,116,129 still at HEAD (47.2 % line-weighted, 12.5 % 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.

Age-matched: AI-tagged lines 65.8 % against untagged lines in the matched age windows 60.3 %, a gap of +5.5 pts, over 5 age windows holding 100 % of the AI-tagged lines.

Line ageAI-taggedcommitsUntaggedcommits
0–30 d75.0 %1,75966.1 %1,077
30–90 d58.5 %2,27957.4 %5,010
90–180 d54.5 %64159.1 %2,231
180–365 d52.0 %1,13636.1 %7,447
365–730 d49.3 %9743.6 %7,670
730+ d28.0 %239.7 %15,790

By agent, in Survival Report #6

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

AgentCommitsLines introducedStill at HEADLine-weightedCapped
aider753091.7 %1.7 %
claude-code1,350469,941290,63261.8 %63.0 %
cursor538367,724165,53145.0 %66.9 %
devin3,8961,650,3601,182,24971.6 %74.1 %
github-copilot8436,92422,53261.0 %58.9 %
openai-codex212,9612,05369.3 %69.3 %
openhands187,9476,33979.8 %79.8 %

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 %: #2 61.2 %; #3 62.2 %; #4 65.2 %; #5 62.7 %; #6 65.8 %
ReportDateAI-tagged commitsLines introducedStill at HEADLine-weighted
Survival Report #22026-09-234,7061,341,172821,28161.2 %
Survival Report #32026-09-284,9671,509,602938,29162.2 %
Survival Report #42026-10-055,1931,774,3521,157,04065.2 %
Survival Report #52026-10-125,5752,217,6401,390,90062.7 %
Survival Report #62026-10-195,9142,536,3871,669,34565.8 %

Reproduce

One command, any machine, no account: the same bytes the report was built from. The exact bytes behind this page are repos/BerriAI__litellm.json of Survival Report #6. Open an issue with your JSON if it differs.

re audit BerriAI/litellm --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 65.8 % · causari · #6 AI code survival 65.8 % · causari · #6, paper on ink

README · Markdown
[![AI code survival](https://causari.dev/r/berriai/litellm/badge.svg)](https://causari.dev/r/berriai/litellm/)

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: 5,914 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: 1,826 lines per commit in this repository; the capped ratio is 70.8 %.
  • .git-blame-ignore-revs: honoured.