repository · survival report #2 · 2026-09-23 · method v2 · unranked

run-llama/llama_index

In Survival Report #2 (2026-09-23, method v2): 7,872 of 8,542 lines introduced by 13 AI-tagged commits are still at HEAD, 92.2 %. 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 #2 · all repositories · Atom feed

13AI-tagged commits · of 7,942 8,542lines introduced by them 7,872still attributed to them at HEAD 92.2 %line-weighted 90.4 %median per commit 73 %of introduced lines in the largest commit

By agent, in Survival Report #2

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

AgentCommitsLines introducedStill at HEADLine-weightedCapped
claude-code118,0117,47793.3 %93.3 %
cursor142130171.5 %71.5 %
github-copilot11109485.5 %85.5 %

History across reports

One row per report this repository was measured in, oldest first; each report measured HEAD as of its own date. A line appears once the repository has been measured in two reports.

ReportDateAI-tagged commitsLines introducedStill at HEADLine-weighted
Survival Report #22026-09-23138,5427,87292.2 %

Reproduce

One command, any machine, no account: the same bytes the report was built from. The exact bytes behind this page are repos/run-llama__llama_index.json of Survival Report #2. Open an issue with your JSON if it differs.

re audit run-llama/llama_index --json   # method v2, 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 92.2 % · causari · #2 AI code survival 92.2 % · causari · #2, paper on ink

README · Markdown
[![AI code survival](https://causari.dev/r/run-llama/llama_index/badge.svg)](https://causari.dev/r/run-llama/llama_index/)

Coverage

  • Method v2, causari 0.2.0. Detection from commit metadata only; survival from git blame -w -M -C at HEAD.
  • Full clone: yes. Method v2 refuses shallow clones; this row comes from a complete history.
  • Sample: 13 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: 6,198 lines per commit in this repository; the capped ratio is 92.2 %.
  • .git-blame-ignore-revs: not present in this repository.