← the index
zylon-ai/private-gpt ↗
20%
of 80 commits were committed by an AI agent — a floor, not an estimate
Too little recent activity to publish. Only 80 commits landed in this window, so the percentage is noisy. Repositories below 100 are excluded from the index for this reason.
20% agent · top contributor 81.3%4 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

16
agent commits
64
human commits
4
agent contributors
81.3%
largest contributor

Assisted or autonomous

16assisted
0autonomous

Assisted — a developer’s identity authored the commit and the agent added itself as co-author. The agent ran git commit during a working session, with a person there. Autonomous — a bot identity is the author, no human in the loop. Across the whole index, 93.7% of agent commits are assisted.

Agent share by month

Feb26
Jun26
Jul26
Aug26
Sep26

Peak month: 33.3%. Bars are scaled to that peak, not to 100%.

Which agents

GitHub CopilotGitHub1316.3%
Claude CodeAnthropic45%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • 39b3a79bfix(tabular): force-close sandbox after analysis to avoid leaks (#2357)GitHub Copilot
  • 21d42fd9feat: code execution v4 (#2295)GitHub Copilot
  • cd8ca221feat: resumable chat worker + tool worker + async tokenizer (#2298)GitHub Copilot
  • cdf4d332feat: add compatibility with skill creator (#2342)Claude Code
  • cd543c2adocs: add DaoXE OpenAI-compatible gateway configuration example (#2303)Claude Code
  • f2cffd1afeat: code execution v2 (#2278)Claude Code

What was excluded

Commits in window97
Merge commits removed−0
CI / dependency bots removed−17
Considered80

Bots are excluded from the denominator entirely. Counting dependabot as “AI-written code” is the fastest way to produce a meaningless number.

How this was measured

Measured over February–August 2026, cloned directly. Detection is deterministic string matching against signatures agents write about themselves — no heuristics, no style analysis. Merge commits and CI bots are excluded from the denominator. The figure is a floor: squash merges strip trailers, so real usage is higher. Contributor counts are aggregate — no individual is named.

Run it yourself: npx qmmit-cli zylon-ai/private-gpt

Scan another repository

Try