A small group is using agents. Adoption has spread beyond one person but is not project-wide.
Assisted or autonomous
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
Peak month: 78%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 102 | 19.8% |
| Devin | Cognition | 53 | 10.3% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
58df71d3fix(agents): let an agent wait on what it already said (#1020)Claude Code0b9e029atest(tui): correct the nudge the internal-turn test asserts (#1016)Claude Codeb260a4eefix(tui): make the mount prompt clickable, and skip the mount instead of aClaude Code52b19233fix(models): frontier model check matches the model name only, never the pDevinf4b0416bdocs: update README and CLI links (#1272)Devinafa7c4a7feat(web_search): add Exa as a web search provider alongside Perplexity (#Devin
What was excluded
| Commits in window | 528 |
| Merge commits removed | −4 |
| CI / dependency bots removed | −9 |
| Considered | 515 |
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 usestrix/strix