One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.
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: 31.5%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 73 | 20.6% |
| Cursor Agent | Anysphere | 1 | 0.3% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
b5375f8cAdd Kimi K2.7-Code model card (official INT4 weights + vision) (#2167)Claude Codee8ec8d50fix ollama API compatibility for VS Code Copilot (#2091)Claude Codea0c00f9dfix(placement): gate RDMA on nodeRdmaCtl.enabled at both endpoints (#2014)Claude Codedab7ed48fix: handle gossipsub MessageTooLarge error to prevent silent crash (#1583Cursor Agent
What was excluded
| Commits in window | 354 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −0 |
| Considered | 354 |
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 exo-explore/exo