Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
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: 7.7%. Bars are scaled to that peak, not to 100%.
Which agents
| GitHub Copilot | GitHub | 252 | 3.5% |
| Claude Code | Anthropic | 33 | 0.5% |
| Cursor Agent | Anysphere | 21 | 0.3% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
d9680f2cSERVER-134544 Skip metadata consistency check in add_shard_refurbish.js (#GitHub Copilot41cc88c6SERVER-134518 Exclude cardinality_and_frequency.js from implicit-shard jscGitHub Copilot46014702SERVER-132944: Rotate phylog encryption keys between checkpoint and promotGitHub Copilot5a311533SERVER-133243 Exponential backoff for PlanExecutorImpl write conflict retrClaude Codead19c39bSERVER-133644: Implement custom build framework (#61193)Claude Codefd4850ecSERVER-133338 Ensure Atlas Infinite cannot be used in our public server coClaude Code9b3f53cbSERVER-133659 Allow updating allowDeletions on an active replica set writeCursor Agentd2ccf277SERVER-133822 Label size-stats histogram from WT-published ceiling (#61455Cursor Agent60bbe3aaSERVER-132823 Tolerate transient setFCV errors in concurrent FCV FSM testsCursor Agent
What was excluded
| Commits in window | 7,693 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −510 |
| Considered | 7,183 |
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 mongodb/mongo