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: 26.6%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 87 | 12.1% |
| Cursor Agent | Anysphere | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
fdfb763ddocs(api-reference): add Dream (memory synthesis) endpoints (#7109)Claude Code4cfcd024docs: add Dream feature page (#6689)Claude Code8005e18afix(qdrant): actually clear points on reset() for local Qdrant (#6412)Claude Code890473f8fix(core): validate and trim entity IDs in delete_all() (#5735)Cursor Agent
What was excluded
| Commits in window | 733 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −12 |
| Considered | 721 |
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 mem0ai/mem0