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: 11.8%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 4 | 1.6% |
| GitHub Copilot | GitHub | 2 | 0.8% |
| Cursor Agent | Anysphere | 1 | 0.4% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
6d6d6250docs: add TiDB to BYODB documentation (#446)Claude Code7263d3c8fix: sanitise recalled history to prevent tool-call corruption (#434) (#43Claude Code46e93bd7Version bump integrations / OC version for npm (#403)Claude Codef79ae840Enhance Hermes Memori integration with improved path resolution and d… (#5GitHub Copilot91ed0a68Hermes compaction (#511)GitHub Copilote6df17fcTransfer SQL drivers and migrations from TypeScript to Rust core (#577)Cursor Agent
What was excluded
| Commits in window | 253 |
| Merge commits removed | −1 |
| CI / dependency bots removed | −0 |
| Considered | 252 |
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 MemoriLabs/Memori