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: 83.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 66 | 43.1% |
| Cursor Agent | Anysphere | 14 | 9.2% |
| GitHub Copilot | GitHub | 1 | 0.7% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
2d96f271fix(falkordb): avoid a full :Entity scan per hit in edge_fulltext_search (Claude Code23330cbcHonor NEO4J_DATABASE in MCP serverClaude Code993e081afix(attributes): preserve prior node attributes when no entity type applieClaude Codeeaa41286Bump graphiti-core to 0.30.2 (#1858)Cursor Agent3ff5c160Land contributor fixes from #1686 #1689 #1720 #1761 (#1856)Cursor Agent11538f6dbump mcp server to 1.1.0 with graphiti-core 0.30.1Cursor Agent0290e4dePotential fix for code scanning alert no. 26: Workflow does not contain peGitHub Copilot
What was excluded
| Commits in window | 241 |
| Merge commits removed | −0 |
| CI / dependency bots removed | −88 |
| Considered | 153 |
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 getzep/graphiti