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: 23.6%. Bars are scaled to that peak, not to 100%.
Which agents
| Cursor Agent | Anysphere | 53 | 6.6% |
| Claude Code | Anthropic | 15 | 1.9% |
| OpenAI Codex | OpenAI | 1 | 0.1% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
5d5055f9docs: update README for removed PROVIDER_TYPE, model prefix formatCursor Agentdb646ef2Remove auto support for whisper_device; only cpu and cuda allowedCursor Agent2135e6daAdd large-v3 and large-v3-turbo whisper model optionsCursor Agentf5e49ea7Add OpenCode Go subscription gateway provider (#505)Claude Codefae8a2a0Remove over-engineering: drop tree_queue setter, _set_connected(), fi… (#6Claude Code8ffe587adocs: rename model picker summary to Multi-Model Support (Model Picker)Claude Codec36c97f8Add Codex App model catalog support (#1297)OpenAI Codex
What was excluded
| Commits in window | 881 |
| Merge commits removed | −33 |
| CI / dependency bots removed | −39 |
| Considered | 809 |
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 Alishahryar1/free-claude-code