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 | 1536 | 36.1% |
| GitHub Copilot | GitHub | 62 | 1.5% |
| Cursor Agent | Anysphere | 27 | 0.6% |
| OpenAI Codex | OpenAI | 1 | 0% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
c0dbe306test(embeddeddolt): let the dep-rekey marker sit below the ignored-series Claude Codef56632adperf(storage): stop burning two wasted MySQL sessions per bd invocation (wClaude Codee21eaf00refactor(import): retire the same-chunk regular<->wisp deferral (wy-y52sycClaude Code9ca6b51bci(nix): auto-update default.nix vendorHash on dependabot Go bumps (#3804)GitHub Copilot6ec4a0d6chore: untrack workflow formulasGitHub Copilot202a4d07chore: track workflow formulas for portabilityGitHub Copilotc990ff2bfix(prime): never split UTF-8 when truncating compact memories (#5338)Cursor Agent9827c663fix(github): content-based dedup on push to stop re-PATCHing every issue (Cursor Agentf4d496fefix(worktree): repair permissive .beads/ after worktree create (GH#3593) (Cursor Agent1696e2f7Make init prompts cancelableOpenAI Codex
What was excluded
| Commits in window | 5,165 |
| Merge commits removed | −796 |
| CI / dependency bots removed | −118 |
| Considered | 4,251 |
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 gastownhall/beads