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: 61.1%. Bars are scaled to that peak, not to 100%.
Which agents
| Claude Code | Anthropic | 116 | 34.4% |
| Cursor Agent | Anysphere | 10 | 3% |
| Other / generic agent | Various | 1 | 0.3% |
Verify it yourself
Sample commits that matched. Every one links to GitHub — check the trailers.
485293badocs: serve docs site at docs.continue.dev root (basePath "" + CNAME)Claude Code740e537aUpdate READMEClaude Codeae32a1b8feat: filter session history by workspace directory (#11813)Claude Coded0a3c0b6fix(gui): remove GitHub issue reporting entrypoints (#12816)Cursor Agentf0df398cfix(gui): remove awkward inner scroll on onboarding API-key card (#12802)Cursor Agentd3f60ba9fix(cli): use explicit model definitions in default config instead of Hub Cursor Agent19c3f358feat: add Tensorix as an LLM provider (#11184)Other / generic agent
What was excluded
| Commits in window | 499 |
| Merge commits removed | −98 |
| CI / dependency bots removed | −64 |
| Considered | 337 |
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 continuedev/continue