← the index
continuedev/continue
37.7%
of 337 commits were committed by an AI agent — a floor, not an estimate
37.7% agent · top contributor 45.7%13 contributors
org-wide

Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.

127
agent commits
210
human commits
13
agent contributors
45.7%
largest contributor

Assisted or autonomous

127assisted
0autonomous

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

Feb26
Mar26
Apr26
Jun26
Jul26

Peak month: 61.1%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic11634.4%
Cursor AgentAnysphere103%
Other / generic agentVarious10.3%

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 Code
  • 740e537aUpdate READMEClaude Code
  • ae32a1b8feat: filter session history by workspace directory (#11813)Claude Code
  • d0a3c0b6fix(gui): remove GitHub issue reporting entrypoints (#12816)Cursor Agent
  • f0df398cfix(gui): remove awkward inner scroll on onboarding API-key card (#12802)Cursor Agent
  • d3f60ba9fix(cli): use explicit model definitions in default config instead of Hub Cursor Agent
  • 19c3f358feat: add Tensorix as an LLM provider (#11184)Other / generic agent

What was excluded

Commits in window499
Merge commits removed98
CI / dependency bots removed64
Considered337

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

Scan another repository