← the index
Kilo-Org/kilocode
0.3%
of 14,533 commits were committed by an AI agent — a floor, not an estimate
0.3% agent · top contributor 19.1%31 contributors
org-wide

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

47
agent commits
14,486
human commits
31
agent contributors
19.1%
largest contributor

Assisted or autonomous

47assisted
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

Jan26
Feb26
Mar26
Apr26
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 0.6%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic330.2%
GitHub CopilotGitHub90.1%
Cursor AgentAnysphere50%
DevinCognition20%

Verify it yourself

Sample commits that matched. Every one links to GitHub — check the trailers.

  • 18657ca3fix: rewrite opening paragraph to lead with DaoXE differentiatorsClaude Code
  • 7437f773Move NES prompt templating to the gateway + wire FileIgnoreControllerClaude Code
  • ca264243Address review feedback: NES correctness, dedupe, testsClaude Code
  • 9fa8a13efix(ui): preserve auto-scroll pause after wheel upGitHub Copilot
  • 7f571d36refactor(core): move database schema ownership (#29068)GitHub Copilot
  • 202ec120docs: fix grammar in config.mdx (#29683)GitHub Copilot
  • f54c215efix(cli): persist snapshot disable across restartsCursor Agent
  • 2d109462Add Atomic Chat as a first-class local provider. (#10555)Cursor Agent
  • 7f7eb2e7fix(provider): remove LiteLLM workarounds ported upstream, requires LiteLLCursor Agent
  • c5a4a828fix: dont show gpt-5.5-pro when using codex oauth (#33400)Devin
  • 1b5ef073Merge OpenCode v1.1.42 (#67)Devin

What was excluded

Commits in window21,994
Merge commits removed4,491
CI / dependency bots removed2,970
Considered14,533

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 Kilo-Org/kilocode

Scan another repository