← the index
CherryHQ/cherry-studio
27.4%
of 2,942 commits were committed by an AI agent — a floor, not an estimate
27.4% agent · top contributor 39%55 contributors
org-wide

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

805
agent commits
2,137
human commits
55
agent contributors
39%
largest contributor

Assisted or autonomous

803assisted
2autonomous

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
May26
Jun26
Jul26
Aug26
Sep26

Peak month: 47.3%. Bars are scaled to that peak, not to 100%.

Which agents

Claude CodeAnthropic79226.9%
GitHub CopilotGitHub140.5%
Cursor AgentAnysphere40.1%

Verify it yourself

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

  • 6868143arevert(preference): drop invalid-JSON startup repair seeder (#19969)Claude Code
  • 74e48e34feat(translate): add temperature, top-p and reasoning effort (#19700)Claude Code
  • c7068045perf(mini-app): isolate card subscriptions (#19884)Claude Code
  • 401acf3afix(provider-registry): detect Xunfei MaaS reasoning models (#17811)GitHub Copilot
  • a1ce1621fix(chat-messages): stop reading-mode freeze from fighting middle-click auGitHub Copilot
  • 35c3db17fix(chat): keep thinking elapsed stable across tab switches (#19764)GitHub Copilot
  • 4e71ffc7fix(mcp-settings): defer capability fetches until tab activation (#18550)Cursor Agent
  • 26508591refactor(paintings): migrate to v2 data layer and UI (#15154)Cursor Agent
  • e59c7aa7refactor(provider-settings): migrate to v2 data layer and UI (#14631)Cursor Agent

What was excluded

Commits in window3,041
Merge commits removed39
CI / dependency bots removed60
Considered2,942

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 CherryHQ/cherry-studio

Scan another repository