- Dataset
- 2026-09-18-v3.0
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-09-16
- Window
- February–September 15, 2026
01Result
CherryHQ/cherry-studio ↗CherryHQ/cherry-studio AI coding statistics: 26.7%
Adoption is broad. Many contributors are committing agent-authored work, which is what a real organisational rollout looks like.
02Drivers
What shapes this result
Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.
Assisted or autonomous
Assisted — a developer’s identity authored the commit and the agent added itself as co-author. Autonomous — a bot identity authored the commit without a human identity attached. Across the whole index, 96% of agent commits are assisted.
Agent share by month
| Month | Agent share | Considered commits |
|---|---|---|
| 2026-02 | 47.3% | 131 |
| 2026-03 | 34.1% | 367 |
| 2026-04 | 21.6% | 328 |
| 2026-05 | 20.3% | 177 |
| 2026-06 | 35.7% | 345 |
| 2026-07 | 22.3% | 660 |
| 2026-08 | 26.1% | 847 |
| 2026-09 | 19.5% | 298 |
Peak month: 47.3%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| Claude Code | Anthropic | 829 | 26.3% |
| GitHub Copilot | GitHub | 19 | 0.6% |
| Cursor Agent | Anysphere | 3 | 0.1% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
94d673daon GitHubfix(global-search): debounce queries and skip IME composition intermediateClaude Code8aaf9255on GitHubfix(image-export): pre-inline remote images with content-type verificationClaude Code65efb53fon GitHubfix(shortcut): label the Enter key as Return on macOS (#20279)Claude Code2c839855on GitHubfix(composer): persist atomic chat draft snapshots (#19901)GitHub Copilotb5270f22on GitHubfix: restore window focus on Windows after hiding main window (#16277)GitHub Copilot9db4ff54on GitHubfix(agent-prompt): decouple agent reply language from UI locale and defer GitHub Copilot4e71ffc7on GitHubfix(mcp-settings): defer capability fetches until tab activation (#18550)Cursor Agent26508591on GitHubrefactor(paintings): migrate to v2 data layer and UI (#15154)Cursor Agente59c7aa7on GitHubrefactor(provider-settings): migrate to v2 data layer and UI (#14631)Cursor Agent
04Method
What entered the denominator
The result begins with commit history, removes merges and routine automation, and reports literal agent signatures as a lower bound.
Exclusion ledger
| Commits in window | 3,253 |
| Merge commits removed | −39 |
| CI / dependency bots removed | −61 |
| Considered | 3,153 |
Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.
05Provenance
Pinned to a source state
This observation names the repository state, release, and detector that produced it. Use these identifiers when reproducing or citing the result.
- Dataset release
- 2026-09-18-v3.0
- Scan date
- 2026-09-16
- Ruleset
- sha256:b2e8889c66f72c18a61839f0bf1a9f77b5481ba2def044dba33c797b2f2bdcae
- Canonical repository
- CherryHQ/cherry-studio
- Default branch
- main
- Resolved HEAD
- a3cd46c94c58173369343478c2cd6271c497606f ↗
- Resolved
- 2026-09-16
- Measurement window
- February–September 15, 2026
06Peer context
Position among comparable repositories
The cohort uses the same release and measurement window, then narrows to the repository’s ecosystem and removes low-activity observations.
Midrank percentile; equal shares split the tied positions.
- Repository
- 26.7%
- Cohort median
- 5.4%
- Share rank
- 64 / 376
Percentile = (repositories below + half of 2 tied repositories) ÷ 376.
Continue exploring
Related coding-agent evidence
Run the same detector locally.
Deterministic signature matching; no code-style inference. Squash merges can remove trailers, so this result remains a measured floor.
npx qmmit-cli CherryHQ/cherry-studio