- Dataset
- 2026-09-18-v3.0
- Ruleset
- b2e8889c66f7
- Scanned
- 2026-09-16
- Window
- February–September 15, 2026
01Result
microsoft/vscode ↗microsoft/vscode AI coding statistics: 34.1%
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 |
|---|---|---|
| 2026-01 | 0% | 1 |
| 2026-02 | 11.4% | 2362 |
| 2026-03 | 19.7% | 2666 |
| 2026-04 | 30.7% | 2229 |
| 2026-05 | 25.9% | 1681 |
| 2026-06 | 40.5% | 1698 |
| 2026-07 | 49.4% | 1669 |
| 2026-08 | 60.8% | 1855 |
| 2026-09 | 65.7% | 884 |
Peak month: 65.7%. Bars are scaled to that peak, not to 100%.
Which agents
| Agent | Vendor | Commits | Share |
|---|---|---|---|
| GitHub Copilot | GitHub | 5068 | 33.7% |
| Claude Code | Anthropic | 68 | 0.5% |
| Cursor Agent | Anysphere | 7 | 0% |
03Evidence
Inspect the matches
Public commit samples let you inspect the signatures behind the aggregate result.
Matched commit samples
2e72cd1eon GitHubPreserve native errors in logs for debugger source mapping (#336332)GitHub Copilotb91d3248on GitHubagentHost: experiment with Copilot skill character budget (#336335)GitHub Copilotaa513800on GitHubMake hover mouseout dismissal tests deterministic (#336325)GitHub Copilotf9550496on GitHubFix main process OOM from unconsumed buffered pty host service events (#32Claude Code1bea02a9on GitHubsessions: back the checkpoint and fork rows over a chat background (#33498Claude Code4603a7f7on GitHubFix terminal-editor shift-drop firing on detached instances (#318756)Claude Code2df67b33on GitHubFix Modern UI editor tab decoration color on full label (#325291)Cursor Agent3855b8b8on GitHubdebug: right-align toolbar actions in exception widget (#324471)Cursor Agent4ac53226on GitHubfix(terminal): track ligatures addon config for change detection (#318992)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 | 17,589 |
| Merge commits removed | −2,145 |
| CI / dependency bots removed | −399 |
| Considered | 15,045 |
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
- microsoft/vscode
- Default branch
- main
- Resolved HEAD
- f80869ac3889f66f437dcbc430b83755ff7d0807 ↗
- 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
- 34.1%
- Cohort median
- 5.4%
- Share rank
- 50 / 376
Percentile = (repositories below + half of 1 tied repository) ÷ 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 microsoft/vscode