Pulse
2026-09-18-v3.0
Dataset
2026-09-18-v3.0
Ruleset
b2e8889c66f7
Scanned
2026-09-16
Window
February–September 15, 2026
Local to this browser
microsoft/vscode ↗

microsoft/vscode AI coding statistics: 34.1%

of 15,045 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
34.1% agent · top contributor 8.7%182 contributors
org-wide

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

5,136
agent commits
9,909
other considered commits
182
agent contributors
8.7%
largest contributor

What shapes this result

Mode, timing, and detected signatures show whether the result reflects broad adoption or one concentrated workflow.

Assisted or autonomous

4874assisted
262autonomous

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

Agent-attributed commit share by month
MonthAgent shareConsidered commits
2026-010%1
2026-0211.4%2362
2026-0319.7%2666
2026-0430.7%2229
2026-0525.9%1681
2026-0640.5%1698
2026-0749.4%1669
2026-0860.8%1855
2026-0965.7%884

Peak month: 65.7%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub506833.7%
Claude CodeAnthropic680.5%
Cursor AgentAnysphere70%

Inspect the matches

Public commit samples let you inspect the signatures behind the aggregate result.

Matched commit samples

  • 2e72cd1e on GitHubPreserve native errors in logs for debugger source mapping (#336332)GitHub Copilot
  • b91d3248 on GitHubagentHost: experiment with Copilot skill character budget (#336335)GitHub Copilot
  • aa513800 on GitHubMake hover mouseout dismissal tests deterministic (#336325)GitHub Copilot
  • f9550496 on GitHubFix main process OOM from unconsumed buffered pty host service events (#32Claude Code
  • 1bea02a9 on GitHubsessions: back the checkpoint and fork rows over a chat background (#33498Claude Code
  • 4603a7f7 on GitHubFix terminal-editor shift-drop firing on detached instances (#318756)Claude Code
  • 2df67b33 on GitHubFix Modern UI editor tab decoration color on full label (#325291)Cursor Agent
  • 3855b8b8 on GitHubdebug: right-align toolbar actions in exception widget (#324471)Cursor Agent
  • 4ac53226 on GitHubfix(terminal): track ligatures addon config for change detection (#318992)Cursor Agent

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 window17,589
Merge commits removed−2,145
CI / dependency bots removed−399
Considered15,045

Bots are excluded from the denominator entirely. Agent attribution requires a literal supported signature; no code-style inference is used.

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
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

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.

CohortJS/TS · 376 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 194 of 570 ecosystem repositories excluded
Agent-commit share position87th percentile

Midrank percentile; equal shares split the tied positions.

Repository
34.1%
Cohort median
5.4%
Share rank
50 / 376
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 376.

Reproduce this observation

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

Scan another repository