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

01Result

microsoft/TypeScript ↗

microsoft/TypeScript AI coding statistics: 26.8%

of 1,209 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
26.8% agent · top contributor 81.8%18 contributors
individual

One person is driving this. The headline number reflects a single contributor's workflow, not a project-wide shift.

324
agent commits
885
other considered commits
18
agent contributors
81.8%
largest contributor

02Drivers

What shapes this result

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

Assisted or autonomous

324assisted
0autonomous

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
2026-0231.1%190
2026-0317%235
2026-0417.8%152
2026-0542.8%159
2026-0638.3%183
2026-0720.5%117
2026-0822%132
2026-0917.1%41

Peak month: 42.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
GitHub CopilotGitHub31325.9%
Claude CodeAnthropic100.8%
OpenAI CodexOpenAI10.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 879f9867 on GitHub[api] Add program.getResolvedModule and similar (#64247)GitHub Copilot
  • 248cd7ff on GitHub[api] Generate optional protocol properties with `| undefined` so we can sGitHub Copilot
  • 8ab45047 on GitHubAdd security skill (#64238)GitHub Copilot
  • f802c848 on GitHubBuild checker cache keys in an inline buffer with one-shot hashing (microsClaude Code
  • f20c2c2c on GitHubInline `GetCombinedNodeFlags` and `GetCombinedModifierFlags` bodies (microClaude Code
  • c83522a4 on GitHubCheck the arrow-function line-terminator rule without the line map (microsClaude Code
  • 71476b44 on GitHubFix module specifier rename trigger spans (microsoft/typescript-go#4783)OpenAI Codex

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 window1,239
Merge commits removed−1
CI / dependency bots removed−29
Considered1,209

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/TypeScript
Default branch
main
Resolved HEAD
d2b20b35034bd902bdda5974f522ff00352895e9 ↗
Resolved
2026-09-16
Measurement window
February–September 15, 2026
Download observation JSONDeterministic export · same values as this page

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.

CohortGo · 132 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 62 of 194 ecosystem repositories excluded
Agent-commit share position86th percentile

Midrank percentile; equal shares split the tied positions.

Repository
26.8%
Cohort median
2.8%
Share rank
19 / 132
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 132.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →OpenAI Codex commitsBrowse repositories with detected OpenAI Codex signatures →GitHub AI commit analyzerInspect another repository with the same evidence model →
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/TypeScript

Scan another repository

Try