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
esengine/DeepSeek-Reasonix ↗

esengine/DeepSeek-Reasonix AI coding statistics: 2.7%

of 5,183 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
2.7% agent · top contributor 53.6%20 contributors
team

A small group is using agents. Adoption has spread beyond one person but is not project-wide.

138
agent commits
5,045
other considered commits
20
agent contributors
53.6%
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

138assisted
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
2026-052%151
2026-066%1640
2026-072%1121
2026-080.7%1613
2026-090.5%658

Peak month: 6%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Cursor AgentAnysphere861.7%
Claude CodeAnthropic480.9%
OpenAI CodexOpenAI30.1%
DevinCognition10%

Inspect the matches

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

Matched commit samples

  • 45889198 on GitHubfix(agent): decouple read coverage from write evidence recoveryCursor Agent
  • 99040648 on GitHubfix(desktop): gray out locked provider name with a rename hint / 灰显供应商名称并提Cursor Agent
  • f53edb59 on GitHubfix(session): fold recovery lineages into one ordinary list row / 恢复谱系折叠为单Cursor Agent
  • c9efeec8 on GitHubfix(desktop): build Windows service as GUI subsystemClaude Code
  • 36d418e6 on GitHubfeat(serve,desktop): multi-session detach, gzip snapshot transport, and crClaude Code
  • 7d88bbe8 on GitHubdocs(boot): restore applyUnifiedProviderToolSurface's doc commentClaude Code
  • 1a87cd4c on GitHubIntegrate clear context telemetry fixes / 集成清空上下文与统计面板修复 (#4329)OpenAI Codex
  • 368dad0e on GitHubfix(desktop): honor user font in UI chrome (#3605)OpenAI Codex
  • f6e6673d on GitHubfeat(desktop): add text size shortcuts (#3576)OpenAI Codex
  • f8758bb5 on GitHubfix(desktop): persist the restore rectangle instead of the maximized frameDevin

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 window7,082
Merge commits removed−1,780
CI / dependency bots removed−119
Considered5,183

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
esengine/DeepSeek-Reasonix
Default branch
main-v2
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.

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 position50th percentile

Midrank percentile; equal shares split the tied positions.

Repository
2.7%
Cohort median
2.8%
Share rank
67 / 132
0th50th100th

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

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 esengine/DeepSeek-Reasonix

Scan another repository