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

HKUDS/DeepCode ↗

HKUDS/DeepCode AI coding statistics: 27.2%

of 298 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
27.2% agent · top contributor 97.5%2 contributors
individual

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

81
agent commits
217
other considered commits
2
agent contributors
97.5%
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

81assisted
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
2026-020%14
2026-030%1
2026-040%17
2026-050%6
2026-0770.8%65
2026-0823.1%147
2026-092.1%48

Peak month: 70.8%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic8127.2%

03Evidence

Inspect the matches

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

Matched commit samples

  • 7df226b4 on GitHubfeat(core): compaction-as-memory sink, <untrusted-data> injection framing,Claude Code
  • eee9f3d9 on GitHubdocs(readme): add news for subagent runtime and compaction batchesClaude Code
  • 4f485541 on GitHubfix(ci): silence the config-layer fixture with an inline gitleaks:allowClaude Code

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 window368
Merge commits removed−70
CI / dependency bots removed−0
Considered298

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
HKUDS/DeepCode
Default branch
main
Resolved HEAD
21ebc57fbcab3e3a238976771a0e06115aa30da6 ↗
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.

CohortPython · 247 eligible repositories · at least 100 considered commits2026-09-18-v3.0 · February–September 15, 2026 · 145 of 392 ecosystem repositories excluded
Agent-commit share position83rd percentile

Midrank percentile; equal shares split the tied positions.

Repository
27.2%
Cohort median
6.3%
Share rank
42 / 247
0th50th100th

Percentile = (repositories below + half of 1 tied repository) ÷ 247.

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code 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 HKUDS/DeepCode

Scan another repository

Try