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/LightRAG ↗

HKUDS/LightRAG AI coding statistics: 43.9%

of 3,188 commits in February–September 15, 2026 were committed by an AI agent — a floor, not an estimate
43.9% agent · top contributor 59.7%25 contributors
team

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

1,401
agent commits
1,787
other considered commits
25
agent contributors
59.7%
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

1378assisted
23autonomous

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
2026-0256.6%53
2026-032.8%391
2026-0413.4%268
2026-0529.8%567
2026-0658.5%400
2026-0761%462
2026-0855.2%567
2026-0967.9%480

Peak month: 67.9%. Bars are scaled to that peak, not to 100%.

Which agents

AgentVendorCommitsShare
Claude CodeAnthropic137443.1%
GitHub CopilotGitHub250.8%
Cursor AgentAnysphere20.1%

03Evidence

Inspect the matches

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

Matched commit samples

  • 9546c20c on GitHubfix(pipeline): keep tokens out of the stall fence message, and tell the trClaude Code
  • dbca60ca on GitHubfix(pipeline): let the enqueue-stall fence spare the holders it was raisedClaude Code
  • 70a0761a on GitHubfix(pipeline): re-check the stalled enqueue set inside the lock that fenceClaude Code
  • 42b818ac on GitHubfix: guard Faiss tests with pytest.importorskip and add offline markerGitHub Copilot
  • bac0ed30 on GitHubFix pre-commit ruff-format CI failures in Milvus test file (#11)GitHub Copilot
  • 634b43d4 on GitHubRemove dead code: Delete unused _create_vector_index_fallback methodGitHub Copilot
  • ec41aa48 on GitHubfeature: add full-service comparison artifactsCursor Agent
  • f405bc36 on GitHubtest: add controlled benchmark for entity extraction stabilityCursor 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 window4,481
Merge commits removed−1,150
CI / dependency bots removed−143
Considered3,188

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/LightRAG
Default branch
main
Resolved HEAD
044eac0b5040191fe73a99e2847ba63b30338763 ↗
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 position90th percentile

Midrank percentile; equal shares split the tied positions.

Repository
43.9%
Cohort median
6.3%
Share rank
25 / 247
0th50th100th

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

Continue exploring

Claude Code commitsBrowse repositories with detected Claude Code signatures →GitHub Copilot commitsBrowse repositories with detected GitHub Copilot signatures →Cursor Agent commitsBrowse repositories with detected Cursor Agent 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/LightRAG

Scan another repository

Try